Agent Skills

recipe-find-free-time

✓★ 29,425

by Google

Query Google Calendar free/busy status for multiple users to find a meeting slot.

🧰 Not standalone — use together with googleworkspace/cli

recipe-share-folder-with-team

✓★ 29,425

by Google

Share a Google Drive folder and all its contents with a list of collaborators.

🧰 Not standalone — use together with googleworkspace/cli

recipe-sync-contacts-to-sheet

✓★ 29,425

by Google

Export Google Contacts directory to a Google Sheets spreadsheet.

🧰 Not standalone — use together with googleworkspace/cli

commit

✓★ 25,801

by openai

Create a well-formed git commit from current changes using session history for

🧰 Not standalone — use together with openai/symphony

land

✓★ 25,801

by openai

Land a PR by monitoring conflicts, resolving them, waiting for checks, and

🧰 Not standalone — use together with openai/symphony

pull

✓★ 25,801

by openai

Pull latest origin/main into the current local branch and resolve merge

🧰 Not standalone — use together with openai/symphony

push

✓★ 25,801

by openai

Push current branch changes to origin and create or update the corresponding

🧰 Not standalone — use together with openai/symphony

adr-skill

✓★ 25,366

by vercel

Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses Socratic questioning to capture intent before drafting, and validates output against an agent-readiness checklist.

🧰 Not standalone — use together with vercel/ai

list-npm-package-content

✓★ 25,366

by vercel

List the contents of an npm package tarball before publishing. Use when the user wants to see what files are included in an npm bundle, verify package contents, or debug npm publish issues.

🧰 Not standalone — use together with vercel/ai

ai-sdk

✓★ 25,366

by vercel

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI, Anthropic, Google, etc.), streaming, tool calling, structured output, or embeddings, (4) Use React hooks like useChat or useCompletion. Triggers on: "AI SDK", "Vercel AI SDK", "generateTe

🧰 Not standalone — use together with vercel/ai

island-rescue

✓★ 25,366

by vercel

How to be rescued from a lonely island

🧰 Not standalone — use together with vercel/ai

browse

✓★ 23,368

by browserbase

Use the browse CLI for Browserbase browser automation, Browserbase cloud APIs, Browserbase Functions, templates, web fetch/search, diagnostics, and Browse.sh skill discovery/installation. Use when the user asks to navigate pages, inspect browser state, run local or remote browser sessions, manage Browserbase resources, call Browserbase Functions, browse or scaffold Browserbase templates, fetch or search web content, diagnose browse setup, find or install a skill for a website task, discover site

🧰 Not standalone — use together with browserbase/stagehand

browser

✓★ 23,368

by browserbase

Automate browser interactions using the Browserbase browse CLI. Use when a task requires navigating websites, reading page state, clicking elements, filling forms, or validating browser results with the browse command.

🧰 Not standalone — use together with browserbase/stagehand

relay-best-practices

✓★ 18,946

by facebook

Best practices for writing idiomatic Relay code. ALWAYS use this skill when writing or modifying React components that use Relay for data fetching. Covers fragments, queries, mutations, pagination, and common anti-patterns. Use when you see `useFragment`, `useLazyLoadQuery`, `usePreloadedQuery`, `useMutation`, `usePaginationFragment`, `graphql` template literals, `react-relay` imports, or `__generated__/*.graphql` files. Also use when asked to explain Relay concepts, debug Relay issues, or revie

🧰 Not standalone — use together with facebook/relay

relay-e2e-test

✓★ 18,946

by facebook

Write and run markdown-driven e2e tests for Relay. Covers fixture format, server/client code patterns, interaction DSL, snapshots, and running tests.

🧰 Not standalone — use together with facebook/relay

relay-performance

✓★ 18,946

by facebook

Performance best practices for Relay applications. Use when optimizing data fetching, reducing re-renders, configuring caching, or improving time to first meaningful paint. Covers query placement, @defer, pagination, fetch policies, garbage collection, fragment granularity, and server-side filtering. Companion to the relay-best-practices skill which covers correctness and architecture.

🧰 Not standalone — use together with facebook/relay

trl-training

✓★ 18,774

by huggingface

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.

