Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 870 files from 1 769 authors, of which 62 217 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
ESM Support. Reference when using this Prisma feature.
Prisma Config. Reference when using this Prisma feature.
Removed Features. Reference when using this Prisma feature.
Schema Changes. Reference when using this Prisma feature.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
|
| Extract clean markdown from any URL, including JavaScript-rendered SPAs. Use this skill whenever the user provides a URL and wants its content, says "scrape", "grab", "fetch", "pull", "get the page", "extract from this URL", or "read this webpage". Handles JS-rendered pages, multiple concurrent URLs, and returns LLM-optimized markdown. Use this instead of WebFetch for any webpage content extraction.
| Web search with full page content extraction. Use this skill whenever the user asks to search the web, find articles, research a topic, look something up, find recent news, discover sources, or says "search for", "find me", "look up", "what are people saying about", or "find articles about". Returns real search results with optional full-page markdown — not just snippets. Provides capabilities beyond Claude's built-in WebSearch.
Delegate complex tasks to Amplifier's multi-agent framework. Use when: (1) research/comparison needing multiple perspectives, (2) multi-file code projects, (3) architecture/design reviews, (4) user asks for deep/thorough work. NOT for: simple Q&A, quick edits, casual chat, anything needing <5s response. CLI: amplifier-openclaw.
> Scans the Teams platform based app code base. Evaluates the code based on the rules described in the skill. Generates a report on the NGC readiness of the app based on the rules. Trigger phrases include "Generate a report for NGC readiness", "NGC readiness report", "Scan for issues related to NGC" etc.
Use when setting up, operating, migrating, repairing, or explaining an OpenClaw deployment on Hugging Face with the ML Claw `mlclaw` CLI. Covers the browser Space gateway, Hugging Face OAuth, local gateway mode, private Storage Buckets, Telegram as an optional connector, Docker context pinning, model selection through the Hugging Face Router, OpenAI API key setup, costs, diagnostics, and state safety.
Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingface-cli`.
Use ML Claw's HF Broker for protected Hugging Face repository and bucket reads, writes, temporary grants, recovery, and revocation. Use instead of asking for or exposing a Hugging Face access token.
> Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. "which model runs on my laptop/machine/device", "recommend a model for", "what LLM should I use for", "compare models for", "what's state of the art for", or any question about choosing an AI model for a specific use case. Always use this skill when the user wants model recommendations or comparisons, even if they don't explicitly mention HuggingFace or benchmarks.
Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't build or run, or otherwise work with `hf spaces …`, `@spaces.GPU`, Space README frontmatter, or the `spaces` Python package.
> Multi-agent QA review team for code changes. This skill should be used when the user asks to "review my code", "run QA", "qa-team", "review this branch", "code review", "check my changes", or wants a comprehensive multi-perspective code review of the current branch's changes. Spawns parallel specialist agents (security, database, reliability, compatibility, data integrity, performance, frontend, copy) that independently review the diff and produce a converged report. Also includes two generalist reviewers for convergence validation.
| Manager-side team rollup for Copilot Cowork ROI. Aggregates the de-identified stats teammates post (via the Cowork Team Report Member skill) to a shared Teams channel into ONE anonymized HTML dashboard (five tabs, with the how-to-read guide built in), then emails the channel members a summary with the dashboard attached. First run asks for the Teams channel link and remembers it; each run reads the latest 15 days and keeps the latest post per person. Numbers only — no names or files; a Role breaks out only when 3+ share it. Small homogeneous teams; not org-wide. Use when the user asks to "build the team Cowork Team Report", "aggregate my team's Cowork stats", "roll up the channel posts", "manager Cowork Team Report", "email the team dashboard", or set up / refresh the rollup.
