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. 79 566 files from 1 758 authors, of which 61 913 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.
Vitest testing framework patterns and best practices. Use when writing unit tests, integration tests, configuring vitest.config, mocking with vi.mock/vi.fn, using snapshots, or setting up test coverage. Triggers on describe, it, expect, vi.mock, vi.fn, beforeEach, afterEach, vitest.
shadcn/ui component patterns with Radix primitives and Tailwind styling. Use when building UI components, using CVA variants, implementing compound components, or styling with data-slot attributes. Triggers on shadcn, cva, cn(), data-slot, Radix, Button, Card, Dialog, VariantProps.
Tailwind CSS v4 with CSS-first configuration and design tokens. Use when setting up Tailwind v4, defining theme variables, using OKLCH colors, or configuring dark mode. Triggers on @theme, @tailwindcss/vite, oklch, CSS variables, --color-, tailwind v4.
Reviews Rust FFI code for type safety, memory layout compatibility, string handling, callback patterns, and unsafe boundary correctness. Use when reviewing extern blocks, #[repr(C)] types, bindgen output, or code calling C/C++ libraries.
Reviews Rust macro code for hygiene issues, fragment misuse, compile-time impact, and procedural macro patterns. Use when reviewing macro_rules! definitions, procedural macros, derive macros, or attribute macros.
Comprehensive Rust code review that fans out across detected technology areas, running them in parallel when the agent supports subagents and sequentially otherwise. Use for pre-push or pre-PR review of .rs files.
> (1) writing new Rust functions or modules, (2) choosing between borrowing, cloning, or ownership patterns, (3) implementing error handling with Result types, (4) optimizing Rust code for performance, (5) configuring clippy and linting for a project, (6) deciding between static and dynamic dispatch, (7) writing documentation or doc tests.
Mandatory verification steps for all code reviews to reduce false positives. Load this skill before reporting ANY code review findings.
Reviews Rust code for ownership, borrowing, lifetime, error handling, trait design, unsafe usage, and common mistakes. Use when reviewing .rs files, checking borrow checker issues, error handling patterns, or trait implementations. Covers Rust 2024 edition patterns and modern idioms.
> (1) starting a new Rust project or workspace, (2) configuring Cargo.toml best practices, (3) setting up CI pipelines for Rust, (4) organizing a multi-crate workspace, (5) configuring clippy, rustfmt, and linting.
Reviews Rust test code for unit test patterns, integration test structure, async testing, mocking approaches, and property-based testing. Covers Rust 2024 edition changes including async fn in traits for mocks, #[expect] lint suppression, LazyLock test fixtures, and temporary scope changes affecting test assertions. Use when reviewing _test.rs files, #[cfg(test)] modules, or test infrastructure in Rust projects. Covers tokio::test, test fixtures, and assertion patterns.
Reviews serde serialization code for derive patterns, enum representations, custom implementations, and common serialization bugs. Use when reviewing Rust code that uses serde, serde_json, toml, or any serde-based serialization format. Covers attribute macros, field renaming, and format-specific pitfalls.
Reviews tokio async runtime usage for task management, sync primitives, channel patterns, and runtime configuration. Covers Rust 2024 edition changes including async fn in traits, RPIT lifetime capture, LazyLock, and if-let temporary scoping. Use when reviewing Rust code that uses tokio, async/await patterns, spawn, channels, or async synchronization. Also covers tokio-util, tower, and hyper integration patterns.
Reviews sqlx database code for compile-time query checking, connection pool management, migration patterns, and PostgreSQL-specific usage. Use when reviewing Rust code that uses sqlx, database queries, connection pools, or migrations. Covers offline mode, type mapping, and transaction patterns.
