obra/superpowers

Last imported 5h ago

ChangedSep 10, 2026

The source has changed since this result was produced. The evidence may not reflect the current state.

Upstream2ce8aa15

In Vettd Directory

Skills Assessed

Graded A or B

Graded C or F

With a Vettd Note

Skills Assessed

requesting-code-review

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

Up to date

1 finding: 0 critical, 0 medium

systematic-debugging

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

Up to date

1 finding: 0 critical, 0 medium

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 (a talk, a business, a renovation).

Up to date

17 findings: 3 critical, 13 medium

test-driven-development

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

Up to date

1 finding: 0 critical, 0 medium

The strictest TDD gate of any published pack; it refuses to write implementation before a failing test exists, and logs a rationale for every skip.

Best forgreenfield modules and refactors that already have a test harness

Not forspikes and throwaway prototypes: the red-green gate slows exploration

writing-skills

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

Up to date

8 findings: 2 critical, 5 medium

subagent-driven-development

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

Up to date

1 finding: 0 critical, 0 medium

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

Up to date

1 finding: 0 critical, 0 medium

writing-plans

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

Up to date

1 finding: 0 critical, 0 medium

finishing-a-development-branch

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

Up to date

1 finding: 0 critical, 0 medium

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 worktree fallback

Up to date

1 finding: 0 critical, 0 medium

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 success claims; evidence before assertions always

Up to date

1 finding: 0 critical, 0 medium

using-superpowers

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

Up to date

1 finding: 0 critical, 0 medium

One of the most-adopted skill packs for Claude. Aggressive by design; it mandates invoking a skill before any response and overrides “red flag” hesitations.

Best forlarge codebases, multi-step engineering work, teams wanting enforced process

Not forquick fixes, token-sensitive workflows: mandates skill invocation on every response

dispatching-parallel-agents

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

Up to date

1 finding: 0 critical, 0 medium

receiving-code-review

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Up to date

1 finding: 0 critical, 0 medium

/ Ship your skills

Import your repository to get your skills certified and listed.

Submit skills →