| Member step of the team Cowork Team Report rollup. Harvests the signed-in user's own Copilot Cowork session history from OneDrive, lets the user exclude any chat/task, computes impact metrics, and posts a de-identified, TABLE-FORMATTED stats message to your team's dedicated "Cowork report" Teams channel (the channel link is requested on first run and remembered). Tables cover KPIs, time-by-category, value pillars, jobs-to-be-done, business processes, roles, skills, and deliverable types. Person names, file names and prompts are excluded; process/JTBD and customer/account names are kept. Bundles its own pipeline. Runs once or on a biweekly schedule (every other Monday; scheduled runs email the user to review/exclude sessions before posting). Use when the user asks to "post my Cowork Team Report stats", "send my Cowork stats to the team channel", "run the Cowork Team Report member step", or "share my Cowork impact with the team".
| Manager-side team rollup for Copilot Cowork ROI. Aggregates the de-identified stats teammates post (via the Cowork Dashboard Member skill) to a shared Teams channel into ONE anonymized HTML dashboard (five tabs), then emails the channel members a summary with the dashboard and a one-page PDF guide attached. First run asks for the Teams channel link and remembers it; each run reads the latest 15 days and keeps the latest post per person. Numbers only — no names or files; a Role breaks out only when 3+ share it. Small homogeneous teams; not org-wide. Use when the user asks to "build the team Cowork Dashboard", "aggregate my team's Cowork stats", "roll up the channel posts", "manager Cowork Dashboard report", "email the team dashboard", or set up / refresh the rollup.
> Use this skill whenever the user wants to add, create, or write a new eval (evaluation) in the auth0-evals repository. This includes requests like "add an eval for X", "create a new eval", "write a grader for Y", "add a test case for the Z SDK", or "extend the eval suite". Use it whenever the user mentions eval IDs, graders, PROMPT.md, graders.ts, or wants to measure how well an LLM handles an Auth0 SDK integration task. Always use this skill before writing any eval files — it contains critical conventions that are easy to get wrong.
Set up slop-farmer for a GitHub repository end-to-end. Use this whenever the user mentions slop-farmer setup, creating a repo config, choosing scrape limits, checking GitHub rate limits, cleaning PR template boilerplate, inspecting issue/PR title patterns with gh, installing or authenticating the Hugging Face hf CLI, publishing datasets, reproducing dashboards, or deploying the static dashboard to a Hugging Face Space. Be proactive even if the user only asks for one piece of the setup, because config, auth, dataset publishing, and dashboard deployment are tightly coupled here.
> Analyze the current session and decide whether an attractor pipeline is "should this be an attractor?", "design a pipeline for", "attractorify this", "do I need an attractor pipeline?", "turn this into a pipeline".
Publish a single demo to v0 and optionally create Typefully drafts. Use when the user says "publish", "publish to v0", or "create typefully draft" for a demo.
End-to-end publish + Typefully draft pipeline for a single demo. Use when the user says "draft", "create draft", "typefully draft", or wants to publish a demo and create social thread drafts in one go.
Use this skill whenever the user mentions Microsoft Teams in a development context — whether they're building, integrating, configuring, debugging, or just asking questions. Covers bots, message extensions, embedded web apps, Adaptive Cards, dialogs, SSO, infrastructure, the Teams Developer CLI/SDK, and general Teams platform queries. If the word "Teams" appears, err on the side of invoking this skill.
Ultimate personal shopping assistant: find, compare, buy, gift, and reorder products across the Shop catalog containing millions of stores. Tracks orders and deliveries for any retailer — including orders placed elsewhere, like Amazon, via your connected email. Helps get order info and initiate returns and refunds.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
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-specific Browse.sh skills, or install/refresh this browse skill.
Operate and supervise an orchid/divybot agent swarm — open issues as work, watch workers over herdr, relay-free PR supervision, governor pacing, credential health, deploy. Use when asked to check the swarm, open work, why a worker is stuck, scale/pause a target, deploy the coordinator, or fix a fleet-wide auth failure.
Cut a new transformers-mlinter release. Bumps the version across all pinned locations, updates the CHANGELOG, runs local checks and a packaged smoke test, then drives the tag-based GitHub Actions publish to PyPI. Use when asked to release, cut a version, or ship X.Y.Z.