Analyze repo, detect stack, trace changes to user-facing entry points, generate E2E YAML test plan
Execute YAML test plan, stop on first failure, output rich debug prompt
Create Chinese HBG “模拟人生 / 人生副本” narrative videos with a consistent comic IP, a rapid multi-life opening, continuous natural-speed narration, synchronized short captions, dense static manga storyboards, audible fixed-level BGM, and alternating zoom/pan motion in HyperFrames. Use for 模拟人生、人生副本、统一主角漫画、快闪职业开头、旁白配图、静态漫画分镜、zoom 推拉、左右平移、Edge TTS、字幕压制，或把长篇中文人生故事组装成视频。
使用中国国家级公开天气数据查询中国天气。支持国家气象中心/中央气象台 nmc.cn、中国气象局天气页面 weather.cma.cn、中国天气网 weather.com.cn 的公开天气信息，覆盖城市实况、7 天预报、预警、空气质量、近期小时观测、未来逐小时预报、全国实况/预报地图、实况排行、雷达/卫星图层、全国预警列表、交通/环境/灾害/台风海洋/农业/数值预报等官方产品页；当用户需要判断未来具体时段是否下雨、出行、通勤、骑行、航班/高铁安排或天气风险时，按需返回可访问来源的数据、来源和发布时间。
面向 Agent 的百度 API 搜索 Skill。用于中文“查一下/搜索/联网查/最近/最新/热点”等场景，调用百度百科和百度 AI Search API，保留原始结果、去重并生成 research pack。
>- WorkRally CLI (workrally) — 面向 AI Agent 的 AIGC 漫剧视频创作全流程工具集。 支持 AI 生图、AI 生视频、项目/剧集/场次/分镜的完整 CRUD、资产库、媒资管理、无限画布、文件上传下载等。 Use when user asks to generate images, generate videos, manage projects, series, shots, upload files, download assets, manage materials, or interact with WorkRally platform via command line.
Use this skill when the user asks to parse the content of an unstructured file (PDF, PPTX, DOCX...)
Use this skill whenever a question should be answered from documents stored in a LlamaCloud Index v2 knowledge base — retrieving passages, locating indexed files, or searching indexed content through the LlamaParse Platform REST API with curl. Teaches agentic retrieval — navigating an index like a file system instead of one-shot RAG.
Use this skill whenever a task involves a document file (PDF, DOCX, PPTX, XLSX, or image) and you need to read it or pull text, tables, or specific values out of it — to answer a question about its contents, look up a figure, or extract data. Provides fast, local, model-free extraction via the `lit` CLI with disciplined, low-cost search patterns.
Write or edit Apify documentation pages following the style guide. Use when user says "write docs for", "create a new page", "document this feature", "add documentation about", "edit this doc page", or "write a guide for [topic]". Handles platform docs, guides, and reference pages with proper formatting and structure.
Review Apify documentation for style guide compliance, quality standards, and best practices. Use when user says "review this doc", "check this page", "audit documentation", "review before PR", "is this ready to publish", or "review-docs". Runs automated checks and manual review against Apify style guide.
Create structured tutorials for Apify Academy or Platform documentation. Use when user says "create a tutorial", "write a tutorial", "build a step-by-step guide", "convert this guide into a tutorial", or "tutorial for [topic]". Handles tutorial structure, learning objectives, prerequisites, step-by-step instructions, code examples, and troubleshooting sections.
Create or update OpenAPI specifications and API documentation for Apify endpoints. Use when user says "add API endpoint", "create OpenAPI spec", "document this endpoint", "add code samples for API", "update API docs", or "api-doc". Handles OpenAPI YAML, schemas, code samples, and operation IDs.
>- Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto frontier of quality vs cost — using native Agent / Workflow / loop tools instead of a standalone Python harness. Use this whenever the user wants to optimize, evolve, tune, distill, or search over a harness, scaffold, prompt system, memory or retrieval policy, context-assembly code, or summarizer while keeping the model fixed; whenever they mention Meta-Harness, harness optimization, scaffold evolution, automatic prompt/memory optimization, an evolutionary or Pareto search over candidate implementations, or "make the harness/agent better without retraining"; and whenever the gain must come from the code AROUND the model rather than the model weights. Reproduces the Meta-Harness paper's method natively, with no claude_wrapper.py and no metered solver API.
Use when the user says "/plan-execute", "plan execute", "implement plan", or "execute plan" and provides a finalized plan file path to carry out. Claude orchestrates, Codex writes code, Claude reviews, and Codex fixes issues until the quality bar is met.
Use when the user says "/plan-review", "plan review", or "PRD review" and provides a plan file path that needs critical review and iterative refinement with Codex.
