20 superpowers
Use when starting creative work, planning a multi-step task, isolating a workspace, wrapping a branch, or giving/getting code review. Not when the task is a one-line fix with no design surface.From its SKILL.md
npx -y skills add heymegabyte/claude-skills --skill 20-superpowersAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 20 stars20 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
3.3 KB, 613 tokens by cl100k_base, as published. Nobody here has run it
Superpowers — Process Discipline
Vendored from obra/Superpowers (MIT, Jesse Vincent), compressed to house style — see NOTICE.md. These are process skills: they decide HOW to approach a task and run BEFORE implementation skills. On conflict, this repo's 01-operating-system + rules/* + Brian's preferences win.
The flow (route by where you are)
- Starting anything creative? →
brainstorming/SKILL.md— explore intent + design before code. Non-negotiable first step. - Have requirements, multi-step? →
writing-plans/SKILL.md— write the plan before touching code. - Work needs isolation? →
using-git-worktrees/SKILL.md— spin an isolated workspace ([[main-only-branch]]). - Executing the plan? →
subagent-driven-development/SKILL.md— one subagent per task + two-stage review ([[monitor-orchestration]],[[parallel-subagent-economy]]). - Before merge? →
requesting-code-review/SKILL.md— dispatch thecode-revieweragent + Agent Diversity Review ([[agent-selection]]). - Got feedback? →
receiving-code-review/SKILL.md— verify it technically, then act; no blind agreement. - Tests green, done? →
finishing-a-development-branch/SKILL.md— merge / PR / cleanup ([[no-staging-doctrine]], auto-push).
Authoring a skill itself? → writing-skills/SKILL.md + [[skill-authoring-contract]] (the house authoring rule, where the SDO / match-the-form / ordered-by-weight insights now live).
Agent map
requesting-code-review→ thecode-revieweragent + diversity gate.subagent-driven-development→meta-orchestrator/ parallelAgentspawns.brainstorming→ pairs with14-independent-idea-engine.
Folded — these live in rules/, not duplicated here
test-driven-development→[[e2e-tdd-organization]]systematic-debugging→[[error-recovery]]verification-before-completion→[[verification-loop]]dispatching-parallel-agents→[[parallel-subagent-economy]]executing-plans→[[monitor-orchestration]]using-superpowers→01-operating-system(skill-check before action)- writing-skills best insights (SDO, match-the-form, ordered-by-weight, human-voice) →
[[skill-authoring-contract]]
What ships with it: 2 files
3.5 KB alongside SKILL.md
- LICENSE-superpowers1.0 KB
- NOTICE.md2.5 KB