Add a new TRF rule to the mlinter. Checks for duplicates, creates the rule module and TOML entry, runs against all models, and handles violations (fix or allowlist).
Build creative-coding sketches and digital art with Klint's immediate-mode Canvas 2D API in React or vanilla JavaScript.
Convene the seven act-steward agents (act-1-setup through act-7-close) into a read-only team and run a coordinated narrative, language, and consistency review across the Workflow SDK GA deck. Use when the user asks for a "narrative review", "council", "consistency pass", "deck review", or questions that span multiple acts (e.g., "does retry vocabulary carry from Act II to Act V?"). Skip for single-slide edits — read the relevant slide directly.
> Build multi-platform chat bots with Chat SDK (`chat` npm package). Use when developers want to (1) Build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, (2) Use Chat SDK to handle mentions, direct messages, subscribed threads, reactions, slash commands, cards, modals, files, or AI streaming, (3) Set up webhook routes or multi-adapter bots, (4) Send rich cards or streamed AI responses to chat platforms, (5) Build or maintain a custom adapter or state adapter. Triggers on "chat sdk", "chat bot", "slack bot", "teams bot", "google chat bot", "discord bot", "telegram bot", "whatsapp bot", "@chat-adapter", "@chat-adapter/state-", "custom adapter", "state adapter", "build adapter", and building bots that work across multiple chat platforms.
| dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.
Deploy, manage, and develop projects on Vercel from the command line
Migrate a Next.js application from Webflow Cloud to Vercel. Use this skill when a user wants to move, migrate, or port a Next.js app off Webflow Cloud onto Vercel. This covers removing the OpenNext Cloudflare adapter (@opennextjs/cloudflare) and the initOpenNextCloudflareForDev dev hook, uninstalling Wrangler, deleting the Webflow Cloud config files (webflow.json, wrangler.json, open-next.config.ts, cloudflare-env.d.ts), dropping the base path the app mounted under on a Webflow site (basePath and assetPrefix in next.config.ts), removing the Edge runtime directive (export const runtime = 'edge') from Route Handlers and middleware, repointing Cloudflare storage bindings read through getCloudflareContext().env (Object Storage/R2, Key Value Store/Workers KV, SQLite/D1) to Vercel storage, recreating environment variables, and deploying. Next.js runs natively on Vercel, so no adapter replaces OpenNext. Triggers include phrases like 'migrate to Vercel', 'move off Webflow Cloud', 'Next.js Webflow Cloud to Vercel', or the presence of webflow.json, wrangler.json, @opennextjs/cloudflare, open-next.config.ts, or getCloudflareContext in a Next.js project. Do not use for non-Next.js frameworks or for migrations in the opposite direction (Vercel to Webflow Cloud).
Migrate a TanStack Start application from Netlify to Vercel. Use this skill when a user wants to move, migrate, or port a TanStack Start (or TanStack) app off Netlify onto Vercel. This covers swapping @netlify/vite-plugin-tanstack-start for Nitro, removing netlify.toml, repointing Netlify Blobs and Netlify DB to Vercel storage (Vercel Blob, Redis, Edge Config, Postgres), and moving Scheduled Functions and Background Functions to their Vercel equivalents (Cron Jobs and Queues), then deploying. Triggers include phrases like 'migrate to Vercel', 'move off Netlify', 'TanStack Start Netlify to Vercel', or the presence of netlify.toml, @netlify/vite-plugin-tanstack-start, or @netlify/blobs imports in a TanStack project. Do not use for non-TanStack frameworks or for migrations in the opposite direction (Vercel to Netlify).