Delegate coding tasks to Codex CLI for execution, or discuss implementation approaches with it. CodeX is a cost-effective, strong coder — great for batch refactoring, code generation, multi-file changes, test writing, and multi-turn implementation tasks. Use when the plan is clear and needs hands-on coding. Claude handles architecture, strategy, copywriting, and ambiguous problems better.
Sets up and installs the AI Software Architect framework in a NEW project for the FIRST time. Use when the user requests "Setup .architecture", "Setup ai-software-architect", "Initialize architecture framework", "Install software architect", or similar setup/installation phrases. Do NOT use for checking status (use architecture-status), creating documents (use create-adr or reviews), or when framework is already set up.
Conducts a comprehensive multi-perspective architecture review using ALL architecture team members. Use when the user requests "Start architecture review", "Full architecture review", "Review architecture for version X.Y.Z", "Conduct comprehensive review", or when they want assessment from multiple perspectives. Do NOT use for single-specialist reviews (use specialist-review instead) or for status checks (use architecture-status instead).
Displays the roster of architecture team members with their specialties and expertise areas. Use when the user asks "Who's on the architecture team?", "List architecture members", "Show me the architects", "What specialists are available?", "Who can I ask for reviews?", or wants to discover available experts. Do NOT use for requesting reviews (use specialist-review or architecture-review) or checking documentation status (use architecture-status).
Conducts a focused review from ONE specific specialist's perspective (e.g., Security Specialist, Performance Expert). Use when the user requests "Ask [specialist role] to review [target]", "Get [specialist]'s opinion on [topic]", "Have [role] review [code/component]", or when they want deep expertise in ONE specific domain. Do NOT use for comprehensive multi-perspective reviews (use architecture-review instead) or for listing available specialists (use list-members instead).
Creates a NEW Architectural Decision Record (ADR) documenting a specific architectural decision. Use when the user requests "Create ADR for [topic]", "Document decision about [topic]", "Write ADR for [choice]", or when documenting technology choices, patterns, or architectural approaches. Do NOT use for reviews (use architecture-review or specialist-review), checking existing ADRs (use architecture-status), or general documentation.
Enables and configures Pragmatic Guard Mode (YAGNI Enforcement) to prevent over-engineering. Use when the user requests "Enable pragmatic mode", "Turn on YAGNI enforcement", "Activate simplicity guard", "Challenge complexity", or similar phrases.
Reports on the health and state of architecture documentation (counts of ADRs, reviews, activity levels, documentation gaps). Use when the user asks "What's our architecture status?", "Show architecture documentation", "How many ADRs do we have?", "What decisions are documented?", "Architecture health check", or wants an overview/summary of documentation state. Do NOT use for listing team members (use list-members), creating new documents (use create-adr), or conducting reviews (use architecture-review or specialist-review).
Secure environment variable management with Varlock. Use when handling secrets, API keys, credentials, or any sensitive configuration. Ensures secrets are never exposed in terminals, logs, traces, or Claude's context. Trigger phrases include "environment variables", "secrets", ".env", "API key", "credentials", "sensitive", "Varlock".
Skillsmith is the canonical lifecycle manager for agent skills (SKILL.md format) across any MCP-capable agent runtime — Claude Code, Cursor, Copilot, Codex, Windsurf. Discover, evaluate, install, use, maintain, author, govern, retire skills. Triggers: 'use Skillsmith', 'ask Skillsmith', 'search Skillsmith', 'find a Skillsmith skill', 'install with Skillsmith', 'Skillsmith trust tier', 'Skillsmith audit', 'create a skill with Skillsmith', 'publish to Skillsmith', 'Skillsmith quota', 'pin a Skillsmith skill', 'compare Skillsmith skills'. Routes natural-language requests to Skillsmith MCP tools and CLI commands.
Discover, install, compare, and manage Claude Code skills. Search the registry, get recommendations, validate skill quality, and manage your installed skills.
