Skill directory · AI agents
AI Agents and LLM Engineering agent skills
Skills that help an agent build, steer and evaluate other AI systems: prompt and context engineering, MCP servers, evals, subagent workflows, and model training and inference. Each one ships as a SKILL.md folder your agent loads only when the task calls for it.
- 599 listed skills
- 68 repositories
- 105 with full pages
Build a shortlist for your task →
All 599 AI agent skills
No matching skills. Try fewer words or clear your search.
| Skill | Repository | What it does |
|---|---|---|
| add-webmcp 83/100 · B | browserbase/skills | Analyzes an existing web application for safe user-visible capabilities, implements first-party WebMCP tools, and validates discovery and invocation with Stagehand. |
| advanced-evaluation 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Guides advanced LLM evaluation, including LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated quality assessment. |
| agent-email-inbox 86/100 · B | resend/resend-skills | Guides building email-triggered systems like AI agent inboxes, using sender allowlists, content filtering, and sandboxed processing to keep untrusted email from controlling the system. |
| agent-experience 74/100 · C | browserbase/skills | Audits the developer experience of a product, SDK, or docs site by sending Claude subagents at it with only a tiny task prompt. |
| agent-platform-deploy 90/100 · A | google/skills | Deploys open models or custom weights from Model Garden to Agent Platform endpoints, checks deployment status and cost, troubleshoots errors, and undeploys models. |
| agent-ready 91/100 · A | mblode/agent-skills | Implements agent-readiness on sites and docs from scorecards like Mintlify Agent Score or AFDocs, including llms.txt coverage and agents hitting 404s on guessed URLs. |
| agent-skills-creator 91/100 · A | mblode/agent-skills | Creates and improves portable Agent Skills using a validator and routing scenarios, with evidence-based decisions to keep, cut, merge, or retire skills. |
| agenttrace-session-audit 78/100 · C | luoyuctl/agenttrace | Audits local AI coding-agent sessions from tools like Claude Code and Codex CLI with agenttrace, checking cost, tokens, tool failures, latency, and anomalies. |
| appie-chatbot 77/100 · C | appierun/appie-mcp | Create and train chatbots on text, URLs, sitemaps or articles through Appie.run’s hosted MCP service with your own project API key; chatbot messages use 1 credit each. |
| autobrowse 83/100 · B | browserbase/skills | Improves browser automation through an iterative loop that runs a browsing task, reads the trace, and refines the navigation strategy until it reliably passes. |
| autonomous-investigation 81/100 · B | deanpeters/Product-Manager-Skills | Defines the protocol behind investigation skills for unattended AI research, using a search-plan gate, Fact, Inference, and Assumption labels, confidence stacking, and diffable outputs. |
| aws-agentic-ai 83/100 · B | zxkane/aws-skills | Guides deploying and managing AI agents on AWS Bedrock AgentCore, covering Gateway, Runtime, Memory, Identity, Observability, Evaluations, MCP tool integration, and governance workflows. |
| aws-mcp-setup 80/100 · B | zxkane/aws-skills | Configures AWS MCP servers for documentation search and API access, covering both the full AWS MCP Server and the lightweight Documentation MCP. |
| ax-extract-workflow 84/100 · B | Necmttn/ax | Reconstructs the workflow behind a past artifact by using ax to find relevant sessions and narrate the ordered skill arcs that produced it. |
| bmad-run-inspector 90/100 · A | tronghieu/agent-skills | Inspects and explains bmad-loop run artifacts for live health checks and post-run forensics, such as why a story failed or where tokens went. |
| build-models 71/100 · C | replicate/skills | Packages and builds custom AI models with Cog for deployment on Replicate, including cog.yaml, predict.py, model inputs and outputs, and Docker images. |
| chat-history 91/100 · A | mblode/agent-skills | Recovers decisions, previous fixes, and research from past AI conversations with source evidence, reading local Claude Code, Codex, Grok, and Cursor history. |
| coding-agent 75/100 · C | swarmclawai/swarmclaw | Delegates coding tasks to external coding agents such as Claude Code, Codex, Pi, and OpenCode via shell, including new features, PR reviews, and refactoring. |
| context-compression 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Guides compression of long-running agent sessions through structured summarization, compaction, and durable handoff summaries that preserve decisions, files, risks, and next actions. |
| context-degradation 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Diagnoses and mitigates context degradation, including lost-in-middle failures, context poisoning, context clash, context confusion, and performance problems caused by accumulated or conflicting context. |
| context-fundamentals 84/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Explains the foundations of context engineering, including the anatomy of a context window, attention mechanics, and why context quality matters more than quantity. |
| context-optimization 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Improves context efficiency through context budgeting, observation masking, KV-cache strategy, partitioning, and token-cost reduction, extending effective context capacity without lowering answer quality. |
| conversation-analyzer 77/100 · C | mhattingpete/claude-skills-marketplace | Analyzes Claude Code conversation history to identify patterns, common mistakes, and opportunities for workflow improvement and automation. |
| create-voltagent 68/100 · D | VoltAgent/skills | Guides creating AI agent projects with the VoltAgent framework, using either CLI setup or manual bootstrapping. |
| data-structure-protocol 82/100 · B | k-kolomeitsev/data-structure-protocol | Builds and navigates a graph-based structural memory of codebases for LLM agents, storing modules, functions, dependencies, public APIs, and the reasons for each connection. |
| diagnosing-superpowers 90/100 · A | obra/superpowers | Diagnoses why a superpowers session went wrong, such as repeated work or ignored plans, and helps build a bug report for maintainers. |
| dispatching-parallel-agents 82/100 · B | obra/superpowers | Guides splitting two or more independent tasks, with no shared state or sequential dependencies, across parallel agents. |
| dojo 82/100 · B | Necmttn/ax | Runs a self-improvement loop over the ax graph using surplus plan quota, locking pending verdicts, backtesting routing classes, and drafting upstream issue reports. |
| efficient-dispatch 82/100 · B | Necmttn/ax | Routes mechanical subagent work to an explicit cheaper model while the main frontier model keeps judgment and review, and ax measures whether routing worked. |
| ensemble-solving 81/100 · B | mhattingpete/claude-skills-marketplace | Generates multiple diverse solutions in parallel and selects the best, for architecture decisions, code generation with several valid approaches, or creative tasks. |
| evaluation 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Guides building agent evaluation systems with deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baseline comparison, and outcome measurement for agent pipelines. |
| executing-plans 83/100 · B | obra/superpowers | Guides executing an implementation plan inline in the current session as the implementer, when inline execution is chosen or no subagent tool is available. |
| filesystem-context 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Guides file-backed context for agent work, including durable scratchpads, tool-output offloading, cross-agent handoff files, and cleanup policies for context stored outside the prompt. |
| find-skills 81/100 · B | vercel-labs/skills | Helps users discover and install agent skills when they ask how to do something or look for a skill that extends capabilities. |
| firebase-ai-logic-basics 80/100 · B | firebase/skills | Integrates Firebase AI Logic into mobile and web apps to call Gemini models from client code for text generation, multimodal input, chat, and streaming. |
| gemini 74/100 · C | nowork-studio/NotFair | Gets a cross-model second opinion from Google Gemini by reviewing changes, stress-testing them, or answering questions about Google Ads, SEO, or implementation. |
| google-cloud-solution-rag-enterprise-search-gke-sqldb 87/100 · B | google/skills | Generates architecture, design, and deployment guidance for a RAG-capable enterprise search system on Google Cloud, using a vector-enabled SQL database and Kubernetes containers. |
| grok-build 87/100 · B | sanjay3290/ai-skills | Delegates well-specified implementation tasks to xAI's Grok Build CLI running headlessly while the assistant writes task specs, reviews every diff, and owns the result. |
| hosted-agents 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Guides design of hosted or background agent infrastructure, including sandboxed execution, remote coding environments, warm pools, session persistence, multiplayer collaboration, and self-spawning agents. |
| huggingface-community-evals 86/100 · B | huggingface/skills | Runs evaluations for Hugging Face Hub models on local hardware using inspect-ai and lighteval, including backend selection and choosing between vLLM, Transformers, and accelerate. |
| huggingface-local-models 80/100 · B | huggingface/skills | Selects models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm, covering quant selection, conversion, and OpenAI-compatible serving. |
| huggingface-lora-space-builder 75/100 · C | huggingface/skills | Builds and publishes a Gradio demo on Hugging Face Spaces for a user-provided LoRA, including the base pipeline and a task-specific UI. |
| huggingface-trackio 83/100 · B | huggingface/skills | Tracks and visualizes ML training experiments with Trackio, including metric logging, training alerts with webhooks, real-time dashboards, and metric retrieval through the CLI. |
| huggingface-zerogpu 85/100 · B | huggingface/skills | Guides writing and reviewing Gradio code for Hugging Face ZeroGPU Spaces, covering @spaces.GPU usage, requirements configuration, and ZeroGPU-specific constraints like pickle isolation. |
| init 75/100 · C | mcollina/skills | Creates, updates, or optimizes a repository's AGENTS.md file with minimal instructions on conventions, tooling quirks, and rules agents cannot infer from the code. |
| iris-development 75/100 · C | redis/agent-skills | Guides work with the Iris Redis Agent Memory data plane on Redis Cloud, covering session events, long-term memories, store configuration, and memory promotion. |
| knowledge-distillation 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Compresses large language models into smaller student models using knowledge distillation, covering temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training. |
| langchain 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Guides building LLM-powered applications with LangChain, including agents, chains, RAG, tool calling, memory management, and vector store retrieval across multiple providers. |
| let-fate-decide 94/100 · A | trailofbits/skills | Draws a Tarot spread to inject entropy into planning when prompts are vague or casually delegated, and interprets the spread to guide next steps. |
| llava 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Guides visual instruction tuning and image-based conversations with LLaVA, which combines a CLIP vision encoder with Vicuna or LLaMA models for visual question answering. |
| manus 87/100 · B | sanjay3290/ai-skills | Delegates complex, long-running tasks to the Manus AI agent for autonomous execution, such as deep web research, market analysis, product comparisons, and stock analysis. |
| mcp-builder 89/100 · B | anthropics/skills | Guides building MCP servers that let LLMs use external services through tools, in Python with FastMCP or TypeScript with the MCP SDK. |
| memory-systems 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Supports persistent semantic memory in agent systems, including cross-session knowledge retention, entity tracking, graph or vector retrieval, memory consolidation, and memory benchmark selection. |
| mine 75/100 · C | ohad6k/emulo | Runs, sets up, updates, re-mines, or deepens Emulo from the user's real local AI coding-session history, only when explicitly asked. |
| ml-training-recipes 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Provides PyTorch training recipes for LLMs, vision, diffusion, and genomics, covering training loops, optimizers, learning rate schedules, mixed precision, debugging, and GPU throughput. |
| model-merging 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Merges multiple fine-tuned models with mergekit to combine capabilities without retraining, using methods such as SLERP, TIES-Merging, DARE, and Task Arithmetic. |
| model-pruning 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Reduces LLM size and speeds inference with pruning techniques like Wanda and SparseGPT, without retraining, including structured, unstructured, N:M, and magnitude pruning. |
| multi-agent-patterns 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Guides design of multi-agent systems with context isolation, supervisor or swarm coordination, explicit handoffs, and parallel execution, including whether multiple agents are justified. |
| multi-agent-patterns 75/100 · C | NeoLabHQ/context-engineering-kit | Guides designing multi-agent architectures for complex tasks, useful when single-agent context limits are exceeded, tasks decompose into subtasks, or specialized agents improve quality. |
| optimize-agent-prompt 81/100 · B | browserbase/skills | Builds and improves Browserbase Agent API demos by running a fixed task, collecting logs, scoring results, revising one system-prompt heuristic, and confirming convergence. |
