obra/superpowers

Agent skills in the GitHub repository obra/superpowers, each with its code score out of 100.

An agentic skills framework & software development methodology that works.

Repository score

68 / 100 C

Skills

15

Verified

0

Average skill score

63

GitHub stars

316,479

License

MIT

Open obra/superpowers on GitHub

15 skills in this repository

1. dispatching-parallel-agents

   Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

   78B
2. writing-skills

   Use when creating new skills, editing existing skills, or verifying skills work before deployment

   71B
3. using-git-worktrees

   Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git…

   70B
4. finishing-a-development-branch

   Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

   69C
5. test-driven-development

   Use when implementing any feature or bugfix, before writing implementation code

   69C
6. verification-before-completion

   Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any suc…

   66C
7. diagnosing-superpowers

   Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too l…

   65C
8. systematic-debugging

   Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

   64C
9. using-superpowers

   Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

   62C
10. receiving-code-review

    Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verificat…

    59C
11. executing-plans

    Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

    57C
12. writing-plans

    Use when you have a spec or requirements for a multi-step task, before touching code

    57C
13. requesting-code-review

    Use when completing tasks, implementing major features, or before merging to verify work meets requirements

    56C
14. subagent-driven-development

    Use when executing implementation plans with independent tasks in the current session

    54D
15. brainstorming

    You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (…

    53D

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.