Skip to content

superpowers

by obra

An agentic skills framework & software development methodology that works.

About

An agentic skills framework & software development methodology that works.

287,128
Stars
14
Skill Files
25,677
Forks
172
PRs Merged
44
Contributors
136
Issues Open
778
Issues Closed
2026-08-12
Last Activity

Skill Analysis

208
Avg Lines / Skill
1,262
Avg Words / Skill
92
Code Blocks
195
Total Files
1.64 MB
Repo Size
5
Reference Files
Skill lines35 min / 168 median / 680 max
Code languagesbash, dot, markdown, python, text, typescript, yaml
Frontmatter keysabout, description, labels, name
Has CLAUDE.mdYes
Has LicenseYes
File typesmd (94), sh (41), json (14), js (10), txt (9), py (6), yaml (2), yml (2), ts (2), mjs (2)

Skills (17)

  • receiving-code-review
    206 lines913 words12 blocks

    Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires ...

  • systematic-debugging
    284 lines1440 words3 blocks

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

    bash
  • writing-plans
    172 lines1059 words5 blocks

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

    bashmarkdownpython
  • writing-skills
    680 lines3779 words21 blocks

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

    bashdotmarkdownyaml
  • verification-before-completion
    121 lines580 words7 blocks

    Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming...

  • test-driven-development
    321 lines1375 words13 blocks

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

    bashdottypescript
  • executing-plans
    65 lines344 words

    Use when you have a written implementation plan to execute in a separate session with review checkpoints

  • using-superpowers
    64 lines485 words

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

  • requesting-code-review
    96 lines421 words2 blocks

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

    bash
  • dispatching-parallel-agents
    168 lines865 words4 blocks

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

    dotmarkdowntext
  • using-git-worktrees
    168 lines1069 words8 blocks

    Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace ex...

    bash
  • finishing-a-development-branch
    226 lines1269 words13 blocks

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

    bash
  • brainstorming
    251 lines2324 words1 blocks

    "You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user inten...

    dot
  • subagent-driven-development
    569 lines4823 words3 blocks

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

    dot
  • Feature Request
    48 lines266 words
  • Bug Report
    56 lines271 words

Recent Commits

-339 contributions across all repos
AugSepOctNovDecJanFebMarAprMayJunJulAug
Less
More
  • b36e0822026-08-12
    Release v6.3.0: Devin CLI and Hermes Agent support, brainstorming three-path router, SDD/Codex efficiency fixes (#2125)
    Jesse Vincent
  • 44c9b2d2026-07-28
    docs: remove the "We're Hiring" section from the README
    Jesse Vincent
  • 3dcbd5c2026-07-24
    Release v6.2.0: SDD plan-scoped workspace and resume-based fix loop, skills compression sweep, Windows SessionStart fix
    Jesse Vincent
  • c8921b52026-07-24
    fix(systematic-debugging): find-polluter accepts ./-prefixed patterns and matches top-level tests
    Jesse Vincent
  • 6015d372026-07-24
    fix(systematic-debugging): match find -path ./ prefix in find-polluter.sh (#2011)
    dev_Hakaze
  • a8686312026-07-24
    docs(using-superpowers): drop dangling subagent-support anchor (#2010)
    Mark Rada
  • ebdd4ec2026-07-24
    feat(sdd): lifecycle restructure with resume-based fix loop, five-round breaker, and rationalization table
    Jesse Vincent
  • 28882fc2026-07-24
    feat(sdd): align templates and codex reference with resume-based fix rounds
    Jesse Vincent
  • 87e40502026-07-24
    feat(sdd): add scoped re-review prompt template
    Jesse Vincent
  • c6fa27e2026-07-24
    docs(plans): SDD fix-loop redesign implementation plan
    Jesse Vincent