| orca-replay 86/100 · B | Continuum-AI-Corp/OrcaReplay | Answers questions about a past agent run from its recording rather than memory, and replays or forks that run. |
| physical-ai-video-data-augmentation 83/100 · B | NVIDIA/skills | Runs video data augmentation and auto-labeling workflows on OSMO, covering flow selection, preflight, submit-time interpolation, monitoring, and output retrieval. |
| project-development 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Guides project-level decisions for LLM-powered systems, including whether an LLM fits the task, token and cost estimation, and single-agent versus multi-agent choices. |
| prompt-optimizer 81/100 · B | getsentry/skills | Creates and refines agent, system, and developer prompts and reusable prompt templates, including porting prompts between OpenAI, Claude, and Gemini and building prompt evals. |
| recursive-decomposition 78/100 · C | massimodeluisa/recursive-decomposition-skill | Decomposes dense codebase-wide, multi-document, and large PDF analysis, following Recursive Language Models research, to aggregate or reason across many scattered sources. |
| redis-semantic-cache 75/100 · C | redis/agent-skills | Guides semantic caching of LLM responses with Redis LangCache on Redis Cloud, including search and set calls, similarity threshold tuning, and per-task caches. |
| retro 82/100 · B | Necmttn/ax | Walks the user through an ax retrospective, triaging open proposals, confirming or overriding pending verdicts, and reviewing recent harness-hook effectiveness signals. |
| retro-meta 84/100 · B | Necmttn/ax | Runs a deep retrospective across older ax retros and the current ax setup to surface improvements, with an external AI agent driving the reasoning. |
| safe-browser 75/100 · C | browserbase/skills | Builds constrained-browser agents whose safe_browser tool enforces a domain allowlist, so an agent can browse without raw browser, shell, or CDP access. |
| sentence-transformers 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Generates sentence, text, and image embeddings with 5000+ pre-trained models for semantic similarity, clustering, retrieval, RAG, and semantic search. |
| sentencepiece 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Guides training language-independent SentencePiece tokenizers with BPE or Unigram directly on raw text, for multilingual, CJK, and reproducible tokenization needs. |
| simple-man 78/100 · C | Maksim-Burtsev/simple-man | Switches to a compact communication mode with no filler, giving terse technical answers and short coding-agent status updates without reducing effort or accuracy. |
| skeptical-triage 82/100 · B | avelikiy/great_cto | Filters false positives from findings and verdicts with a three-round self-challenge and arbiter pattern, when a false-positive block costs more than extra LLM turns. |
| skill-builder 81/100 · B | yusufkaraaslan/Skill_Seekers | Detects source types automatically and builds AI skills with Skill Seekers from documentation, repos, PDFs, videos, or other knowledge sources. |
| skill-creator 83/100 · B | anthropics/skills | Guides creating new skills, improving existing ones, running evals, benchmarking skill performance with variance analysis, and optimizing a skill's description for better triggering. |
| skill-creator 79/100 · C | swarmclawai/swarmclaw | Creates, edits, improves, and audits skills for SwarmClaw agents, including restructuring a skill directory or tidying an existing SKILL.md file. |
| skill-generalizer 74/100 · C | hqhq1025/skill-optimizer | Turns local or personal Agent Skills into publishable ones by removing private paths, personal habits, credentials, internal hosts, and user-specific context. |
| skill-miner 76/100 · C | hqhq1025/skill-optimizer | Mines coding-agent session history, archived transcripts, memories, and repeated local work to discover recurring workflows that should become new Agent Skills. |
| skill-optimizer 74/100 · C | mcollina/skills | Optimizes AI skills for activation, clarity, and cross-model reliability, including diagnosing weak skill uptake, shrinking context cost, and setting benchmark and release gates. |
| skill-personalizer 74/100 · C | hqhq1025/skill-optimizer | Audits and adapts new, downloaded, forked, or community Agent Skills to the user's tools, habits, directories, and workflows, especially when triggers feel wrong. |
| skill-writer 86/100 · B | getsentry/skills | Creates, synthesizes, and iteratively improves agent skills following the Agent Skills specification, including source capture, precision passes, authoring, registration, and validation. |
| slicing-code-context 89/100 · B | trailofbits/skills | Selects bounded, graph-informed source slices with Trailmark and delegates focused code analysis or patch-proposal work to a smaller subagent. |
| speculative-decoding 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Accelerates LLM inference with speculative decoding, Medusa multiple heads, and lookahead decoding, covering draft models, tree-based attention, and parallel token generation. |
| subagent-driven-development 78/100 · C | NeoLabHQ/context-engineering-kit | Executes implementation plans by dispatching a fresh subagent per independent task, with code review between tasks to enable fast iteration with quality gates. |
| swarmclaw 74/100 · C | swarmclawai/swarmclaw | Teaches agents running on SwarmClaw how to use its 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. |
| tao-analyze-detection-kpi 90/100 · A | NVIDIA/skills | Runs TAO Data Services KPI analysis for object detection, comparing inference annotations with ground truth to compute per-class TP/FP/FN/TN, precision, recall, accuracy, and AP. |
| tao-run-deft-cr-its-mining 87/100 · B | NVIDIA/skills | Runs a mining-based DEFT improvement loop for ITS Cosmos-Reason binary video questions, focusing on classification and evaluation without reasoning, driven by gap analysis. |
| tao-run-deft-object-detection 92/100 · A | NVIDIA/skills | Runs the DEFT data augmentation loop for Grounding DINO object detection, with baseline inference, gap analysis, unique-neighbor mining, retraining, and source pool preparation. |
| tao-validate-recipe-transfer 88/100 · B | NVIDIA/skills | Ports a published computer vision paper's code and training recipe onto a customer's dataset, and diagnoses why such transfers give bad results. |
| test-skill 78/100 · C | NeoLabHQ/context-engineering-kit | Tests skills before deployment by running a baseline without the skill, writing fixes for failures, and iterating to close loopholes under pressure. |
| tool-design 86/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | Guides the tool-interface layer of agent systems, including tool descriptions, schemas, response formats, error recovery messages, MCP server design, and adding or removing tools. |
| train-sentence-transformers 83/100 · B | huggingface/skills | Trains and fine-tunes sentence-transformers models, including bi-encoders, cross-encoders, sparse encoders, and multi-vector encoders, with guidance on loss selection, hard-negative mining, evaluators, and Hub publishing. |
| tune 86/100 · B | Necmttn/ax | Reviews one coding session and proposes changes to the agent's hooks, checks, steering files, and tool access, filing each as an ax proposal. |
| unbrowse 83/100 · B | unbrowse-ai/unbrowse | Searches and calls websites through Unbrowse's API or remote MCP, reusing indexed site tools, reading pages, and learning missing routes in its cloud browser. |
| using-superpowers 84/100 · B | obra/superpowers | Establishes how to find and use skills at the start of any conversation, requiring skill invocation before any response, including clarifying questions. |
| utility-pm-skill-iterate 83/100 · B | product-on-purpose/pm-skills | Applies targeted improvements to an existing pm-skills skill based on feedback or validation reports, previews changes, writes on confirmation, and suggests a version bump. |
| utility-pm-skill-validate 83/100 · B | product-on-purpose/pm-skills | Audits an existing pm-skills skill against structural conventions and quality criteria, producing a validation report with pass/fail checks, severity-graded findings, and recommendations. |
| utility-pm-workflow-builder 83/100 · B | product-on-purpose/pm-skills | Guides a contributor from a workflow idea to a Workflow Implementation Packet, running overlap analysis against existing workflows and helping select and sequence skills. |
| utility-update-pm-skills 83/100 · B | product-on-purpose/pm-skills | Compares the locally installed pm-skills version against the latest public release and updates local files with conflict-aware overwrite-or-skip options, producing an update report. |
| venice-models 78/100 · C | veniceai/skills | Discovers Venice models, their capabilities, constraints, and pricing through the models endpoints, so the right model can be picked programmatically. |
Show the other 499 AI agent skills
| Skill | Repository | What it does |
|---|---|---|
| venice-text-routing 80/100 · B | veniceai/skills | Routes a prompt to the right Venice text model based on privacy tier, modality, capability, uncensored needs, and cost, when a local agent escalates. |
| verification-before-completion 84/100 · B | obra/superpowers | Requires running verification commands and confirming their output before claiming work is complete, fixed, or passing, and before committing or creating pull requests. |
| voltagent-docs-bundle 62/100 · D | VoltAgent/skills | Looks up VoltAgent documentation embedded in node_modules for version-matched API signatures, guides, and examples. |
| work 77/100 · C | ohad6k/emulo | Guides execution, debugging, verification, planning, and shipping so the work follows the user's Emulo working profile, excluding design, marketing writing, and Emulo setup. |
| writing-plans 80/100 · B | obra/superpowers | Guides writing a plan from a spec or requirements for a multi-step task, before touching any code. |
| acquire-codebase-knowledge 87/100 · B | github/awesome-copilot | Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase"… |
| acreadiness-generate-instructions 69/100 · D | github/awesome-copilot | Generate tailored AI agent instruction files via AgentRC instructions command. Produces .github/copilot-instructions.md (default, recommended for… |
| actualize 66/100 · D | NeoLabHQ/context-engineering-kit | Reconcile the project's FPF state with recent repository changes |
| add-educational-comments 67/100 · D | github/awesome-copilot | Add educational comments to the file specified, or prompt asking for file to comment if one is not provided. |
| agent-advisor 82/100 · B | aws/agent-toolkit-for-aws | Entry point for AI-agent work on AWS: pick a runtime, plan a migration for existing workloads, and build an executable POC — one phased flow… |
| agent-architecture 72/100 · C | github/awesome-copilot | Design AI agent architectures through requirements discovery, or audit and diagnose architectural flaws in existing agents. Architecture only… |
| agent-development 86/100 · B | anthropics/claude-plugins-official | This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use… |
| agent-evaluation 64/100 · D | NeoLabHQ/context-engineering-kit | Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or… |
| agent-governance 67/100 · D | github/awesome-copilot | Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call… |
| agent-orchestration-advisor 70/100 · C | deanpeters/Product-Manager-Skills | Design multi-agent AI workflows with clear boundaries, handoffs, and monitoring. Use when a complex PM task should run as parallel specialized… |
| agent-platform-endpoint-management 84/100 · B | google/skills | Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on… |
| agent-platform-eval-flywheel 74/100 · C | google/skills | Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when generating synthetic… |
| agent-platform-inference 70/100 · C | google/skills | Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS… |
| agent-platform-model-registry 84/100 · B | google/skills | Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their… |
| agent-platform-prompt-management 87/100 · B | google/skills | Manages and orchestrates prompts in Agent Platform. Use when you need to create, list, retrieve, version, or delete managed prompts in Agent… |
| agent-platform-rag-engine-management 84/100 · B | google/skills | Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files… |
| agent-platform-skill-registry 79/100 · C | google/skills | Interact with the Gemini Enterprise Agent Platform Skill Registry to create and search for available skills. Use this skill to enable agents to… |
| agent-platform-tuning 75/100 · C | google/skills | Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model… |
| agent-platform-tuning-management 84/100 · B | google/skills | Manages GenAI tuning jobs in Agent Platform. Use this to list, get, or cancel ongoing model tuning jobs. Don't use for fine-tuning models (use… |
| agent-skill-stack 84/100 · B | github/awesome-copilot | Find, evaluate, and assemble the smallest compatible set of AI Agent Skills for an end-to-end natural-language goal. Use when a user wants Skills… |
| agent-supply-chain 80/100 · B | github/awesome-copilot | Verify supply chain integrity for AI agent plugins, tools, and dependencies. Use this skill when: - Generating SHA-256 integrity manifests for agent… |
| agent-usability-test 63/100 · D | serpapi/skills | Test whether agents can discover and use your tool — not whether agents are capable. The subject under test is the interface. A bad score means fix… |
| agentic-eval 77/100 · C | github/awesome-copilot | Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops… |
| agents-build 83/100 · B | aws/agent-toolkit-for-aws | Use to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments, or… |
