Agent Skills
Instruction packs that give your AI agent know-how. Three different kinds — pick the right one below.
✦ Standalone skills2,933
Self-contained. Install one into any project and it works on its own — no other software needed.
🧰 Tool add-ons725
Come bundled with a specific tool and only work together with it — they teach your agent how to operate that tool.
extract-errors
✓★ 246,200by facebook
Extract and manage error codes for React applications. Automatically extracts error messages from React source code and assigns unique error codes to new messages Detects "unknown error code" warnings and flags messages that need code assignment Validates that error codes remain synchronized with the current codebase through a simple yarn command
🧰 Not standalone — use together with react/react
author-contributions
✓★ 187,000by microsoft
Identify all files a specific author contributed to on a branch vs its upstream, tracing code through renames. Use when asked who edited what, what code an…
🧰 Not standalone — use together with microsoft/vscode
cpu-profile-analysis
✓★ 187,000by microsoft
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-*.json). Use when: profiling performance, investigating slow functions, comparing…
🧰 Not standalone — use together with microsoft/vscode
fix-ci-failures
✓★ 187,000by microsoft
Investigate and fix CI failures on a pull request. Use when CI checks fail on a PR branch — covers finding the PR, identifying failed checks, downloading logs…
🧰 Not standalone — use together with microsoft/vscode
memory-leak-audit
✓★ 187,000by microsoft
Audit code for memory leaks and disposable issues. Use when reviewing event listeners, DOM handlers, lifecycle callbacks, or fixing leak reports. Covers…
🧰 Not standalone — use together with microsoft/vscode
project-setup-info-context7
✓★ 187,000by microsoft
Comprehensive setup steps to help the user create complete project structures in a VS Code workspace. This tool is designed for full project initialization and…
🧰 Not standalone — use together with microsoft/vscode
heap-snapshot-analysis
✓★ 187,000by microsoft
Analyze V8 heap snapshots to investigate memory leaks and retention issues. Use when given .heapsnapshot files, asked to compare before/after snapshots, asked…
🧰 Not standalone — use together with microsoft/vscode
accessibility
✓★ 187,000by microsoft
Primary accessibility skill for VS Code. REQUIRED for new feature and contribution work, and also applies to updates of existing UI. Covers accessibility help…
🧰 Not standalone — use together with microsoft/vscode
find-release
✓★ 177,600by flutter
A skill to find the lowest Dart and Flutter release containing a given commit. Use this skill whenever users ask about when a commit landed in Flutter or Dart…
🧰 Not standalone — use together with flutter/flutter
dart-log-failure-parser
✓★ 177,600by flutter
Parse failures from Dart and Flutter test logs.
🧰 Not standalone — use together with flutter/flutter
add-or-fix-type-checking
✓★ 162,200by huggingface
Fixes broken typing checks detected by ty, make typing, or make check-repo. Use when typing errors appear in local runs, CI, or PR logs.
🧰 Not standalone — use together with huggingface/transformers
authoring-skills
✓★ 140,300by vercel
Use this skill when creating or modifying agent skills in .agents/skills/ .
🧰 Not standalone — use together with vercel/next.js
v8-jit
✓★ 140,300by vercel
Use this skill when writing or optimizing performance-critical code paths in Next.js server internals — especially per-request hot paths like rendering, streaming, routing, and caching.
🧰 Not standalone — use together with vercel/next.js
publish-extension
✓★ 136,000by microsoft
Guide for distributing your Command Palette extension through the Microsoft Store, WinGet, or both.
🧰 Not standalone — use together with microsoft/powertoys
winmd-api-search
✓★ 136,000by microsoft
Find and explore Windows desktop APIs. Use when building features that need platform capabilities — camera, file access, notifications, UI controls, AI/ML,…
🧰 Not standalone — use together with microsoft/powertoys
dev-toolbar-review
✓★ 105,700by supabase
Use when reviewing PRs that touch packages/dev-tools/, packages/common/posthog-client.ts,
🧰 Not standalone — use together with supabase/supabase
vercel-composition-patterns
✓★ 105,700by supabase
React composition patterns that scale. Use when refactoring components with
🧰 Not standalone — use together with supabase/supabase
github-issue-creator
✓★ 105,700by google-gemini
Use this skill when asked to create a GitHub issue. It handles different issue
🧰 Not standalone — use together with google-gemini/gemini-cli
string-reviewer
✓★ 105,700by google-gemini
Act as a Senior UX Writer. Look for user-facing strings that are too long, unclear, or inconsistent. This includes inline text, error messages, and other user-facing text.
🧰 Not standalone — use together with google-gemini/gemini-cli
vitest
✓★ 105,700by supabase
Vitest fast unit testing framework powered by Vite with Jest-compatible API. Use when writing tests, mocking, configuring coverage, or working with test…
🧰 Not standalone — use together with supabase/supabase
greeter
✓★ 105,700by google-gemini
A friendly greeter skill
🧰 Not standalone — use together with google-gemini/gemini-cli
pirate-skill
✓★ 105,700by google-gemini
Speak like a pirate.
🧰 Not standalone — use together with google-gemini/gemini-cli
code-reviewer
✓★ 105,700by google-gemini
Automated code review for local changes and remote pull requests with structured analysis across correctness, maintainability, and security. Supports both local file system changes (staged and unstaged) and remote PRs (by number or URL) with automatic GitHub CLI checkout Analyzes code across seven dimensions: correctness, maintainability, readability, efficiency, security, edge case handling, and test coverage Runs optional preflight verification suites (e.g., npm run preflight ) to catch...
🧰 Not standalone — use together with google-gemini/gemini-cli
pr-creator
✓★ 105,700by google-gemini
Guided pull request creation that enforces repository templates and safety standards. Enforces branch safety with critical checks to prevent commits and pushes to main Locates and applies repository-specific PR templates from .github/ directories, supporting multiple template variants Guides description drafting with template structure preservation, checklist completion, and issue linking Includes preflight validation via npm run preflight to catch build, lint, and test failures before PR...
🧰 Not standalone — use together with google-gemini/gemini-cli
review-duplication
✓★ 105,700by google-gemini
Use this skill during code reviews to proactively investigate the codebase for duplicated functionality, reinvented wheels, or failure to reuse existing…
🧰 Not standalone — use together with google-gemini/gemini-cli
skill-creator
✓★ 105,700by google-gemini
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Gemini CLI's…
🧰 Not standalone — use together with google-gemini/gemini-cli
behavioral-evals
✓★ 105,700by google-gemini
Guidance for creating, running, fixing, and promoting behavioral evaluations. Use when verifying agent decision logic, debugging failures, debugging prompt…
🧰 Not standalone — use together with google-gemini/gemini-cli
async-pr-review
✓★ 105,700by google-gemini
Trigger this skill when the user wants to start an asynchronous PR review, run background checks on a PR, or check the status of a previously started async PR…
🧰 Not standalone — use together with google-gemini/gemini-cli
babysit-pr
✓★ 95,500by openai
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is…
🧰 Not standalone — use together with openai/codex
code-review
✓★ 95,500by openai
Run a final code review on a pull request
🧰 Not standalone — use together with openai/codex