Skills

Skills

Find a skill for the job, see what it can touch and what our pattern check flagged at the exact commit, then install it in Claude Code, Codex, Cursor or any agent that reads SKILL.md.

3,887 skills from 42 repos · copies merged · data as of 26 Oct 2026 · How we check

Official collections

Published from the vendor's own GitHub organisation.

All skills

3,887 skills

  • brainstorming

    obra/superpowers

    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).

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Reaches the network +2

    MIT · 305.7k repo stars · Updated 21 Oct 2026

  • diagnosing-superpowers

    obra/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 long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Reaches the network +1

    MIT · 305.7k repo stars · Updated 20 Oct 2026

  • dispatching-parallel-agents

    obra/superpowers

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

    Pattern check: Nothing flaggedWhat it can touch: Instructions only

    MIT · 305.7k repo stars · Updated 23 Jul 2026

  • executing-plans

    obra/superpowers

    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

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Bundles scripts

    MIT · 305.7k repo stars · Updated 21 Oct 2026

  • finishing-a-development-branch

    obra/superpowers

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

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Reaches the network

    MIT · 305.7k repo stars · Updated 12 Aug 2026

  • receiving-code-review

    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

    Pattern check: Nothing flaggedWhat it can touch: Reaches the network

    MIT · 305.7k repo stars · Updated 23 Jul 2026

  • requesting-code-review

    obra/superpowers

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

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands

    MIT · 305.7k repo stars · Updated 9 Oct 2026

  • subagent-driven-development

    obra/superpowers

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

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Bundles scripts

    MIT · 305.7k repo stars · Updated 21 Oct 2026

  • systematic-debugging

    obra/superpowers

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

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Bundles scripts

    MIT · 305.7k repo stars · Updated 9 Oct 2026

  • test-driven-development

    obra/superpowers

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

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands

    MIT · 305.7k repo stars · Updated 18 Sept 2026

  • using-git-worktrees

    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

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Reaches the network

    MIT · 305.7k repo stars · Updated 23 Jul 2026

  • using-superpowers

    obra/superpowers

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

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands

    MIT · 305.7k repo stars · Updated 18 Sept 2026

  • verification-before-completion

    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

    Pattern check: Nothing flaggedWhat it can touch: Instructions only

    MIT · 305.7k repo stars · Updated 23 Jul 2026

  • writing-plans

    obra/superpowers

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

    Pattern check: Nothing flaggedWhat it can touch: Instructions only

    MIT · 305.7k repo stars · Updated 25 Sept 2026

  • writing-skills

    obra/superpowers

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

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Reaches the network +2

    MIT · 305.7k repo stars · Updated 21 Oct 2026

  • accessibility

    affaan-m/ECC

    Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels, accessibility traits and hints, focus management, contrast, target size, and screen-reader support. Use when building or auditing UI for accessibility compliance, keyboard navigation, or screen-reader support.

    Pattern check: Nothing flaggedWhat it can touch: Names web addresses

    MIT · 290.0k repo stars · Updated 27 Sept 2026

  • agent-architecture-audit

    affaan-m/ECC

    Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands

    MIT · 290.0k repo stars · Updated 11 Aug 2026

  • agent-eval

    affaan-m/ECC

    Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Names web addresses

    MIT · 290.0k repo stars · Updated 11 Aug 2026

  • agent-harness-construction

    affaan-m/ECC

    Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent's tool set, action space, or observation format.

    Pattern check: Nothing flaggedWhat it can touch: Instructions only

    MIT · 290.0k repo stars · Updated 11 Aug 2026

  • agent-introspection-debugging

    affaan-m/ECC

    Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

    Pattern check: Nothing flaggedWhat it can touch: Instructions only

    MIT · 290.0k repo stars · Updated 11 Aug 2026

  • agent-payment-x402

    affaan-m/ECC

    Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk, X Layer through OKX Payments / OKX Agent Payments Protocol, and Solana plus multi-network EVM through the upstream x402 packages with facilitator-based settlement. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Reaches the network +1

    MIT · 290.0k repo stars · Updated 9 Oct 2026

  • agent-runtime-gateway-smoke-test

    affaan-m/ECC

    Verify a local agent API, temporary gateway tunnel, and remote sandbox callback with a tool-free task, then restore the original app connection.