| agents-connect 74/100 · C | aws/agent-toolkit-for-aws | Use when connecting your agent to external APIs, tools, or services via Gateway, or restricting tool access with Cedar policies. Handles gateway… |
| agents-debug 76/100 · C | aws/agent-toolkit-for-aws | Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to diagnose root… |
| agents-get-started 87/100 · B | aws/agent-toolkit-for-aws | Use when a developer wants to create a new agent project or get started with AgentCore. Handles framework selection, project scaffolding, first… |
| agents-harden 74/100 · C | aws/agent-toolkit-for-aws | Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session… |
| agents-md 75/100 · C | getsentry/skills | Creates and maintains concise AGENTS.md and CLAUDE.md project instruction files. Use when asked to create AGENTS.md, update AGENTS.md, maintain… |
| agents-md 87/100 · B | mblode/agent-skills | Audits and edits agent instruction files, verifies repository commands, and migrates repositories to AGENTS.md as the single shared source. Use when… |
| agents-optimize 84/100 · B | aws/agent-toolkit-for-aws | Use when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI/CD quality gates, observability, or cost… |
| agents-pay 78/100 · C | aws/agent-toolkit-for-aws | Use when THIS agent needs to pay for x402-protected content at runtime: hitting a paywall mid-task, settling it via AgentCore Payments, and applying… |
| agents-sdk 69/100 · D | cloudflare/skills | Build, debug, or review Cloudflare Agents SDK applications using the agents package. |
| ai-prompt-engineering-safety-review 69/100 · D | github/awesome-copilot | Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and… |
| ai-ready 74/100 · C | github/awesome-copilot | Make any repo AI-ready — analyzes your codebase and generates AGENTS.md, copilot-instructions.md, CI workflows, issue templates, and more. Mines… |
| amazon-bedrock 71/100 · C | aws/agent-toolkit-for-aws | Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents… |
| amazon-elasticache 78/100 · C | aws/agent-toolkit-for-aws | Activate when developers have latent caching needs: slow API responses, database read bottlenecks, DynamoDB throttling or cost, RDS/Aurora scaling… |
| amazon-workspaces-agent-access 83/100 · B | aws/agent-toolkit-for-aws | Connects AI agents to remote Windows desktop applications on Amazon WorkSpaces Applications (AppStream 2.0) through the managed Agent Access MCP… |
| ambient-healthcare-agent-with-nemotron-voice-agent 77/100 · C | NVIDIA/skills | Customize NVIDIA Nemotron Voice Agent's Generic Pipecat example for healthcare appointment, five-field patient intake, or custom tool-calling… |
| api-ai-augmented 73/100 · C | LambdaTest/agent-skills | Designs AI-powered API features, LLM tool/function definitions, MCP server tool schemas, natural language to API conversion, and agentic API… |
| api-gateway-mcp-server 89/100 · B | google/skills | Configures Google Cloud API Gateway to act as a remote Model Context Protocol (MCP) server (Public Preview) that exposes REST APIs as agent tools… |
| apify-integration-development 80/100 · B | apify/agent-skills | Design and build an official Apify integration for a company's product - workflow-automation apps (Zapier/n8n-style), AI agent plugins (coding-agent… |
| apollo-mcp-server 84/100 · B | apollographql/skills | Guide for using Apollo MCP Server to connect AI agents with GraphQL APIs. Use this skill when: (1) setting up or configuring Apollo MCP Server, (2)… |
| apply-anthropic-skill-best-practices 62/100 · D | NeoLabHQ/context-engineering-kit | Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure |
| arize-ai-provider-integration 82/100 · B | github/awesome-copilot | Creates, reads, updates, and deletes Arize AI integrations that store LLM provider credentials used by evaluators and other Arize features. Supports… |
| arize-evaluator 68/100 · D | github/awesome-copilot | Handles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing… |
| arize-instrumentation 82/100 · B | github/awesome-copilot | Adds Arize AX tracing to an LLM application for the first time. Follows a two-phase agent-assisted flow to analyze the codebase then implement… |
| arize-prompt-optimization 82/100 · B | github/awesome-copilot | Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers… |
| arize-trace 79/100 · C | github/awesome-copilot | Downloads, exports, and inspects existing Arize traces and spans to understand what an LLM app is doing or debug runtime issues. Covers exporting… |
| autogpt-agents 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous… |
| autoskill 89/100 · B | K-Dense-AI/claude-scientific-skills | Analyzes user-requested Screenpipe history windows to detect repeated research workflows, match existing scientific skills, and stage new skill… |
| awq-quantization 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B)… |
| aws-network-monitoring 69/100 · D | aws/agent-toolkit-for-aws | Installs, configures, and troubleshoots Network Flow Monitor agents on EC2 instances to monitor network path health. Covers agent installation, IAM… |
| ax-audit 87/100 · B | mblode/agent-skills | Audits agentic products for tool parity, authority, approval payloads, recovery, and trust using 24 rules and a ship verdict. Use when asked for an… |
| ax-narrate 76/100 · C | Necmttn/ax | Write the agent-generated narration of the current session - the reviewable story of what changed, including what never reaches a PR (user… |
| axolotl 67/100 · D | Orchestra-Research/AI-Research-SKILLs | Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support |
| azure-aigateway 71/100 · C | microsoft/azure-skills | Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load… |
| bdi-mental-states 84/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions, RDF-to-belief transformations, rational… |
| birdview-compatibility 73/100 · C | Qiuner/birdview | Audit the installed AI skill environment for duplicate installations, broad triggers and possible instruction conflicts. Use only when the user… |
| boost-prompt 63/100 · D | github/awesome-copilot | Interactive prompt refinement workflow: interrogates scope, deliverables, constraints; copies final markdown to clipboard; never writes code… |
| brainstorming 68/100 · D | infrasity-labs/dev-gtm-claude-skills | You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user… |
| brainstorming 78/100 · C | obra/superpowers | You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything… |
| breakdown-epic-arch 72/100 · C | github/awesome-copilot | Prompt for creating the high-level technical architecture for an Epic, based on a Product Requirements Document. |
| breakdown-feature-implementation 73/100 · C | github/awesome-copilot | Prompt for creating detailed feature implementation plans, following Epoch monorepo structure. |
| breakdown-feature-prd 70/100 · C | github/awesome-copilot | Prompt for creating Product Requirements Documents (PRDs) for new features, based on an Epic. |
| build-mcp-app 84/100 · B | anthropics/claude-plugins-official | This skill should be used when the user wants to build an "MCP app", add "interactive UI" or "widgets" to an MCP server, "render components in… |
| build-mcp-server 84/100 · B | anthropics/claude-plugins-official | This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose… |
| build-mcpb 84/100 · B | anthropics/claude-plugins-official | This skill should be used when the user wants to "package an MCP server", "bundle an MCP", "make an MCPB", "ship a local MCP server", "distribute a… |
| chrome-mcp-troubleshooting 87/100 · B | trailofbits/skills | Diagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools fail, return "Browser extension is not… |
| claude-automation-recommender 81/100 · B | anthropics/claude-plugins-official | Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation… |
| cli-mastery 69/100 · D | github/awesome-copilot | Interactive training for the GitHub Copilot CLI. Guided lessons, quizzes, scenario challenges, and a full reference covering slash commands… |
| clip 77/100 · C | Orchestra-Research/AI-Research-SKILLs | OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on… |
| code-execution 75/100 · C | mhattingpete/claude-skills-marketplace | Execute Python code locally with marketplace API access for 90%+ token savings on bulk operations. Activates when user requests bulk operations (10+… |
| code-exemplars-blueprint-generator 69/100 · D | github/awesome-copilot | Technology-agnostic prompt generator that creates customizable AI prompts for scanning codebases and identifying high-quality code exemplars… |
| codebase-memory-mcp 77/100 · C | github/awesome-copilot | Use when exploring unfamiliar code, mapping architecture, finding symbols or relationships, tracing callers, callees, data flow or dependencies… |
| codex-host 69/100 · D | avelikiy/great_cto | Run the great_cto controlled Codex lifecycle with controller-owned writes, verifier evidence, human gates and optional artifact release. |
| compare-models 57/100 · D | replicate/skills | Compare Replicate models by cost, speed, quality, and capabilities. |
| composio 56/100 · D | composiohq/skills | Use 1000+ external apps via Composio - either directly through the CLI or by building AI agents and apps with the SDK |
| constitutional-ai 74/100 · C | Orchestra-Research/AI-Research-SKILLs | Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then… |
| context-engineering 64/100 · D | NeoLabHQ/context-engineering-kit | Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or… |
| context-engineering-advisor 68/100 · D | deanpeters/Product-Manager-Skills | Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably. |
| context-engineering-collection 76/100 · C | muratcankoylan/Agent-Skills-for-Context-Engineering | A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems… |
| conventional-commit 74/100 · C | github/awesome-copilot | Prompt and workflow for generating conventional commit messages using a structured XML format. Guides users to create standardized, descriptive… |
| convert-plaintext-to-md 69/100 · D | github/awesome-copilot | Convert a text-based document to markdown following instructions from prompt, or if a documented option is passed, follow the instructions for that… |
| copilot-sdk 69/100 · D | github/awesome-copilot | Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses… |
| create-agent 70/100 · C | NeoLabHQ/context-engineering-kit | Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official… |
| create-agentsmd 73/100 · C | github/awesome-copilot | Prompt for generating an AGENTS.md file for a repository |
| create-command 68/100 · D | NeoLabHQ/context-engineering-kit | Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration |
| create-llms 67/100 · D | github/awesome-copilot | Create an llms.txt file from scratch based on repository structure following the llms.txt specification at https://llmstxt.org/ |
| create-rule 70/100 · C | NeoLabHQ/context-engineering-kit | Use when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time when you say "You absolutly right… |
| create-skill 67/100 · D | NeoLabHQ/context-engineering-kit | Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends… |
| create-workflow-command 68/100 · D | NeoLabHQ/context-engineering-kit | Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts |
| crewai-multi-agent 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex… |
| crystallize 71/100 · C | avelikiy/great_cto | Distils repeating patterns from session logs and lessons.md into draft skill files. Run after ≥10 sessions to extract durable knowledge. Output… |
| decay 66/100 · D | NeoLabHQ/context-engineering-kit | Manage evidence freshness by identifying stale decisions and providing governance actions |
| decision-eval 71/100 · C | avelikiy/great_cto | Spawns the decision-scorer agent after architect proposes 2+ variants in an ADR. Produces a weighted scoring table and recommended choice saved to… |
| declarative-agents 69/100 · D | github/awesome-copilot | Complete development kit for Microsoft 365 Copilot declarative agents with three comprehensive workflows (basic, advanced, validation), TypeSpec… |
| deep-agents-core 77/100 · C | langchain-ai/langchain-skills | INVOKE THIS SKILL when building ANY Deep Agents application. Covers create_deep_agent(), harness architecture, SKILL.md format, and configuration… |
| deep-agents-memory 77/100 · C | langchain-ai/langchain-skills | INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent)… |
| deep-agents-orchestration 69/100 · D | langchain-ai/langchain-skills | INVOKE THIS SKILL when using subagents, task planning, or human approval in Deep Agents. Covers SubAgentMiddleware, TodoList for planning, and HITL… |
| deepagents-python-quickstart 74/100 · C | langchain-ai/langchain-skills | Scaffold a minimal local Deep Agent in Python by following the official quickstart, using provider-native web search instead of Tavily. Use when the… |
| deepagents-typescript-quickstart 74/100 · C | langchain-ai/langchain-skills | Scaffold a minimal local Deep Agent in TypeScript by following the official quickstart, using provider-native web search instead of Tavily. Use when… |
| deepspeed 61/100 · D | Orchestra-Research/AI-Research-SKILLs | Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention |
| deepstream-import-vision-model 83/100 · B | NVIDIA/skills | Use this skill to bring a supported object-detection vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end… |
| deepstream-sop 77/100 · C | NVIDIA/skills | Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a… |
| developing-genkit-dart 83/100 · B | google/skills | Generates code and provides documentation for the Genkit Dart SDK. Use when the user asks to build AI agents in Dart, use Genkit flows, or integrate… |
| developing-genkit-go 83/100 · B | google/skills | Develop AI-powered applications using Genkit in Go. Use when the user asks to build AI features, agents, flows, or tools in Go using Genkit, or when… |