Delegate your agent-skill lifecycle: keep skills current, audit and clean up your inventory, and vet skills before you install them. The Skillsmith Agent diagnoses in full for free, proposes a batched fix plan, and changes files only with your per-changeset approval, with one-step undo. Triggers: \"ask the Skillsmith Agent\", \"clean up my skills\", \"what skills are outdated\", \"audit my skills\", \"vet this skill before I install it\".
| Professional nmap scanning techniques and optimization for penetration testing. Use this skill when you need to perform network reconnaissance, port scanning, or service enumeration during authorized security assessments.
| Comprehensive system control operations for security testing. Use this skill when you need unified access to file operations, process management, system information, and command execution through a single interface during authorized penetration testing.
| Security-focused command execution techniques for penetration testing. Use this skill when executing system commands during authorized security assessments. Covers Windows and Linux command execution, common security testing commands, and best practices for avoiding detection.
| System-level commands for security assessment and system enumeration. Use this skill when performing local system reconnaissance, process analysis, or system information gathering during authorized security testing.
| Route shell, runtime.command, runtime.script, mcp.call, cli.run, or task_graph.submit work through Secbot's ExecGo-backed control tools.
| Persistent terminal session management for security testing. Use this skill when you need an interactive shell session that maintains state between commands (working directory, environment variables, etc.) during authorized penetration testing.
> 灵魂引擎 — 让唤醒后的 Relic 活起来。当用户说"跟XX聊天""召唤XX"或直接调用 /relic-talk 时触发。
> 万物永生引擎 — 把任何你在乎的东西唤醒成可交互的数字灵魂。 当用户说"帮我唤醒/蒸馏/创建一个 Relic"、"我想永生XX"、"把XX做成 Relic"、 "我想保存/留住/纪念XX的记忆"、"帮我做一个数字分身"、 "我想和已故/离开的XX聊天"、"让我跟XX继续说话"时触发。 支持蒸馏对象：人类、宠物、关系、团队文化、地方、时刻、公众人物、业务专家、飞书协作记忆。 支持数据源：微信、QQ、Telegram、Discord、Slack、飞书、iMessage、照片、语音、实时对话。
> 灵魂护盾 — 保护 Relic 不被未授权复制、篡改或滥用。 提供灵魂指纹、授权协议和伦理框架。可直接调用 /relic-shield。
> 灵魂唤醒室 — 从多源数据中唤醒四维灵魂画像。 当用户说"帮我唤醒/蒸馏/创建一个 Relic"或直接调用 /relic-forge 时触发。 支持人类、宠物、关系、地方、团队、时刻等万物蒸馏。
Comprehensive Drupal patterns from "Drupal at Your Fingertips" by Selwyn Polit. Covers 50+ topics including services, hooks, forms, entities, caching, testing, and more.
Drupal Canvas Code Components - a framework for building interactive, server-side-rendered components in Drupal. Covers scaffolding with @drupal-canvas/create, the Nebula starter template, component architecture, and integration with Acquia Source Site Builder.
Drupal Canvas SDC (Single Directory Components) with Twig templates. Use when creating, modifying, or troubleshooting Twig-based Canvas components in themes/modules, component.yml schemas, Canvas preview issues, or page builder functionality. For React/JSX Code Components, see drupal-canvas-code-components skill. (project)
Drupal configuration management including config import/export, config splits (complete and partial), syncing config across environments, drush commands for config management, config:import, config:export, config-split commands
Canvas contribution workflow for contributing features/fixes back to drupal.org. Use when developing features for Canvas module that will be contributed upstream. Covers two-repository workflow, issue forks, merge requests, and composer patches.
Connect to an Acquia Source ("Source powered by Drupal CMS") site — its JSON:API and MCP endpoints, OAuth2 auth, the @drupal-canvas CLI, and the Canvas Page API deploy workflow. Use when wiring an AI agent or app to a Source CMS site, building/uploading Drupal Canvas Code Components, deploying landing pages via the Page API, or registering the Source MCP server with Claude Code/Cursor.
Reconcile Drupal configuration drift between a working tree and a deployed environment one item at a time, deciding import (disk wins) vs export (DB wins) vs skip for each difference. Use when `drush config:status` shows drift, after pulling a fresh DB, before a deploy, or when local config and a remote/prod environment disagree. Pantheon/Terminus-aware but works with any remote alias; never writes to production.
Comprehensive guide for managing Drupal contributed modules via Composer, including updates, patches, version compatibility, and Drupal 11 upgrades. Use when updating modules or resolving dependency issues.
Claude Skills — questions
Answers built from the skills we actually parsed.