Migrate an Astro application from Webflow Cloud to Vercel. Use this skill when a user wants to move, migrate, or port an Astro app off Webflow Cloud onto Vercel. This covers swapping the @astrojs/cloudflare adapter for @astrojs/vercel, removing Wrangler and the Webflow Cloud config files (webflow.json, wrangler.json, worker-configuration.d.ts), dropping the base path the app mounted under on a Webflow site, removing the Edge runtime directive from API routes, repointing Cloudflare storage bindings read through locals.runtime.env (Object Storage/R2, Key Value Store/Workers KV, SQLite/D1) to Vercel storage, recreating environment variables, and deploying. Triggers include phrases like 'migrate to Vercel', 'move off Webflow Cloud', 'Astro Webflow Cloud to Vercel', or the presence of webflow.json, wrangler.json, @astrojs/cloudflare, or locals.runtime.env in an Astro project. Do not use for non-Astro frameworks or for migrations in the opposite direction (Vercel to Webflow Cloud).
Migrate a TanStack Start application from Cloudflare Workers to Vercel. Use this skill when a user wants to move, migrate, or port a TanStack Start (or TanStack) app off Cloudflare Workers or Wrangler onto Vercel. This covers swapping the @cloudflare/vite-plugin for Nitro, removing Wrangler config, repointing Cloudflare bindings (R2, Workers KV, D1, Durable Objects, Workers AI) to Vercel storage, and moving Cron Triggers and Queues to their Vercel equivalents, then deploying. Triggers include phrases like 'migrate to Vercel', 'move off Cloudflare', 'TanStack Start Cloudflare to Vercel', or the presence of wrangler.jsonc, wrangler.toml, or cloudflare:workers imports in a TanStack project. Do not use for non-TanStack frameworks or for migrations in the opposite direction (Vercel to Cloudflare).
Generates agent-friendly markdown documentation for API routes. Use when user says "generate docs", "document this API", "create API documentation", or "make docs for my endpoints".
>- Use single-quoted strings for multiline git commit messages in the Shell tool. Prevents heredoc escaping failures that produce garbled commit messages.
>- package.json version, propagates it to every workspace package in lockstep, merges the PR, the `Publish to npm` workflow runs automatically and ships the new version to npm under dist-tag `latest`, plus a matching GitHub Release with auto-generated notes. Use when a maintainer asks to "cut the next minor", "bump to the next version", "open a release PR", or "prepare a publish PR".
Debug ClickHouse reference test failures (the tests/clickhouse-reference-{ast,format,explain,round-trip} suites). Use when one or more of those reference cases fail and you need to see what this library produced vs. the committed expected output. Maps a failing case to the right diff:* npm script and walks through isolating, diffing, and fixing the cause in the grammar/formatter/explain code.
Manage Spec Kit workflow step types via `specify workflow step`. USE FOR: listing built-in and custom workflow step types, installing/removing a custom step type from a catalog, searching/showing step-type info, managing step-type catalog sources. DO NOT USE FOR: running or installing whole workflows (use speckit-workflow), or bundles (use speckit-bundle).
Check for and apply Spec Kit CLI updates via `specify self`. USE FOR: checking whether a newer specify-cli release is available, previewing an upgrade with --dry-run, upgrading the CLI in place (optionally to a pinned tag). DO NOT USE FOR: checking project tools/integrations (use speckit-check) or managing extensions/presets/integrations/workflows.
Check the local environment for Spec Kit by running `specify check` (and `specify version`). USE FOR: verifying required tools are installed, diagnosing a broken spec-kit setup, reporting CLI version/feature capabilities. DO NOT USE FOR: installing or upgrading the CLI itself (use the speckit-self skill).
Detect and install the Spec Kit `specify` CLI that every other speckit skill depends on. USE FOR: checking whether `specify` is installed/on PATH, installing it when missing, fixing "command not found: specify", confirming the CLI is new enough (>= 0.11). DO NOT USE FOR: upgrading an already-installed CLI to a newer release (use speckit-self) or verifying project tools (use speckit-check).
Discover, install, and author Spec Kit bundles via `specify bundle`. USE FOR: searching/showing/listing bundles, installing/updating/removing a bundle (a curated set of extensions/presets/integrations/workflows), validating a bundle manifest, building a distributable bundle artifact, initializing a project and installing a bundle, managing bundle catalog sources. DO NOT USE FOR: individual extensions/presets/integrations/workflows (use their respective skills).