| developing-genkit-js 83/100 · B | google/skills | Develop AI-powered applications using Genkit in Node.js/TypeScript. Use when the user asks about Genkit, AI agents, flows, or tools in… |
| developing-genkit-python 83/100 · B | google/skills | Develop AI-powered applications using Genkit in Python. Use when the user asks about Genkit, AI agents, flows, or tools in Python, or when… |
| diagnose 69/100 · D | github/awesome-copilot | Perform a systematic diagnostic scan of an AI workflow across 5 quality dimensions — prompt quality, context efficiency, tool health, architecture… |
| digital-health-clinical-asr-build 87/100 · B | NVIDIA/skills | Stage 2 of the Clinical ASR Flywheel. Use when curating clinical terms, tagging IPA, and synthesizing a NeMo manifest. NOT for scoring (use… |
| digital-health-clinical-asr-eval 79/100 · C | NVIDIA/skills | Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diagnostic). Not for ASR auth… |
| digital-health-clinical-asr-finetune 87/100 · B | NVIDIA/skills | Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT… |
| digital-health-clinical-asr-setup 81/100 · B | NVIDIA/skills | Stage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps install, TTS+ASR smoke test. |
| distributed-llm-pretraining-torchtitan 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1… |
| do-in-parallel 64/100 · D | NeoLabHQ/context-engineering-kit | Run independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge… |
| do-in-steps 64/100 · D | NeoLabHQ/context-engineering-kit | Execute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge… |
| done-blocked 77/100 · C | avelikiy/great_cto | Reusable reporting contract for any agent that hands work back to the pipeline. Forces ONE of two terminal statuses (DONE or BLOCKED) with a… |
| dotnet-mcp-builder 79/100 · C | github/awesome-copilot | Build Model Context Protocol (MCP) servers in C#/.NET against the current ModelContextProtocol 2.x NuGet packages. Helps with cases the model gets… |
| dotnet-upgrade 65/100 · D | github/awesome-copilot | Ready-to-use prompts for comprehensive .NET framework upgrade analysis and execution |
| ecosystem-primer 69/100 · D | langchain-ai/langchain-skills | INVOKE FIRST for any LangChain / LangGraph / Deep Agents agent building project before consulting other skills or writing any agent code. Required… |
| entra-agent-id 84/100 · B | microsoft/azure-skills | Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth… |
| entra-agent-user 69/100 · D | github/awesome-copilot | Create Agent Users in Microsoft Entra ID from Agent Identities, enabling AI agents to act as digital workers with user identity capabilities in… |
| ethos-explore 79/100 · C | NVIDIA/skills | Captures what an AI agent is supposed to do — its purpose, boundaries, and success criteria — as a durable snapshot for anyone building, evaluating… |
| ethos-orchestrate 85/100 · B | NVIDIA/skills | Entry point for an AI agent's ethos.md: a durable snapshot of what the agent is for, what it must not do, and what success looks like. Routes a… |
| ethos-write 79/100 · C | NVIDIA/skills | Writes an AI agent's ethos.md — a durable snapshot of its purpose, intended behavior, boundaries, and success criteria — from the answers gathered… |
| eval-driven-dev 82/100 · B | github/awesome-copilot | Improve AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and… |
| eval-engineering 82/100 · B | langchain-ai/langchain-skills | Inspect an agent repository and optional traces, interview the user, write reviewed Task Specs, build and audit Harbor tasks, and bootstrap reusable… |
| evaluating-code-models 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models… |
| evaluating-cosmos-policy 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation… |
| evaluating-llms-harness 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing… |
| evolving-ai-agents 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building… |
| experiment-tracking-swanlab 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight… |
| fal-prompting 76/100 · C | fal-ai-community/skills | Model-family-specific prompt craft for fal.ai endpoints. Trigger when the user mentions a specific model family by name and asks how to prompt it… |
| finalize-agent-prompt 59/100 · D | github/awesome-copilot | Finalize prompt file using the role of an AI agent to polish the prompt for the end user. |
| find-models 57/100 · D | replicate/skills | Find AI models on Replicate using search and curated collections. |
| find-skill 78/100 · C | gooseworks-ai/goose-skills | Find and install skills from the Orthogonal skill library. Use when you need capabilities you don't have, want to discover available skills, or need… |
| fine-tuning-expert 84/100 · B | jeffallan/claude-skills | Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters… |
| fine-tuning-openvla-oft 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM… |
| fine-tuning-serving-openpi 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across… |
| fine-tuning-with-trl 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization… |
| finetuning 86/100 · B | microsoft/azure-skills | Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation… |
| firecrawl-knowledge-base 74/100 · C | firecrawl/skills | Build a knowledge base from web content with Firecrawl. Use for local reference docs, RAG-ready chunks, fine-tuning datasets, documentation mirrors… |
| flowstudio-power-automate-build 80/100 · B | github/awesome-copilot | Build, scaffold, and deploy Power Automate cloud flows using the FlowStudio MCP server. Your agent constructs flow definitions, wires connections… |
| flowstudio-power-automate-debug 78/100 · C | github/awesome-copilot | Debug failing Power Automate cloud flows using the FlowStudio MCP server. The Graph API only shows top-level status codes. This skill gives your… |
| flowstudio-power-automate-governance 75/100 · C | github/awesome-copilot | Govern Power Automate flows and Power Apps at scale using the FlowStudio MCP cached store. Classify flows by business impact, detect orphaned… |
| flowstudio-power-automate-mcp 70/100 · C | github/awesome-copilot | Foundation skill for Power Automate via FlowStudio MCP — auth setup, the reusable MCP helper (Python + Node.js), tool discovery via `list_skills` /… |
| flowstudio-power-automate-monitoring 69/100 · D | github/awesome-copilot | Pro+ subscription required. Tenant-wide Power Automate monitoring using the FlowStudio MCP cached store: failure rates, run-health trends, maker/app… |
| foundationpose-pipeline 78/100 · C | NVIDIA/skills | Adapt BOP datasets, run the FoundationPose perception pipeline with TAO depth, and evaluate or re-score pose results. Use for dataset runs and… |
| foundationpose-setup 81/100 · B | NVIDIA/skills | Install or repair the FoundationPose perception pipeline and build its FoundationStereo TensorRT engines. Use for SAM3/TAO dependency conflicts… |
| foundry-agent-sync 78/100 · C | github/awesome-copilot | Create and synchronize prompt-based AI agents directly within Azure AI Foundry via REST API, from a local JSON manifest. Unlike scaffolding skills… |
| foundry-hosted-agent-copilotkit 72/100 · C | github/awesome-copilot | Build and evolve agentic web apps that pair a CopilotKit React frontend with a Microsoft Agent Framework agent running as a Microsoft Foundry hosted… |
| foundry-iq 71/100 · C | microsoft/azure-skills | Foundry IQ knowledge bases. WHEN: make local or Blob documents searchable; create/diagnose KBs; triage unsupported connectors or multi-source KB… |
| gemini-agents-api 80/100 · B | google/skills | Manages custom Agent resources on Gemini Enterprise Agent Platform. Use when the user wants to programmatically create, configure, list, update, or… |
| gemini-api 85/100 · B | google/skills | Use when the user asks about using Gemini in an enterprise environment or explicitly mentions Vertex AI, Google Cloud, or Agent Platform. Guides the… |
| gemini-interactions-api 83/100 · B | google/skills | Guides the usage of Gemini Interactions API on Gemini Enterprise Agent Platform. Use when the user wants to use the stateful, server-managed… |
| gemini-live-api 87/100 · B | google/skills | Generates a Gemini LiveAPI client service class in the user's chosen programming language. Use when the user wants to build, scaffold, or integrate… |
| gguf-quantization 69/100 · D | Orchestra-Research/AI-Research-SKILLs | GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when… |
| gh-address-comments 62/100 · D | openai/skills | Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to… |
| github-issues 81/100 · B | github/awesome-copilot | Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues… |
| gke-inference 84/100 · B | google/skills | Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring… |
| go-mcp-server-generator 69/100 · D | github/awesome-copilot | Generate a complete Go MCP server project with proper structure, dependencies, and implementation using the official… |
| goal-prompt 88/100 · B | trailofbits/skills | Drafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex. Use when the user asks to create, write, rewrite, improve, compress… |
| google-agents-cli-onboarding 83/100 · B | google/skills | Onboarding entrypoint for agents-cli in Agent Platform. It should be used when the user wants to "create a new agent", "develop an agent", "build an… |
| google-cloud-solution-agentic-ai-bidirectional-streaming 87/100 · B | google/skills | Guides agents to interactively discover customer requirements for live, bidirectional multi-agent AI systems that process continuous streams of… |
| google-cloud-solution-build-deploy-agents 87/100 · B | google/skills | Designs, builds, and deploys AI agents or multi-agent systems on Google Cloud. Provides an interactive workflow to gather requirements, recommend a… |
| gptq 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4×… |
| gtm-ai-gtm 69/100 · D | github/awesome-copilot | Go-to-market strategy for AI products. Use when positioning AI products, handling "who is responsible when it breaks" objections, pricing… |
| half-clone 64/100 · D | ykdojo/claude-code-tips | Clone the later half of the current conversation, discarding earlier context to reduce token usage while preserving recent work. |
| handoff 60/100 · D | mattpocock/skills | Compact the current conversation into a handoff document for another agent to pick up. |
| handoff 62/100 · D | ykdojo/claude-code-tips | Write or update a handoff document so the next agent with fresh context can continue this work. |
| harness-engineering 77/100 · C | github/awesome-copilot | Adopt repository-level harness engineering for coding agents. Use when a user wants to prevent repeated AI coding-agent mistakes by turning failures… |
| harness-engineering 81/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable… |
| hf-cli 76/100 · C | huggingface/skills | Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging… |
| hf-mcp 72/100 · C | huggingface/skills | Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use… |
| hf-mem 67/100 · D | huggingface/skills | Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub |
| hivemind-memory 72/100 · C | activeloopai/hivemind | Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information. |
| hook-development 78/100 · C | anthropics/claude-plugins-official | This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement… |
| hqq-quantization 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration… |
| huggingface-best 81/100 · B | huggingface/skills | Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models… |
| huggingface-gradio 75/100 · C | huggingface/skills | Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots. |
| huggingface-llm-trainer 72/100 · C | huggingface/skills | Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure… |
| huggingface-tokenizers 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram… |
| huggingface-vision-trainer 72/100 · C | huggingface/skills | Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3… |
| i4h-lerobot-viz 79/100 · C | NVIDIA/skills | Serve and visually inspect a converted LeRobot dataset in the browser. Use for videos and state/action timelines; do not use for raw workflow HDF5… |
| i4h-workflow 81/100 · B | NVIDIA/skills | Orient users to the i4h workflow runtime and route them to the correct stage skill. Use for architecture, support, or where-to-start questions; do… |
| i4h-workflow-create 76/100 · C | NVIDIA/skills | Create a minimal blank Workflow scaffold with a Scene containing ground and light plus an idle run mode. Use for fast new Workflow scaffolding. |
| i4h-workflow-dataset-annotate 82/100 · B | NVIDIA/skills | Grade or filter workflow HDF5 episodes with an OpenAI-compatible vision model. Use for visual success labels; do not use for replay, policy… |
| i4h-workflow-dataset-convert 82/100 · B | NVIDIA/skills | Convert workflow HDF5 recordings to LeRobot datasets for training or browser inspection. Use for conversion; do not use for replay, augmentation, or… |
| i4h-workflow-dataset-mimic 79/100 · C | NVIDIA/skills | Expand workflow HDF5 demonstrations with action jitter, optionally scoped to node segments. Use for synthetic variants; do not use to collect data… |
| i4h-workflow-dataset-replay 79/100 · C | NVIDIA/skills | Replay a workflow HDF5 episode through its original Scene. Use for visual trajectory and recording verification; do not use for policy evaluation or… |
| i4h-workflow-dataset-teleop 82/100 · B | NVIDIA/skills | Record demonstrations through a workflow's teleop Task into workflow HDF5. Use for keyboard, leader, VR, or bus input; do not use for policy… |
| i4h-workflow-e2e 82/100 · B | NVIDIA/skills | Run the maintained workflow data-to-policy pipeline from recording through checkpoint validation. Use for full end-to-end requests; do not use for… |
| i4h-workflow-finetune 82/100 · B | NVIDIA/skills | Fine-tune a manifest-backed GR00T or openpi remote Task on compatible LeRobot data. Use for training; do not use for inference-only Tasks or… |
