Skill collection · NeoLabHQ
context-engineering-kit agent skills by NeoLabHQ
53 skills from NeoLabHQ/context-engineering-kit are listed in the directory, across 5 categories. 11 skills have a full page with install steps and a pre-install summary.
View NeoLabHQ/context-engineering-kit on GitHub
At a glance
| Publisher | NeoLabHQ |
|---|---|
| Repository | github.com/NeoLabHQ/context-engineering-kit |
| Listed skills | 53 |
| Security scan | Not scanned |
| Categories | AI Agents and LLM Engineering, Code Review and Code Quality, Developer Tools and Frameworks, Productivity and Knowledge Work, Testing and QA |
| License | GPL-3.0 |
| Last commit | August 26, 2026 |
| Install every skill | npx skills add https://github.com/NeoLabHQ/context-engineering-kit |
| README badge | Get the badge for this listing |
Show the listing in your README
This general badge links to the repository listing. For the two quality badges and feature offer, choose Get badges beside a skill below. Each skill keeps its own score and grade.
Markdown
[](https://skills.suedeai.ai/directory/neolabhq/context-engineering-kit/)HTML
<a href="https://skills.suedeai.ai/directory/neolabhq/context-engineering-kit/"><img src="https://skills.suedeai.ai/directory/neolabhq/context-engineering-kit/badge.svg" alt="Suede Skills Directory: listed" height="20"></a>Limited-time feature offer: display either the numeric or letter badge in your repository or skill README (both also qualify), then request badge verification. Eligible skills scoring 80–99 can receive a featured placement after Suede verifies at least one valid badge linked to the skill’s listing. Suede has not announced an end date.
Skills in NeoLabHQ/context-engineering-kit
Linked names open the skill's directory page; the rest open the skill folder on GitHub. Descriptions on rows without a page are quoted from each SKILL.md.
No matching skills. Try fewer words or clear your search.
| Skill | Category | What it does |
|---|---|---|
| brainstorm 82/100 · B | Productivity | Refines rough ideas into fully formed designs through collaborative questioning, alternative exploration, and incremental validation before writing code or implementation plans. |
| git-notes 78/100 · C | Dev tools | Explains git notes commands and patterns for attaching metadata such as review status, test results, and annotations to commits without changing history. |
| load-pr-comments 76/100 · C | Code quality | Loads open, unresolved PR review comments and aggregates them as task files in .specs/comments so parallel agents can fix them. |
| multi-agent-patterns 75/100 · C | AI agents | 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. |
| review-local-changes 78/100 · C | Code quality | Reviews uncommitted working-tree changes, including untracked files, and returns actionable improvement suggestions before committing, when nothing has been pushed yet. |
| review-pr 78/100 · C | Code quality | Reviews an existing GitHub pull request and posts inline review comments on its diff, for changes that are already on an opened PR. |
| root-cause-tracing 78/100 · C | Testing | Traces bugs backward through the call stack, adding instrumentation when needed, to find the original source of invalid data or incorrect behavior. |
| subagent-driven-development 78/100 · C | AI agents | Executes implementation plans by dispatching a fresh subagent per independent task, with code review between tasks to enable fast iteration with quality gates. |
| test-skill 78/100 · C | AI agents | Tests skills before deployment by running a baseline without the skill, writing fixes for failures, and iterating to close loopholes under pressure. |
| traiage-review 74/100 · C | Code quality | Prioritizes the changed code in a repository to decide what a human must review. |
| write-tests 78/100 · C | Testing | Generates new test files to cover uncommitted and untracked local changes, or the latest commit if everything is committed. |
| actualize 66/100 · D | AI agents | Reconcile the project's FPF state with recent repository changes |
| add-task 66/100 · D | Productivity | creates draft task file in .specs/tasks/draft/ with original user intent |
| agent-evaluation 64/100 · D | AI agents | Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or… |
| analyse-problem 66/100 · D | Productivity | Comprehensive A3 one-page problem analysis with root cause and action plan |
| analyze-issue 63/100 · D | Dev tools | Analyze a GitHub issue and create a detailed technical specification |
| apply-anthropic-skill-best-practices 62/100 · D | AI agents | Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure |
| cause-and-effect 66/100 · D | Productivity | Systematic Fishbone analysis exploring problem causes across six categories |
| commit 66/100 · D | Dev tools | Create well-formatted commits with conventional commit messages and emoji |
| context-engineering 64/100 · D | AI agents | Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or… |
| create-agent 70/100 · C | AI agents | Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official… |
| create-command 68/100 · D | AI agents | Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration |
| create-ideas 60/100 · D | Productivity | Generate ideas in one shot using creative sampling |
| create-pr 66/100 · D | Dev tools | Create pull requests using GitHub CLI with proper templates and formatting |
| create-rule 70/100 · C | AI agents | 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 | AI agents | 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 | AI agents | Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts |
| critique 66/100 · D | Code quality | Comprehensive multi-perspective review using specialized judges with debate and consensus building |
| decay 66/100 · D | AI agents | Manage evidence freshness by identifying stale decisions and providing governance actions |
| do-in-parallel 64/100 · D | AI agents | 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 | AI agents | 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… |
| fix-tests 66/100 · D | Testing | Systematically fix all failing tests after business logic changes or refactoring |
| git-worktrees 64/100 · D | Dev tools | Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or… |
| judge 66/100 · D | AI agents | Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation |
| judge-with-debate 66/100 · D | AI agents | Evaluate solutions through multi-round debate between independent judges until consensus |
| kaizen 70/100 · C | Code quality | Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation… |
| launch-sub-agent 70/100 · C | AI agents | Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and… |
| load-issues 60/100 · D | Dev tools | Load all open issues from GitHub and save them as markdown files |
| memorize 66/100 · D | AI agents | Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering |
| plan-do-check-act 66/100 · D | Productivity | Iterative PDCA cycle for systematic experimentation and continuous improvement |
| prompt-engineering 70/100 · C | AI agents | Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing… |
| propose-hypotheses 66/100 · D | AI agents | Execute complete FPF cycle from hypothesis generation to decision |
| query 63/100 · D | AI agents | Search the FPF knowledge base and display hypothesis details with assurance information |
| resolve-fixed-pr-comments 70/100 · C | Code quality | Verify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed… |
| setup-arxiv-mcp 66/100 · D | AI agents | Guide for setup arXiv paper search MCP server using Docker MCP |
| setup-codemap-cli 66/100 · D | Dev tools | Guide for setup Codemap CLI for intelligent codebase visualization and navigation |
| setup-context7-mcp 60/100 · D | AI agents | Guide for setup Context7 MCP server to load documentation for specific technologies. |
| setup-serena-mcp 66/100 · D | AI agents | Guide for setup Serena MCP server for semantic code retrieval and editing capabilities |
| status 63/100 · D | AI agents | Display the current state of the FPF knowledge base |
| test-driven-development 70/100 · C | Testing | Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass… |
| test-prompt 70/100 · C | AI agents | Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies… |
| thought-based-reasoning 67/100 · D | AI agents | Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or… |
| why 63/100 · D | Productivity | Iterative Five Whys root cause analysis drilling from symptoms to fundamentals |
Where this repository is cited
NeoLabHQ/context-engineering-kit appears in 3 curated lists: ComposioHQ/awesome-claude-skills, VoltAgent/awesome-agent-skills, hesreallyhim/awesome-claude-code.