superpowers agent skills by obra
15 skills from obra/superpowers are listed in the directory, across 4 categories. 12 skills have a full page with install steps and a pre-install summary.
View obra/superpowers on GitHub
At a glance
| Publisher | obra |
|---|---|
| Repository | github.com/obra/superpowers |
| Listed skills | 15 |
| Security scan | Not scanned |
| Categories | AI Agents and LLM Engineering, Code Review and Code Quality, Developer Tools and Frameworks, Testing and QA |
| License | MIT |
| Last commit | October 9, 2026 |
| Install every skill | npx skills add https://github.com/obra/superpowers |
| 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.
[](https://skills.suedeai.ai/directory/obra/superpowers/)<a href="https://skills.suedeai.ai/directory/obra/superpowers/"><img src="https://skills.suedeai.ai/directory/obra/superpowers/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 obra/superpowers
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.
| Skill | Category | What it does |
|---|---|---|
| diagnosing-superpowers 90/100 · A | AI agents | 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 | AI agents | Guides splitting two or more independent tasks, with no shared state or sequential dependencies, across parallel agents. |
| executing-plans 83/100 · B | AI agents | Guides executing an implementation plan inline in the current session as the implementer, when inline execution is chosen or no subagent tool is available. |
| finishing-a-development-branch 82/100 · B | Dev tools | Guides deciding how to integrate completed work once implementation is finished and all tests pass. |
| receiving-code-review 84/100 · B | Code quality | Guides handling code review feedback with technical rigor and verification, rather than performative agreement or blind implementation, especially when feedback is unclear or questionable. |
| requesting-code-review 79/100 · C | Code quality | Guides requesting a code review after completing tasks, implementing major features, or before merging, to verify the work meets requirements. |
| systematic-debugging 80/100 · B | Testing | Guides a systematic approach to any bug, test failure, or unexpected behavior, before proposing fixes. |
| test-driven-development 80/100 · B | Testing | Guides test-driven development when implementing any feature or bugfix, applied before writing implementation code. |
| using-git-worktrees 84/100 · B | Dev tools | Ensures feature work or plan execution happens in an isolated workspace, using native tools or a git worktree fallback. |
| using-superpowers 84/100 · B | AI agents | Establishes how to find and use skills at the start of any conversation, requiring skill invocation before any response, including clarifying questions. |
| verification-before-completion 84/100 · B | AI agents | Requires running verification commands and confirming their output before claiming work is complete, fixed, or passing, and before committing or creating pull requests. |
| writing-plans 80/100 · B | AI agents | Guides writing a plan from a spec or requirements for a multi-step task, before touching any code. |
| brainstorming 78/100 · C | AI agents | You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything… |
| subagent-driven-development 68/100 · D | AI agents | Use when executing implementation plans with independent tasks in the current session |
| writing-skills 69/100 · D | AI agents | Use when creating new skills, editing existing skills, or verifying skills work before deployment |
Where this repository is cited
obra/superpowers appears in 6 curated lists: BehiSecc/awesome-claude-skills, ComposioHQ/awesome-claude-skills, VoltAgent/awesome-agent-skills, hesreallyhim/awesome-claude-code, karanb192/awesome-claude-skills, travisvn/awesome-claude-skills.