| i4h-workflow-scene-edit 85/100 · B | NVIDIA/skills | Edit an existing workflow Scene or task contract. Use for assets, layout, cameras, randomization, task text, or success rules; do not use to create… |
| i4h-workflow-setup 79/100 · C | NVIDIA/skills | Preflight and set up the root-level workflow runtime. Use for installation, missing component environments, or third-party failures; do not use for… |
| i4h-workflow-train-rl 76/100 · C | NVIDIA/skills | Use when training, evaluating, or exporting Workflow policies with online RSL-RL or RLinf, including RL checkpoint and Workflow handoff. |
| i4h-workflow-validate 82/100 · B | NVIDIA/skills | Run the root-level workflow runtime policy or rule-based rollouts and verify simulator success. Use for evaluation, checkpoints, or local… |
| implementing-llms-litgpt 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean… |
| java-mcp-server-generator 89/100 · B | github/awesome-copilot | Use this skill when the user wants to create a Model Context Protocol (MCP) server in Java or in a Spring Boot app. Also use it when the user wants… |
| jetson-inference-mem-tune 70/100 · C | NVIDIA/skills | Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson. |
| jetson-llm-benchmark 70/100 · C | NVIDIA/skills | Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output. |
| jetson-llm-serve 68/100 · D | NVIDIA/skills | Stand up vLLM or SGLang serving on Jetson, using upstream vLLM on Thor and Orin JetPack 7.2+, and NVIDIA-AI-IOT vLLM on older Orin. |
| jetson-speculative-decoding 68/100 · D | NVIDIA/skills | Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck. |
| judge 66/100 · D | NeoLabHQ/context-engineering-kit | Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation |
| judge-with-debate 66/100 · D | NeoLabHQ/context-engineering-kit | Evaluate solutions through multi-round debate between independent judges until consensus |
| jules 84/100 · B | sanjay3290/ai-skills | Delegate coding tasks to Google Jules AI agent for asynchronous execution. Use when user says: 'have Jules fix', 'delegate to Jules', 'send to… |
| kotlin-mcp-server-generator 69/100 · D | github/awesome-copilot | Generate a complete Kotlin MCP server project with proper structure, dependencies, and implementation using the official… |
| langchain-fundamentals 67/100 · D | langchain-ai/langchain-skills | Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling. |
| langchain-python-quickstart 71/100 · C | langchain-ai/langchain-skills | Scaffold a minimal local LangChain agent in Python by following the official quickstart. Use when the user wants to quickly build or try a LangChain… |
| langchain-rag 69/100 · D | langchain-ai/langchain-skills | INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings… |
| langchain-typescript-quickstart 71/100 · C | langchain-ai/langchain-skills | Scaffold a minimal local LangChain agent in TypeScript by following the official quickstart. Use when the user wants to quickly build or try a… |
| langgraph-decision-models 72/100 · C | langchain-ai/langchain-skills | INVOKE THIS SKILL when routing a LangGraph agent with a decision model (TypeSafe Jev, SemIf) instead of an LLM, or when auditing an existing agent… |
| langgraph-python-quickstart 71/100 · C | langchain-ai/langchain-skills | Scaffold a minimal local LangGraph agent in Python by following the official quickstart. Use when the user wants to quickly build or try a LangGraph… |
| langgraph-typescript-quickstart 71/100 · C | langchain-ai/langchain-skills | Scaffold a minimal local LangGraph agent in TypeScript by following the official quickstart. Use when the user wants to quickly build or try a… |
| langsmith-observability 69/100 · D | Orchestra-Research/AI-Research-SKILLs | LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets… |
| latent-briefing 87/100 · B | muratcankoylan/Agent-Skills-for-Context-Engineering | This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context"… |
| launch-nemo-rl 72/100 · C | NVIDIA/skills | Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs… |
| launch-sub-agent 70/100 · C | NeoLabHQ/context-engineering-kit | Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and… |
| llama-cpp 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when… |
| llama-factory 64/100 · D | Orchestra-Research/AI-Research-SKILLs | Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support |
| llamaguard 66/100 · D | Orchestra-Research/AI-Research-SKILLs | Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances… |
| llamaindex 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector… |
| long-context 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents… |
| long-horizon-prompting 76/100 · C | muratcankoylan/Agent-Skills-for-Context-Engineering | This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent… |
| managed-deep-agents 63/100 · D | langchain-ai/langchain-skills | INVOKE THIS SKILL when building, testing, or deploying Managed Deep Agents in LangSmith. Walks a user through their first agent end to end —… |
| mcore-run-on-slurm 70/100 · C | NVIDIA/skills | How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for… |
| mcp-cli 74/100 · C | github/awesome-copilot | Interface for MCP (Model Context Protocol) servers via CLI. Use when you need to interact with external tools, APIs, or data sources through MCP… |
| mcp-cli 64/100 · D | obra/superpowers-lab | Use MCP servers on-demand via the mcp CLI tool - discover tools, resources, and prompts without polluting context with pre-loaded MCP integrations |
| mcp-copilot-studio-server-generator 67/100 · D | github/awesome-copilot | Generate a complete MCP server implementation optimized for Copilot Studio integration with proper schema constraints and streamable HTTP support |
| mcp-create-declarative-agent 65/100 · D | github/awesome-copilot | Skill converted from mcp-create-declarative-agent.prompt.md |
| mcp-deploy-manage-agents 65/100 · D | github/awesome-copilot | Skill converted from mcp-deploy-manage-agents.prompt.md |
| mcp-developer 84/100 · B | jeffallan/claude-skills | Use when building, debugging, or extending MCP servers or clients that connect AI systems with external tools and data sources. Invoke to implement… |
| mcp-implementation-security-review 76/100 · C | github/awesome-copilot | Review the implementation source code of MCP (Model Context Protocol) servers, clients, and tool handlers against a security baseline —… |
| mcp-integration 76/100 · C | anthropics/claude-plugins-official | This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context… |
| mcp-release-qa 77/100 · C | github/awesome-copilot | Verify an MCP server before release by exercising a real protocol session, comparing runtime capabilities with source and documentation, testing… |
| mcp-security-audit 78/100 · C | github/awesome-copilot | Audit MCP (Model Context Protocol) server configurations for security issues. Use this skill when: - Reviewing .mcp.json files for security risks… |
| md-starter 70/100 · C | infrasity-labs/dev-gtm-claude-skills | Generates a fully structured, project-specific CLAUDE.md by scanning the repo for signal files (package.json, Makefile, .github/workflows/… |
| medtech-model-evidence-export 78/100 · C | NVIDIA/skills | Exports sanitized metadata, parameters, reproducibility details, quality metrics, and optional review artifacts from Medical AI inference runs or… |
| memorize 66/100 · D | NeoLabHQ/context-engineering-kit | Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering |
| microsoft-docs 69/100 · D | github/awesome-copilot | Query official Microsoft documentation to find concepts, tutorials, and code examples across Azure, .NET, Agent Framework, Aspire, VS Code, GitHub… |
| microsoft-foundry 79/100 · C | microsoft/azure-skills | Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent… |
| microsoft-skill-creator 82/100 · B | github/awesome-copilot | Create agent skills for Microsoft technologies using Learn MCP tools. Use when users want to create a skill that teaches agents about any Microsoft… |
| migrate-to-codex 69/100 · D | openai/skills | Migrate supported instruction files, skills, agents, and MCP config into Codex project and global files. |
| miles-rl-training 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4… |
| mind-clone 61/100 · D | yzfly/Mind-Cloning-Engineering | Activate a Cognitive Digital Twin. Can simulate a custom subject (via core/ directory) OR load pre-installed celebrity/expert personas (from… |
| mini-context-graph 74/100 · C | github/awesome-copilot | A persistent, compounding knowledge base combining Karpathy's LLM Wiki pattern with a structured knowledge graph. Ingest documents once — the LLM… |
| ml-pipeline 82/100 · B | jeffallan/claude-skills | Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking with MLflow or Weights & Biases, creates Kubeflow… |
| moe-training 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction… |
| nanogpt 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej… |
| nemo-automodel-launcher-config 68/100 · D | NVIDIA/skills | Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution. |
| nemo-automodel-model-onboarding 70/100 · C | NVIDIA/skills | Guide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and… |
| nemo-automodel-recipe-development 68/100 · D | NVIDIA/skills | Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow. |
| nemo-curator 77/100 · C | Orchestra-Research/AI-Research-SKILLs | GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+… |
| nemo-evaluator-sdk 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing… |
| nemo-fabric-integrate 81/100 · B | NVIDIA/skills | Use this skill when integrating NVIDIA NeMo Fabric into a consumer application, service, evaluation harness, or platform through the typed Python… |
| nemo-mbridge-mlm-bridge-training 68/100 · D | NVIDIA/skills | Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available recipes, and multi-GPU examples. |
| nemo-mbridge-multi-node-slurm 73/100 · C | NVIDIA/skills | Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed… |
| nemo-mbridge-perf-activation-recompute 78/100 · C | NVIDIA/skills | Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute. Use for… |
| nemo-mbridge-perf-cpu-offloading 70/100 · C | NVIDIA/skills | Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with… |
| nemo-mbridge-perf-cuda-graphs 70/100 · C | NVIDIA/skills | Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention… |
| nemo-mbridge-perf-expert-parallel-overlap 70/100 · C | NVIDIA/skills | Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and… |
| nemo-mbridge-perf-hierarchical-context-parallel 68/100 · D | NVIDIA/skills | Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. |
| nemo-mbridge-perf-megatron-fsdp 65/100 · D | NVIDIA/skills | Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification. |
| nemo-mbridge-perf-memory-tuning 70/100 · C | NVIDIA/skills | Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP input re-gather, parallelism resizing, activation… |
| nemo-mbridge-perf-moe-comm-overlap 68/100 · D | NVIDIA/skills | MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling. |
| nemo-mbridge-perf-moe-dispatcher-selection 70/100 · C | NVIDIA/skills | Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns… |
| nemo-mbridge-perf-moe-hardware-configs 70/100 · C | NVIDIA/skills | Representative, point-in-time MoE training playbooks by hardware and model family. Use them as candidate seeds, then revalidate the exact runtime… |
| nemo-mbridge-perf-moe-long-context 70/100 · C | NVIDIA/skills | Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3… |
| nemo-mbridge-perf-moe-optimization-workflow 70/100 · C | NVIDIA/skills | Evidence-gated workflow for MoE performance optimization in Megatron Bridge. Covers measurement contracts, the Three Walls framework, parallel… |
| nemo-mbridge-perf-moe-vlm-training 70/100 · C | NVIDIA/skills | Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL… |
| nemo-mbridge-perf-parallelism-strategies 70/100 · C | NVIDIA/skills | Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and… |
| nemo-mbridge-perf-sequence-packing 70/100 · C | NVIDIA/skills | Validate and use packed sequences and long-context training in Megatron-Bridge, including offline LLM packing, collate-time VLM packing, Energon… |
| nemo-mbridge-perf-tp-dp-comm-overlap 67/100 · D | NVIDIA/skills | Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and… |
| nemo-mbridge-recipe-recommender 81/100 · B | NVIDIA/skills | Recommend and customize Megatron Bridge library and benchmark recipes for a user's model, GPU count, hardware, sequence length, and… |
| nemo-mbridge-resiliency 68/100 · D | NVIDIA/skills | Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine. |
| nemo-relay-debug-runtime-integration 78/100 · C | NVIDIA/skills | Use this skill when NeMo Relay is installed or imported but application-side runtime behavior is missing or incorrect, including load failures… |
| nemo-relay-get-started 81/100 · B | NVIDIA/skills | Use this skill when first-time NeMo Relay users want to try Relay, choose the least-complex supported quick start, or verify initial value through… |
| nemo-relay-install 81/100 · B | NVIDIA/skills | Use this skill when choosing or running NeMo Relay installation for the CLI, Python, Node.js, Rust, OpenClaw, Hermes, or maintained framework… |
| nemo-relay-instrument-calls 78/100 · C | NVIDIA/skills | Use this skill when an application owns tool or LLM/provider call sites and needs to wrap them with NeMo Relay scopes and managed execution APIs for… |
| nemo-relay-instrument-context-isolation 75/100 · C | NVIDIA/skills | Use this skill when concurrent requests, async tasks, threads, workers, goroutines, or agents need independent NeMo Relay scope stacks and correct… |
| nemo-relay-instrument-typed-wrappers 75/100 · C | NVIDIA/skills | Use this skill when adding NeMo Relay typed wrappers, domain types, or provider codecs while preserving JSON middleware semantics and caller-visible… |