Scaffold a Spec Kit (spec-driven development) project for GitHub Copilot by running `specify init --integration copilot --integration-options="--skills"`. USE FOR: starting a new spec-kit project, bootstrapping spec-driven development in an existing repo, installing spec-kit templates/scripts/commands for Copilot. DO NOT USE FOR: managing extensions/presets/bundles of an already-initialized project (use the speckit-extension / speckit-preset / speckit-bundle skills instead).
Manage Spec Kit presets via `specify preset`. USE FOR: installing/removing presets, searching the preset catalog, showing preset info, resolving which template a preset name maps to, enabling/disabling presets, setting preset resolution priority, managing preset catalogs. DO NOT USE FOR: extensions (use speckit-extension), bundles (use speckit-bundle), or workflows (use speckit-workflow).
Manage and run Spec Kit automation workflows via `specify workflow`. USE FOR: running a workflow by ID or local YAML, resuming a paused/failed run, checking run status, listing/installing/removing workflows, searching the workflow catalog, showing a workflow step graph. DO NOT USE FOR: extensions (use speckit-extension), presets (use speckit-preset), or bundles (use speckit-bundle).
Manage Spec Kit extensions via `specify extension`. USE FOR: installing/removing/updating spec-kit extensions, searching the extension catalog, showing extension info, enabling/disabling extensions, setting extension resolution priority, managing extension catalogs. DO NOT USE FOR: presets (use speckit-preset), bundles (use speckit-bundle), or workflows (use speckit-workflow).
>- How to write, test, and deploy an app with Prisma Composer dependencies, define RPC contracts, compose Modules, declare the service input (config and secrets as one schema, read back with `input()`), compose the ready-made cron/storage/streams Modules, provision a raw S3-compatible object-store bucket with `bucket()`, find extensions (npm packages named `prisma-composer-*`), test with `mockService`/`bootstrapService`, run the whole app locally with `prisma-composer dev` and tail its logs with `prisma-composer log`, and deploy with `prisma-composer deploy` (stages, destroy). Use when building a Prisma App, wiring a service dependency, adding a Postgres database, adding scheduled jobs / blob storage / event streams / a raw bucket, writing tests for composed services, running an app locally, reading its logs, or deploying/tearing down an environment. Triggers on "prisma composer", "@prisma/composer", "prisma app", "compute()", "service.load()", "module()", "contract()", "mockService", "bootstrapService", "prisma-composer dev", "prisma-composer log", "prisma-composer deploy", "--stage", "--fresh", "--tail", "prisma-composer destroy", "prisma-composer-", "bucket()".
Run a sustained bug-farming round — keep a full swarm hunting until N distinct OpenTofu-vs-pulumi-hcl divergences are proven, then ship each as its own draft PR containing only the failing test. Use when the user asks to "find 10 more bugs", "raise the next N issues", or run another bug-hunting round.
Open a PR for the current change — branch, optional changelog fragment, and gh pr create. Use when asked to submit, open, or ship a PR.
Fix a proven OpenTofu-vs-pulumi-hcl divergence and ship it as its own PR. Use after find-tfcompat-bug has produced a failing tfcompat test — fix the runtime to match OpenTofu, sweep for the sibling bug, add unit coverage, and open a PR. Use when asked to fix/ship a known tfcompat mismatch.
Run a swarm of parallel agents that each hunt for one OpenTofu-vs-pulumi-hcl runtime divergence and prove it with a failing tfcompat test. Use when the user asks to "spin up N agents", "run a swarm", or hunt for a tfcompat mismatch in parallel.
Find and prove a single runtime divergence between OpenTofu and pulumi-hcl with a failing tfcompat test. Use when the user asks to "find another bug/mismatch", find a tfcompat mismatch, or hunt for behavior that differs from Terraform/OpenTofu.
Claude Skills — questions
Answers built from the skills we actually parsed.