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Reaches the network

    MIT · 290.0k repo stars · Updated 10 Oct 2026

  • agent-security-hardening

    affaan-m/ECC

    Security hardening guidance for AI agent frameworks that process untrusted content, invoke tools, write workspace files, manage runtime identifiers, or handle credentials. Use when building or reviewing an agent runtime, autonomous worker, tool gateway, memory service, or multi-tenant agent deployment. Do not use for general web application security or offensive testing.

    Pattern check: Nothing flaggedWhat it can touch: Instructions only

    MIT · 290.0k repo stars · Updated 9 Oct 2026

  • agent-self-evaluation

    affaan-m/ECC

    Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Reaches the network +2

    MIT · 290.0k repo stars · Updated 11 Oct 2026

Recently updated

By the last commit that changed the skill's folder.

  • vercel-react-view-transitions

    vercel-labs/agent-skills

    Guide for implementing smooth, native-feeling animations using React's View Transition API (`<ViewTransition>` component, `addTransitionType`, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate route changes, create shared element animations, animate enter/exit of components, animate list reorder, implement directional (forward/back) navigation animations, or integrate view transitions in Next.js. Also use when the user mentions view transitions, `startViewTransition`, `ViewTransition`, transition types, or asks about animating between UI states in React without third-party animation libraries.

    Pattern check: Nothing flaggedWhat it can touch: Runs shell commands · Names web addresses

    MIT · 33.1k repo stars · Updated 26 Oct 2026

  • eval-plan

    garrytan/gstack

    Preregister a paid eval (bars, arms, decoys, stop rules), dry-run it at zero cost, then run a three-item priced pilot whose spend table gates approval. (gstack)

    Pattern check: Items to reviewWhat it can touch: Runs shell commands · Pre-approves tools

    MIT · 137.8k repo stars · Updated 26 Oct 2026

  • plan-tune

    garrytan/gstack

    Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). (gstack)

    Pattern check: Items to reviewWhat it can touch: Runs shell commands · Pre-approves tools

    MIT · 137.8k repo stars · Updated 26 Oct 2026

  • design-motion

    garrytan/gstack

    Design motion: animate an approved design into a seamless MP4 and GIF loop. (gstack)

    Pattern check: Items to reviewWhat it can touch: Runs shell commands · Reaches the network +2

    MIT · 137.8k repo stars · Updated 26 Oct 2026

  • design-review

    garrytan/gstack

    Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. (gstack)

    Pattern check: Items to reviewWhat it can touch: Changes agent settings · Runs shell commands +3

    MIT · 137.8k repo stars · Updated 26 Oct 2026

  • plan-design-review

    garrytan/gstack

    Designer's eye plan review — interactive, like CEO and Eng review. (gstack)

    Pattern check: Items to reviewWhat it can touch: Runs shell commands · Reaches the network +2

    MIT · 137.8k repo stars · Updated 26 Oct 2026

Most-starred repos

GitHub stars on the repo that holds the skill, not on the skill itself.

Browse by category

Install in your agent

Where each agent looks for skills, from its own docs.

Tools

  • Check a repo

    Run our pattern check on any public GitHub repo before you install from it.

  • Validate a SKILL.md

    See what Claude Code, the Claude apps, OpenAI and VS Code will reject, or build one that loads everywhere.

  • Get listed

    Send us a public repo with a SKILL.md.

Skills and repo facts come from public GitHub repos. Data as of 26 Oct 2026. Sources: GitHub REST API (opens in a new tab), GitHub GraphQL API (opens in a new tab).

QAI did not write these skills and is not affiliated with their authors unless a page says so. How we check