| nemo-relay-migrate-from-flow 80/100 · B | NVIDIA/skills | Use this skill when migrating applications, examples, integrations, documentation, manifests, or repository code from NeMo Flow to NeMo Relay across… |
| nemo-relay-plugin-adaptive-tuning 81/100 · B | NVIDIA/skills | Use this skill when baseline NeMo Relay instrumentation exists and the user wants to configure or evaluate adaptive plugin behavior, including… |
| nemo-relay-plugin-build 78/100 · C | NVIDIA/skills | Use this skill when building or packaging reusable NeMo Relay runtime behavior as an embedded configuration component or a manifest-backed… |
| nemo-relay-plugin-observability 81/100 · B | NVIDIA/skills | Use this skill when choosing or configuring NeMo Relay 0.6 or 0.7 observability through the built-in plugin, subscribers, or exporters, including… |
| nemo-retriever 79/100 · C | NVIDIA/skills | Use when searching, extracting, ingesting, or querying a document collection with the NeMo Retriever 26.8.1 CLI, including local LanceDB indexes and… |
| nemo-retriever-mcp 68/100 · D | NVIDIA/skills | Use when a task needs to search or add documents through NeMo Retriever MCP. |
| nemo-rl-auto-research 85/100 · B | NVIDIA/skills | Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment… |
| nemo-rl-session-memory 82/100 · B | NVIDIA/skills | Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code… |
| nemoclaw-user-guide 78/100 · C | NVIDIA/skills | Guides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form. Use when users ask how to install… |
| nemotron-asr-finetune 78/100 · C | NVIDIA/skills | Orchestration skill for NVIDIA Nemotron Speech (Riva) / NeMo ASR domain and language adaptation. Given a goal like "improve/fine-tune ASR for my… |
| nemotron-customize 83/100 · B | NVIDIA/skills | Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT… |
| nemotron-policy-generator 75/100 · C | NVIDIA/skills | Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal… |
| nemotron-retrieval-recipes 79/100 · C | NVIDIA/skills | Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes. |
| nemotron-speech 73/100 · C | NVIDIA/skills | Routes NVIDIA Nemotron Speech (Formerly Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted. |
| nemotron-voice-agent-builder 82/100 · B | NVIDIA/skills | Create, refine, or fix NVIDIA voice agents (Cascaded or Omni) with Pipecat or LiveKit. Use when building, scaffolding, or iterating on a real-time… |
| neon-ai-gateway 79/100 · C | neondatabase/agent-skills | One API and one credential for frontier and open-source LLMs and embedding models, built into your Neon branch and powered by Databricks. Use when a… |
| nnsight-remote-interpretability 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to… |
| noob-mode 72/100 · C | github/awesome-copilot | Plain-English translation layer for non-technical Copilot CLI users. Translates every approval prompt, error message, and technical output into… |
| nvflare-autofl 89/100 · B | NVIDIA/skills | Use for agent-assisted Auto-FL optimization of an existing NVFLARE job in simulation, POC, or production. Do not use for code conversion… |
| nvflare-autofl-report 77/100 · C | NVIDIA/skills | Generate a reproducible final report, literature-outcome synthesis, JSON summary, and refreshed progress plot for a stopped or interrupted NVFLARE… |
| nvflare-convert-huggingface 87/100 · B | NVIDIA/skills | Convert existing Hugging Face Transformers Trainer or TRL SFTTrainer training code into an NVFLARE federated job using flare.patch(trainer), local… |
| nvflare-convert-lightning 83/100 · B | NVIDIA/skills | Convert existing PyTorch Lightning training code into an NVFLARE federated job using the Lightning Client API patch, local validation, and job… |
| nvflare-convert-pytorch 85/100 · B | NVIDIA/skills | Convert existing plain or manual PyTorch training code into an NVFLARE federated job using Client API model exchange, local validation, and job… |
| nvflare-diagnose-job 81/100 · B | NVIDIA/skills | Use when the user asks why a reported NVFLARE job failure signal occurred: the job failed, stalled, timed out, lost clients, ended with… |
| nvflare-orient 70/100 · C | NVIDIA/skills | Route open-ended NVFLARE advice and only conversion requests whose preliminary source inspection reports unresolved or conflicting ownership; never… |
| nvflare-shared 79/100 · C | NVIDIA/skills | Internal NVFLARE conversion references and templates. Use only when another NVFLARE skill directs you to a shared workflow, policy, or asset. |
| nvidia-skill-finder 85/100 · B | NVIDIA/skills | Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware… |
| onboard-context-matic 84/100 · B | github/awesome-copilot | Interactive onboarding tour for the context-matic MCP server. Walks the user through what the server does, shows all available APIs, lets them pick… |
| openai-docs 79/100 · C | openai/skills | Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official… |
| openrlhf-training 69/100 · D | Orchestra-Research/AI-Research-SKILLs | High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM… |
| optimizing-attention-flash 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long… |
| paidf-auto-labeling 81/100 · B | NVIDIA/skills | Use when a user needs to get started with PAIDF Auto-Labeling, plan a scenario, run or debug a shipped cookbook, author prompts or cookbooks… |
| paidf-orchestration-write-dag 78/100 · C | NVIDIA/skills | Use when a user describes a custom PAIDF Orchestration pipeline — a specific ordered combination of stages such as augmentation only, auto-labeling… |
| peft-fine-tuning 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory… |
| phoenix-cli 85/100 · B | github/awesome-copilot | Debug LLM applications using the Phoenix CLI. Fetch traces, analyze errors, structure trace review with open coding and axial coding, inspect… |
| phoenix-evals 67/100 · D | github/awesome-copilot | Build and run evaluators for AI/LLM applications using Phoenix. |
| phoenix-observability 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running… |
| physical-ai-image-attribute-augmentation 79/100 · C | NVIDIA/skills | Run the PAIDF Orchestration Image Attribute Augmentation DAG on Kubernetes - person-crop clothing augmentation, attribute search, and augmented… |
| physicsnemo-shard-tensor 83/100 · B | NVIDIA/skills | Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new… |
| pi-agent 83/100 · B | K-Dense-AI/claude-scientific-skills | Builds with and operates Pi, the minimal terminal coding harness. Use for installing Pi, configuring providers/models/settings/environment… |
| pinecone-rag 84/100 · B | github/awesome-copilot | Build production RAG pipelines and persistent agent memory using Pinecone as the vector database backend. ALWAYS USE THIS SKILL when the user… |
| playground 78/100 · C | anthropics/claude-plugins-official | Creates interactive HTML playgrounds — self-contained single-file explorers that let users configure something visually through controls, see a live… |
| pm-skill-creator 79/100 · C | deanpeters/Product-Manager-Skills | Design a new PM skill through guided conversation. Use when you have raw content or an idea and want to shape it into a compliant skill. |
| power-bi-dax-optimization 67/100 · D | github/awesome-copilot | Comprehensive Power BI DAX formula optimization prompt for improving performance, readability, and maintainability of DAX calculations. |
| power-bi-performance-troubleshooting 69/100 · D | github/awesome-copilot | Systematic Power BI performance troubleshooting prompt for identifying, diagnosing, and resolving performance issues in Power BI models, reports… |
| power-platform-mcp-connector-suite 69/100 · D | github/awesome-copilot | Generate complete Power Platform custom connector with MCP integration for Copilot Studio - includes schema generation, troubleshooting, and… |
| prompt-engineer 84/100 · B | jeffallan/claude-skills | Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test… |
| prompt-engineering 70/100 · C | NeoLabHQ/context-engineering-kit | Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing… |
| prompt-optimizer 75/100 · C | github/awesome-copilot | Turn any rough prompt, half-formed idea, or task description into a finished, ready-to-send prompt optimized for any LLM model inside a chat… |
| propose-hypotheses 66/100 · D | NeoLabHQ/context-engineering-kit | Execute complete FPF cycle from hypothesis generation to decision |
| pufferlib 81/100 · B | K-Dense-AI/claude-scientific-skills | Version-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint… |
| pytorch-fsdp2 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use… |
| pytorch-lightning 81/100 · B | K-Dense-AI/claude-scientific-skills | Deep learning framework (PyTorch Lightning / lightning package). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU… |
| pytorch-lightning 77/100 · C | Orchestra-Research/AI-Research-SKILLs | High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate… |
| pyvene-interventions 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting… |
| qdrant-search-quality 76/100 · C | github/awesome-copilot | Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall'… |
| qdrant-search-quality-diagnosis 69/100 · D | github/awesome-copilot | Diagnoses Qdrant search quality issues. Use when someone reports 'results are bad', 'wrong results', 'not relevant results', 'missing matches'… |
| quantizing-models-bitsandbytes 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models… |
| quarter-clone 64/100 · D | ykdojo/claude-code-tips | Clone the last quarter of the current conversation, discarding earlier context to reduce token usage while preserving recent work. |
| query 63/100 · D | NeoLabHQ/context-engineering-kit | Search the FPF knowledge base and display hypothesis details with assurance information |
| rag-architect 84/100 · B | jeffallan/claude-skills | Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search… |
| rag-blueprint 77/100 · C | NVIDIA/skills | NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change… |
| rag-eval 81/100 · B | NVIDIA/skills | Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use… |
| rag-perf 81/100 · B | NVIDIA/skills | Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for… |
| ray-train 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter… |
| reflect 80/100 · B | infrasity-labs/dev-gtm-claude-skills | Mid-conversation reflection skill that pauses execution and zooms out from detail-mode to honestly reassess direction, assumptions, and bias. Use… |
| remember-interactive-programming 62/100 · D | github/awesome-copilot | A micro-prompt that reminds the agent that it is an interactive programmer. Works great in Clojure when Copilot has access to the REPL (probably via… |
| research 71/100 · C | mattpocock/skills | Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic… |
| resourceful-problem-solving 60/100 · D | swarmclawai/swarmclaw | Always-on guidance for solving tasks resourcefully. Teaches agents to escalate through skills, CLI tools, and custom scripts instead of refusing… |
| review-claudemd 65/100 · D | ykdojo/claude-code-tips | Review recent conversations to find improvements for CLAUDE.md files. |
| rook-skill 75/100 · C | LambdaTest/agent-skills | Use rook to test, evaluate, red-team or regression-check an AI agent the user owns, or to interpret saved Rook results. Does not apply to ordinary… |
| run-models 60/100 · D | replicate/skills | Run AI models on Replicate via predictions, webhooks, and streaming. |
| scikit-learn 89/100 · B | K-Dense-AI/claude-scientific-skills | Supports machine learning in Python with scikit-learn. Applies when working with supervised learning (classification, regression), unsupervised… |
| secret-scanning 80/100 · B | github/awesome-copilot | Guide for configuring and managing GitHub secret scanning, push protection, custom patterns, and secret alert remediation. For pre-commit secret… |
| segment-anything-model 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as… |
| self-improvement-loops 79/100 · C | muratcankoylan/Agent-Skills-for-Context-Engineering | This skill should be used when the harness, scaffold, workflow, or optimizer itself is the optimization target: recursive self-improvement (RSI)… |
| self-managed-context 79/100 · C | muratcankoylan/Agent-Skills-for-Context-Engineering | This skill should be used when a model gets read-write control over its own live context window instead of a harness-scheduled compaction policy… |
| serving-llms-vllm 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference… |
| session-report 67/100 · D | anthropics/claude-plugins-official | Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects… |
| setup 73/100 · C | aws/agent-toolkit-for-aws | Set up the AWS DevOps Agent and AWS Security Agent connections. Use when the user says "set up", "configure", "connect", or when MCP tools are… |
| setup-arxiv-mcp 66/100 · D | NeoLabHQ/context-engineering-kit | Guide for setup arXiv paper search MCP server using Docker MCP |
| setup-context7-mcp 60/100 · D | NeoLabHQ/context-engineering-kit | Guide for setup Context7 MCP server to load documentation for specific technologies. |
| setup-devops-agent 80/100 · B | aws/agent-toolkit-for-aws | Setup and diagnostics for the AWS DevOps Agent MCP connection. Triggers when aws-devops-agent is missing from .mcp.json, when the connection is… |
| setup-serena-mcp 66/100 · D | NeoLabHQ/context-engineering-kit | Guide for setup Serena MCP server for semantic code retrieval and editing capabilities |
| sglang 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic… |
| shap 89/100 · B | K-Dense-AI/claude-scientific-skills | Explain and audit machine-learning predictions with SHAP. Use for selecting SHAP explainers and maskers, computing and validating feature… |
| simpo-training 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No… |