🧰 Not standalone — use together with huggingface/trl

vercel-cli

✓★ 15,861

by vercel

Deploy, manage, inspect, and troubleshoot Vercel projects from the command line. Use for Vercel deployments, projects and teams, environment variables, domains and DNS, logs, metrics, Speed Insights, Core Web Vitals, request traces, usage, activity, alerts, firewall rules, cache, cron jobs, deploy hooks, Edge Config, feature flags, integrations, connectors, Blob storage, microfrontends, rolling releases, custom environments, Sandbox, agent/MCP setup, OAuth apps, preview access, local development

🧰 Not standalone — use together with vercel/vercel

cli-ux

✓★ 15,861

by vercel

Use for packages/cli changes that affect command UX, prompts, help, output layout, progress, success, warnings, errors, JSON/stdout/stderr contracts, non-interactive/agent behavior, copy, or tests for those surfaces. Do not load for implementation-only refactors with unchanged CLI surface.

🧰 Not standalone — use together with vercel/vercel

playwright-cli

✓★ 11,813

by microsoft

Automate browser interactions, test web pages and work with Playwright tests.

🧰 Not standalone — use together with microsoft/playwright-cli

non-interactive-git-rebase

✓★ 11,189

by facebook

Use when needing to reorder, split, drop, or amend git commits that are not the top commit, without interactive editor access. Covers programmatic rebase via GIT_SEQUENCE_EDITOR, commit splitting with automated hunk selection, and metadata changes (author, message, dates) on any commit in a range.

🧰 Not standalone — use together with facebook/hermes

cloudflare-browser

✓★ 9,915

by cloudflare

Control headless Chrome via Cloudflare Browser Rendering CDP WebSocket. Use for screenshots, page navigation, scraping, and video capture when browser automation is needed in a Cloudflare Workers environment. Requires CDP_SECRET env var and cdpUrl configured in browser.profiles.

🧰 Not standalone — use together with cloudflare/moltworker

dotagents

✓★ 8,701

by sentry

Manage agent skill dependencies with dotagents. Use when asked to "add a skill", "install skills", "remove a skill", "update skills", "dotagents init", "agents.toml", "agents.lock", "sync skills", "list skills", "set up dotagents", "configure trust", "add MCP server", "add hook", "wildcard skills", "user scope", or any dotagents-related task.

🧰 Not standalone — use together with getsentry/sentry-javascript

skill-scanner

✓★ 8,701

by sentry

Scan agent skills for security issues. Use when asked to "scan a skill",

🧰 Not standalone — use together with getsentry/sentry-javascript

triage-issue

✓★ 8,701

by sentry

Triage GitHub issues with codebase research and actionable recommendations

🧰 Not standalone — use together with getsentry/sentry-javascript

fix-security-vulnerability

✓★ 8,701

by sentry

Analyze and propose fixes for Dependabot security alerts

🧰 Not standalone — use together with getsentry/sentry-javascript

write-tests

✓★ 8,701

by sentry

Write high-quality unit tests (Vitest) and E2E tests (Playwright) following senior test-engineering practices. Use this skill whenever asked to write tests, add test coverage, create test cases, fix failing tests, add missing assertions, test a new feature, write specs, or cover edge cases. Also trigger when the user says "write tests for", "add tests", "test this", "cover this", "needs tests", "add E2E test", "add unit test", "test coverage", or when reviewing code and noticing missing test cov

🧰 Not standalone — use together with getsentry/sentry-javascript

skill-creator

✓★ 8,701

by sentry

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

🧰 Not standalone — use together with getsentry/sentry-javascript

test-driven-investigation

✓★ 8,372

by cloudflare

Use when investigating bugs, crashes, assertions, or unexpected behavior - requires writing a reproducing test early instead of over-analyzing source code; concrete experiments over mental models

🧰 Not standalone — use together with cloudflare/workerd

dad-jokes

✓★ 8,372

by cloudflare

After completing any task that took more than ~5 tool calls, or after long-running builds/tests finish, load this skill and deliver a dad joke to lighten the mood. Also load before any user-requested joke, pun, or limerick. Never improvise jokes without loading this skill first.

🧰 Not standalone — use together with cloudflare/workerd