Model VS Skills Intelligence

Public Agent Skills catalogue

Valid public SKILL.md packages, grouped by purpose and ordered with observable repository signals. This page is a catalogue, not an evaluation or installation recommendation.

Current source snapshot

1,434 valid skills from 90 accepted public repositories across 8 categories. Updated . Source: GitHub public repositories.

Method: Only public repositories containing valid SKILL.md packages are included. Repository stars and forks show repository popularity, not skill quality; third-party scripts are never executed.

Limits: Package metadata does not establish security, maintenance, compatibility, or fitness for a particular use. Review source instructions before using a package.

Representative skills from this snapshot

brainstorming

Repository: obra/superpowers

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Repository signals: 282,170 stars; 25,275 forks. First indexed: .

dispatching-parallel-agents

Repository: obra/superpowers

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

Repository signals: 282,170 stars; 25,275 forks. First indexed: .

executing-plans

Repository: obra/superpowers

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

Repository signals: 282,170 stars; 25,275 forks. First indexed: .

finishing-a-development-branch

Repository: obra/superpowers

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

Repository signals: 282,170 stars; 25,275 forks. First indexed: .

receiving-code-review

Repository: obra/superpowers

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

Repository signals: 282,170 stars; 25,275 forks. First indexed: .

requesting-code-review

Repository: obra/superpowers

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

Repository signals: 282,170 stars; 25,275 forks. First indexed: .

subagent-driven-development

Repository: obra/superpowers

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

Repository signals: 282,170 stars; 25,275 forks. First indexed: .

systematic-debugging

Repository: obra/superpowers

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

Repository signals: 282,170 stars; 25,275 forks. First indexed: .

test-driven-development

Repository: obra/superpowers

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

Repository signals: 282,170 stars; 25,275 forks. First indexed: .

using-git-worktrees

Repository: obra/superpowers

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

Repository signals: 282,170 stars; 25,275 forks. First indexed: .

using-superpowers

Repository: obra/superpowers

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

Repository signals: 282,170 stars; 25,275 forks. First indexed: .

verification-before-completion

Repository: obra/superpowers

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

Repository signals: 282,170 stars; 25,275 forks. First indexed: .

Explore the interactive catalogue to filter all current entries by category and source metadata.