| skill-authoring-workflow 79/100 · C | deanpeters/Product-Manager-Skills | Turn raw PM content into a compliant, publish-ready skill. Use when creating or updating a repo skill without breaking standards. |
| skill-card-generator 89/100 · B | NVIDIA/skills | Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing… |
| skill-creator 84/100 · B | apollographql/skills | Guide for creating effective skills for Apollo GraphQL and GraphQL development. Use this skill when: (1) users want to create a new skill, (2) users… |
| skill-creator 78/100 · C | gooseworks-ai/goose-skills | Create, structure, and package agent skills. Use when designing new skills, updating existing skills, or helping users build skills with scripts… |
| skill-evaluator 84/100 · B | HeshamFS/materials-simulation-skills | Rigorously evaluate an Agent Skill end-to-end across ANY coding-agent CLI — verify its scripts emit the documented numbers (deterministic checks)… |
| skill-improver 93/100 · A | trailofbits/skills | Runs an autonomous review-and-fix improvement loop over a Claude Code skill until a review comes back clean, with a cross-round findings ledger… |
| slime-rl-training 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data… |
| solo 72/100 · C | anthropics/claude-plugins-official | Work on one hard mathematics problem in this session yourself, with no sub-agents: reason in stages, record each settled step in a notes file so… |
| sparse-autoencoder-training 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable… |
| stable-baselines3 81/100 · B | K-Dense-AI/claude-scientific-skills | Trains and evaluates single-agent reinforcement learning with Stable Baselines3 (PPO, SAC, DQN, TD3, DDPG, A2C), Gymnasium custom environments… |
| status 63/100 · D | NeoLabHQ/context-engineering-kit | Display the current state of the FPF knowledge base |
| stitch-loop 67/100 · D | google-labs-code/stitch-skills | Teaches agents to iteratively build websites using Stitch with an autonomous baton-passing loop pattern |
| storing-and-querying-vectors 84/100 · B | aws/agent-toolkit-for-aws | Store and query vector embeddings using Amazon S3 Vectors, a cost-effective long-term vector storage service with its own API namespace (s3vectors)… |
| stripe-docs 74/100 · C | stripe/ai | Use when the user or agent needs to read, search, or look up Stripe documentation or API reference. Prefer this over curl or WebFetch for any… |
| stripe-pay 80/100 · B | stripe/ai | Helps users send funds to another Stripe business, transfer money to a Stripe Profile handle or network ID, or ask whether an agent can pay a Stripe… |
| structured-autonomy-generate 65/100 · D | github/awesome-copilot | Structured Autonomy Implementation Generator Prompt |
| subagent-driven-development 68/100 · D | obra/superpowers | Use when executing implementation plans with independent tasks in the current session |
| suggest-awesome-github-copilot-agents 69/100 · D | github/awesome-copilot | Suggest relevant GitHub Copilot Custom Agents files from the awesome-copilot repository based on current repository context and chat history… |
| system-prompt-creator 84/100 · B | tronghieu/agent-skills | Create high-quality, model-aware system prompts for any LLM (Claude, GPT, Gemini, open-source, etc.). Use this skill whenever the user wants to… |
| tao-analyze-changenet-rca 88/100 · B | NVIDIA/skills | Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with image-evidence-driven investigation. Use when… |
| tao-analyze-gaps-od-map 90/100 · A | NVIDIA/skills | Run TAO Data Services object-detection gap analysis from ground-truth and inference annotations. Use when an object detection workflow needs to… |
| tao-analyze-gaps-visual-changenet 85/100 · B | NVIDIA/skills | Performs gap analysis on NVIDIA TAO VCN Classify (Visual Component Net) experiments by invoking the pinned TAO data-services container directly via… |
| tao-analyze-gaps-vlm-bcq 90/100 · A | NVIDIA/skills | Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions. Use when the user asks to "analyze… |
| tao-artifacts 88/100 · B | NVIDIA/skills | The contract home for TAO's SDK-free execution pipeline — authoritative JSON Schemas for the four typed artifacts (spec-bundle, job-record… |
| tao-finetune-anomalygennext 91/100 · A | NVIDIA/skills | Validate a user AnomalyGenNext dataset and recipe, freeze its validation set, and prepare a canonical texture fine-tuning recipe. Use when… |
| tao-finetune-clip 89/100 · B | NVIDIA/skills | CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment. Use when… |
| tao-finetune-cosmos-embed 88/100 · B | NVIDIA/skills | Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning. Use when the user… |
| tao-finetune-cosmos-reason 79/100 · C | NVIDIA/skills | Shared Cosmos3 frontend that explicitly routes Cosmos Framework and Cosmos-RL, validates runtime model/video-dataset/SLURM inputs, consumes an SQSH… |
| tao-finetune-huggingface-model 85/100 · B | NVIDIA/skills | Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container when no dedicated TAO model skill matches. Use… |
| tao-finetune-kumo-anomaly 88/100 · B | NVIDIA/skills | Kumo-Anomaly — diffusion-based anomaly detection and fine-tuning for multivariate time series. Use when the user asks to "fine-tune Kumo-Anomaly"… |
| tao-finetune-kumo-forecast 88/100 · B | NVIDIA/skills | Kumo-Forecast — transformer-based multivariate time series forecasting with DARR (context-enhanced kNN retrieval), interpretability, and… |
| tao-finetune-video-clip 88/100 · B | NVIDIA/skills | InternVideo2-CLIP L14 (TAO video_clip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX export, and… |
| tao-generate-anomalies 88/100 · B | NVIDIA/skills | Full PAIDF AnomalyGen pipeline — fine-tune on a new anomaly dataset, generate synthetic anomaly images (SDG), evaluate quality (nn_score), and… |
| tao-generate-image-embeddings 90/100 · A | NVIDIA/skills | Run TAO Data Services image embedding to turn a parquet of image filepaths into an embedding parquet using CLIP, SigLIP, or a TAO checkpoint. Use… |
| tao-generate-image-grounding 88/100 · B | NVIDIA/skills | Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pixel-space bounding boxes via a… |
| tao-generate-od-defects 84/100 · B | NVIDIA/skills | Run AnomalyGenNext 1.1 inference from a native testcase or a prepared generation plan, then publish validated fine-grained and binary COCO labels… |
| tao-generate-referring-expressions 86/100 · B | NVIDIA/skills | Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region descriptions, scene captions, grounded… |
| tao-generate-video-reasoning-annotations 88/100 · B | NVIDIA/skills | Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and… |
| tao-launch-workflow 80/100 · B | NVIDIA/skills | The mandatory pre-launch gate and four-verb execution contract for every TAO workflow or action. Invoke BEFORE launching anything side-effecting —… |
| tao-list-capabilities 82/100 · B | NVIDIA/skills | Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. Use… |
| tao-mine-aoi-images 79/100 · C | NVIDIA/skills | Runs the DEFT embed-then-mine workflow for VCN AOI iterations — embeds the gap-analysis target parquet, embeds a source pool, and mines… |
| tao-mine-nearest-neighbors 87/100 · B | NVIDIA/skills | Run TAO Data Services TMM nearest-neighbor mining from embedding parquet files. Use when a workflow needs to mine source samples closest to target… |
| tao-mine-od-images 87/100 · B | NVIDIA/skills | Run TAO Data Services TMM unique-neighbor matching mining from embedding parquet files for object detection workflows. Use when an object detection… |
| tao-port-huggingface-model 84/100 · B | NVIDIA/skills | Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT… |
| tao-prepare-anomalygennext-inputs 91/100 · A | NVIDIA/skills | Prepare normalized object-detection false negatives, source masks, and clean-image embedding inputs for AnomalyGenNext. Use when turning box-level… |
| tao-route-visual-changenet-samples 85/100 · B | NVIDIA/skills | Routes the weakest VCN samples (output of `tao-analyze-gaps-visual-changenet`) into per-augmentation-module subsets based on each module's label… |
| tao-run-automl 90/100 · A | NVIDIA/skills | Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian… |
| tao-run-automl-deft-pipeline 84/100 · B | NVIDIA/skills | Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-train… |
| tao-run-deft-aoi 89/100 · B | NVIDIA/skills | Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, Cosmos AnomalyGen /… |
| tao-run-deft-aoi-cosmos3 92/100 · A | NVIDIA/skills | Run the disk-backed DEFT AOI improvement loop for NVIDIA Cosmos Reason 3 / Cosmos3 models, using Nano by default and Edge or Super when explicitly… |
| tao-run-deft-pas 89/100 · B | NVIDIA/skills | Run iterative improvement for NVIDIA TAO CLIP / SigLIP image-text retrieval on attribute-labelled data. Use when a request combines retrieval… |
| tao-run-dinov3-ssl-deft 85/100 · B | NVIDIA/skills | Run iterative DINOv3 SSL DEFT data selection and retraining from an unlabeled pool, using GRIT or multi-task weakness and fixed-encoder retrieval… |
| tao-run-inference-service 85/100 · B | NVIDIA/skills | Start, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by delegating container execution to… |
| tao-setup 79/100 · C | NVIDIA/skills | One-time session setup and orchestration map for the TAO skill bank. Run this first when the TAO skills were installed individually (e.g. from a… |
| tao-train-action-recognition 88/100 · B | NVIDIA/skills | Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for classifying temporal actions in video… |
| tao-train-bevfusion 88/100 · B | NVIDIA/skills | BEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view (BEV) space, used in autonomous… |
| tao-train-centerpose 88/100 · B | NVIDIA/skills | CenterPose for keypoint / pose estimation. Detects object centers and regresses keypoint locations for 6-DoF object pose estimation. Use when… |
| tao-train-codetr 88/100 · B | NVIDIA/skills | Co-DETR (CoDINO) for object detection. A DETR-family detector with collaborative hybrid assignment — auxiliary one-to-many heads supervise the… |
| tao-train-deformable-detr 88/100 · B | NVIDIA/skills | Deformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing, lighter than DINO with competitive… |
| tao-train-depth-anything-v2 88/100 · B | NVIDIA/skills | Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts per-pixel depth from single RGB images… |
| tao-train-dino 88/100 · B | NVIDIA/skills | DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with denoising training, multi-scale features… |
| tao-train-dinov3 80/100 · B | NVIDIA/skills | DINOv3 continual self-supervised pre-training. Domain-adapts public DINOv3 ViT backbones on unlabeled images via teacher-student self-distillation… |
| tao-train-fast-foundation-stereo 88/100 · B | NVIDIA/skills | Real-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of FoundationStereo. Predicts disparity… |
| tao-train-foundation-stereo 88/100 · B | NVIDIA/skills | Stereo depth estimation using FoundationStereo. Predicts disparity maps from stereo image pairs for 3D reconstruction. Use when training… |
| tao-train-grounding-dino 88/100 · B | NVIDIA/skills | Grounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for language-guided detection — detects objects… |
| tao-train-image-classification 88/100 · B | NVIDIA/skills | PyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.) with distillation and quantization for… |
| tao-train-mask-auto-encoder 88/100 · B | NVIDIA/skills | Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs them to learn visual… |
| tao-train-mask-auto-label 88/100 · B | NVIDIA/skills | MAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations (point or box annotations) using a… |
| tao-train-mask-grounding-dino 88/100 · B | NVIDIA/skills | Mask Grounding DINO for grounded instance segmentation. Extends Grounding DINO with a mask-prediction head for open-set segmentation guided by text… |
| tao-train-mask2former 88/100 · B | NVIDIA/skills | Mask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with masked attention for high-quality… |
| tao-train-metric-learning-recognition 88/100 · B | NVIDIA/skills | Metric-learning recognition (ml-recog) for fine-grained visual recognition. Learns embeddings for retrieval-based matching (e.g., retail product… |
| tao-train-nvdinov2 88/100 · B | NVIDIA/skills | NVDINOv2 for self-supervised visual representation learning. Trains vision transformers via self-distillation (teacher-student) without labels and… |
| tao-train-nvpanoptix3d 88/100 · B | NVIDIA/skills | NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation (semantic, instance, and panoptic masks)… |
| tao-train-ocdnet 88/100 · B | NVIDIA/skills | OCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a differentiable binarization approach. Use when… |
| tao-train-ocrnet 88/100 · B | NVIDIA/skills | OCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC and attention-based decoders. Use when… |
| tao-train-oneformer 88/100 · B | NVIDIA/skills | OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single architecture using task-conditioned… |
| tao-train-optical-inspection 90/100 · A | NVIDIA/skills | Optical Inspection for defect detection using Siamese networks. Compares image pairs to detect manufacturing defects, anomalies, or quality issues… |
| tao-train-pointpillars 88/100 · B | NVIDIA/skills | PointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a pillar-based representation, then… |
| tao-train-pose-classification 88/100 · B | NVIDIA/skills | Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences into action categories from… |
| tao-train-reid 88/100 · B | NVIDIA/skills | Person re-identification (ReID). Learns discriminative embeddings to match the same person across different camera views, based on metric learning… |
| tao-train-rtdetr 88/100 · B | NVIDIA/skills | RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive accuracy and supports… |
| tao-train-segformer 88/100 · B | NVIDIA/skills | SegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature extraction, efficient for real-time… |
| tao-train-single-step 88/100 · B | NVIDIA/skills | Standard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset without iterative data augmentation… |
| tao-train-sparse4d 87/100 · B | NVIDIA/skills | Prepare calibrated multi-camera data and train, evaluate, run inference, export, or quantize TAO Sparse4D 3D detection and tracking models. Includes… |
| tao-train-visual-changenet 90/100 · A | NVIDIA/skills | Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training, evaluating, exporting, or running… |
| tao-validate-dataset-format 86/100 · B | NVIDIA/skills | Run `tao-daft validate` to check NVIDIA TAO DAFT datasets for structure, schema, and cross-reference errors. Do not use for non-DAFT formats. Use… |
| tensorrt-llm 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100)… |
| test-prompt 70/100 · C | NeoLabHQ/context-engineering-kit | Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies… |
| testing-handbook-generator 88/100 · B | trailofbits/skills | Generates Claude Code skills from the Trail of Bits Testing Handbook (appsec.guide), analyzing handbook pages and emitting SKILL.md files with the… |
| thought-based-reasoning 67/100 · D | NeoLabHQ/context-engineering-kit | Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or… |
| tilegym-monkey-patch-kernels-to-transformers 83/100 · B | NVIDIA/skills | Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations… |
| timesfm-forecasting 81/100 · B | K-Dense-AI/claude-scientific-skills | Performs zero-shot time-series forecasting with Google's TimesFM, including regular-grid CSV preparation, quantile forecasts, XReg covariates, and… |
| tldr-prompt 67/100 · D | github/awesome-copilot | Create tldr summaries for GitHub Copilot files (prompts, agents, instructions, collections), MCP servers, or documentation from URLs and queries. |
| torch-geometric 89/100 · B | K-Dense-AI/claude-scientific-skills | Supports PyTorch Geometric (PyG) graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous… |
| torchforge-rl-training 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL… |
| training-llms-megatron 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B… |
| transformer-lens-interpretability 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and… |
| transformers 87/100 · B | K-Dense-AI/claude-scientific-skills | Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and… |
| triage 68/100 · D | mattpocock/skills | Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs. |
| trl-training 77/100 · C | huggingface/skills | Post-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-model training. Use when writing or debugging… |
| typespec-create-agent 64/100 · D | github/awesome-copilot | Generate a complete TypeSpec declarative agent with instructions, capabilities, and conversation starters for Microsoft 365 Copilot |
| unsloth 64/100 · D | Orchestra-Research/AI-Research-SKILLs | Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization |
| update-llms 69/100 · D | github/awesome-copilot | Update the llms.txt file in the root folder to reflect changes in documentation or specifications following the llms.txt specification at… |
| utility-pm-skill-auditor 83/100 · B | product-on-purpose/pm-skills | Run a repo-wide cross-cutting governance audit via the pm-skill-auditor sub-agent. Aggregates the enforcing validator suite, re-derives aggregate… |
| utility-pm-skill-builder 75/100 · C | product-on-purpose/pm-skills | Guides contributors from a PM skill idea to a complete Skill Implementation Packet aligned with pm-skills conventions. Runs gap analysis, validates… |
| utility-pm-workflow-orchestrator 75/100 · C | product-on-purpose/pm-skills | Run an ordered sequence of pm-skills against one input, pausing for go/no-go and stopping on a failed or empty step. Accepts a saved prioritized… |
| venice-characters 70/100 · C | veniceai/skills | Discover and use Venice public characters (persona-driven system prompts with a suggested model). Covers GET /characters… |
| venice-decisions 73/100 · C | veniceai/skills | Call Venice's Beta POST /decisions (and its TypeSafe-compatible alias POST /systemone) to get typed judgments instead of generated text. Covers the… |
| venice-embeddings 70/100 · C | veniceai/skills | Call POST /embeddings on Venice. Covers request shape (input, model, encoding_format, dimensions, user), text-only input (token arrays rejected)… |
| venice-responses 70/100 · C | veniceai/skills | Use Venice's Alpha POST /responses endpoint - an OpenAI-compatible, stateless Responses API with typed output blocks (reasoning, message… |
| verify-agent-action 77/100 · C | github/awesome-copilot | Review a proposed AI-agent action or human-approval packet before execution. Use when an agent wants to run a consequential tool, command… |
| verl-rl-training 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL… |
| voltagent-best-practices 57/100 · D | VoltAgent/skills | VoltAgent architectural patterns and conventions. Covers agents vs workflows, project layout, memory, servers, and observability. |
| vss-ask-video 82/100 · B | NVIDIA/skills | Use this skill to ask the VSS agent's video_understanding tool a fresh visual question about a recorded clip. Not for prior tool output, search… |
| vss-generate-video-calibration 85/100 · B | NVIDIA/skills | Use to run AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, and to deploy vss-auto-calibration when needed. Do not use for non-AMC… |
| vss-generate-video-report 82/100 · B | NVIDIA/skills | Use this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics. Not for standalone video… |
| vss-search-archive 85/100 · B | NVIDIA/skills | Use this skill to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. Do NOT use for ad-hoc… |
| vss-summarize-video 85/100 · B | NVIDIA/skills | Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP… |
| wayfinder 70/100 · C | mattpocock/skills | Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at… |
| webmcp-gen 77/100 · C | browserbase/skills | Create, compile, and validate site-specific WebMCP init scripts from a target URL and desired tool capability. Use when the user wants to author… |
| webmcpify 83/100 · B | github/awesome-copilot | Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for… |
| workflow-builder 79/100 · C | infrasity-labs/dev-gtm-claude-skills | Design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool. Use when a user wants… |
| write-coding-standards-from-file 67/100 · D | github/awesome-copilot | Write a coding standards document for a project using the coding styles from the file(s) and/or folder(s) passed as arguments in the prompt. |
| writing-for-agents 76/100 · C | mattpocock/skills | Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md. |
| writing-skills 69/100 · D | obra/superpowers | Use when creating new skills, editing existing skills, or verifying skills work before deployment |
How to choose AI agent and LLM engineering skills
Start from the system you are building. Skills for a specific framework or model provider carry that provider's conventions, so they beat general prompting advice when you already know your stack.
Check what a skill expects to run. Training and inference skills often name GPU tooling, cloud credentials or a model hub token; the Before you install panel on each page lists the scripts it bundles and the environment variables its code reads.
For agent workflow skills (planning, subagents, review loops), read the SKILL.md body first. They change how your agent works on every task, so pick one method and stay with it rather than stacking overlapping ones.
Where to start
mcp-builderGuides building MCP servers that let LLMs use external services through tools, in Python with FastMCP or TypeScript… Published by Anthropic.
let-fate-decideDraws a Tarot spread to inject entropy into planning when prompts are vague or casually delegated, and interprets the… Published by Trail of Bits.
agent-platform-deployDeploys open models or custom weights from Model Garden to Agent Platform endpoints, checks deployment status and… Published by Google.
huggingface-community-evalsRuns evaluations for Hugging Face Hub models on local hardware using inspect-ai and lighteval, including backend… Published by Hugging Face.
agent-email-inboxGuides building email-triggered systems like AI agent inboxes, using sender allowlists, content filtering, and… Published by Resend.
Featured AI agent skills
mcp-builder89/100 · B
anthropics/skills
Guides building MCP servers that let LLMs use external services through tools, in Python with FastMCP or TypeScript with the MCP SDK.
skill-creator83/100 · B
anthropics/skills
Guides creating new skills, improving existing ones, running evals, benchmarking skill performance with variance analysis, and optimizing…
diagnosing-superpowers90/100 · A
obra/superpowers
Diagnoses why a superpowers session went wrong, such as repeated work or ignored plans, and helps build a bug report for maintainers.
dispatching-parallel-agents82/100 · B
obra/superpowers
Guides splitting two or more independent tasks, with no shared state or sequential dependencies, across parallel agents.
executing-plans83/100 · B
obra/superpowers
Guides executing an implementation plan inline in the current session as the implementer, when inline execution is chosen or no subagent…
using-superpowers84/100 · B
obra/superpowers
Establishes how to find and use skills at the start of any conversation, requiring skill invocation before any response, including…
verification-before-completion84/100 · B
obra/superpowers
Requires running verification commands and confirming their output before claiming work is complete, fixed, or passing, and before…
writing-plans80/100 · B
obra/superpowers
Guides writing a plan from a spec or requirements for a multi-step task, before touching any code.
orca-replay86/100 · B
Continuum-AI-Corp/OrcaReplay
Answers questions about a past agent run from its recording rather than memory, and replays or forks that run.
grok-build87/100 · B
sanjay3290/ai-skills
Delegates well-specified implementation tasks to xAI's Grok Build CLI running headlessly while the assistant writes task specs, reviews…
manus87/100 · B
sanjay3290/ai-skills
Delegates complex, long-running tasks to the Manus AI agent for autonomous execution, such as deep web research, market analysis, product…
let-fate-decide94/100 · A
trailofbits/skills
Draws a Tarot spread to inject entropy into planning when prompts are vague or casually delegated, and interprets the spread to guide next…
slicing-code-context89/100 · B
trailofbits/skills
Selects bounded, graph-informed source slices with Trailmark and delegates focused code analysis or patch-proposal work to a smaller…
aws-agentic-ai83/100 · B
zxkane/aws-skills
Guides deploying and managing AI agents on AWS Bedrock AgentCore, covering Gateway, Runtime, Memory, Identity, Observability, Evaluations…
aws-mcp-setup80/100 · B
zxkane/aws-skills
Configures AWS MCP servers for documentation search and API access, covering both the full AWS MCP Server and the lightweight…
autonomous-investigation81/100 · B
deanpeters/Product-Manager-Skills
Defines the protocol behind investigation skills for unattended AI research, using a search-plan gate, Fact, Inference, and Assumption…
agenttrace-session-audit78/100 · C
luoyuctl/agenttrace
Audits local AI coding-agent sessions from tools like Claude Code and Codex CLI with agenttrace, checking cost, tokens, tool failures…
agent-ready91/100 · A
mblode/agent-skills
Implements agent-readiness on sites and docs from scorecards like Mintlify Agent Score or AFDocs, including llms.txt coverage and agents…
agent-skills-creator91/100 · A
mblode/agent-skills
Creates and improves portable Agent Skills using a validator and routing scenarios, with evidence-based decisions to keep, cut, merge, or…
chat-history91/100 · A
mblode/agent-skills
Recovers decisions, previous fixes, and research from past AI conversations with source evidence, reading local Claude Code, Codex, Grok…
conversation-analyzer77/100 · C
mhattingpete/claude-skills-marketplace
Analyzes Claude Code conversation history to identify patterns, common mistakes, and opportunities for workflow improvement and automation.
ensemble-solving81/100 · B
mhattingpete/claude-skills-marketplace
Generates multiple diverse solutions in parallel and selects the best, for architecture decisions, code generation with several valid…
advanced-evaluation86/100 · B
muratcankoylan/Agent-Skills-for-Context-Engineering
Guides advanced LLM evaluation, including LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias…
context-compression86/100 · B
muratcankoylan/Agent-Skills-for-Context-Engineering
Guides compression of long-running agent sessions through structured summarization, compaction, and durable handoff summaries that…
Top AI agent collections
NVIDIA/skills173 AI agent skills
github/awesome-copilot78 AI agent skills
Orchestra-Research/AI-Research-SKILLs63 AI agent skills
NeoLabHQ/context-engineering-kit28 AI agent skills
google/skills24 AI agent skills
muratcankoylan/Agent-Skills-for-Context-Engineering19 AI agent skills
aws/agent-toolkit-for-aws15 AI agent skills
langchain-ai/langchain-skills15 AI agent skills
huggingface/skills14 AI agent skills
anthropics/claude-plugins-official10 AI agent skills
K-Dense-AI/claude-scientific-skills10 AI agent skills
obra/superpowers9 AI agent skills
Other skill directories
Developer Tools and Frameworks · Marketing and SEO · Product Management · Science and Research · DevOps and Cloud · Video, Image, Audio and Creative · Productivity and Knowledge Work · Business, Sales and Finance · Testing and QA · Data, Analytics and Databases · Security · Frontend and Design · Writing and Editing · Code Review and Code Quality · Documents and Office Files