AI Skills Hub - Browse 180,000+ Agent Skills

Validates test suite quality through mutation testing. Generates intelligent code mutations, runs tests to verify they catch the changes, and identifies gaps in test coverage. Use when evaluating test effectiveness, validating newly written tests, or improving test quality for mission-critical code.

Run and interact with lnd Lightning Network daemon in Docker. Use for Lightning development, testing payment channels on regtest, managing lnd containers, and calling lnd RPC endpoints (getinfo, connect, open/close channels, pay/receive). Supports bitcoind, btcd, and neutrino backends.

DDEV local development environment patterns for Drupal, including configuration, commands, database management, debugging tools, and performance optimization.

Fetches and processes GitHub pull requests waiting for review. Returns fully formatted markdown with PRs grouped by category (Feature/Bug, Chores, Dependency Updates) and sorted by age. Includes metadata like CI status, review status, size metrics, and viewing history. Use when user wants to see their PR review queue.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

This skill provides a complete workflow for handling GitHub Pull Request reviews, specifically optimized for @gemini-code-assist automated reviews. This skill should be used when addressing PR review comments, responding to reviewers, resolving threads, requesting re-reviews, or merging PRs after feedback is addressed. Triggers include: /pr-review command, "address PR feedback", "handle review comments", "respond to gemini", or any PR review lifecycle management request.

Your bulletproof guide to executing implementation phases! Handles commits, detects when phases are too big, and knows when to bail cleanly. Load this whenever you're implementing a phase - it provides clean commit protocol and signals the orchestrator when things go sideways.

The Planner's guide to becoming an orchestrator! Manages the complete implementation lifecycle: worktrees, branches, spawning Implement agents, validation gates, and decomposition triggers. When ready to execute a plan, load this skill.

Guide when to use built-in tools (WebFetch, WebSearch) and MCP servers (Parallel Search, Perplexity, Context7) for research. Synthesize findings into narrative for braindump. Use when gathering data, examples, or citations for blog posts.

Guides systematic implementation of new sustainability metrics in OSS Sustain Guard using the plugin-based metric system. Use when adding metric functions to evaluate project health aspects like issue responsiveness, test coverage, or security response time.

GitHub Projects v2 workflow (personal account) + `gpw` helper CLI for listing/creating/moving draft issues, issues, and statuses across projects. Use for any GitHub Projects request (ex: list projects, list project items, set status). ALWAYS load this core skill together with exactly one role overlay: `gh-projects-workflow-pm` (backlog mgmt), `gh-projects-workflow-coder` (implementation), or `gh-projects-workflow-reviewer` (review/verification).

Generate concise CLAUDE.md files and agent documentation following best practices. Use when setting up a new project for Claude Code, auditing existing CLAUDE.md, or creating progressive disclosure documentation structure.

Speak text aloud using high-quality AI voice synthesis (Kokoro TTS on Apple Silicon). Use when user asks to vocalize, narrate, or speak text out loud.

Complete the required presubmit. Use before declaring a feature finished, after a large refactor or when asked.

This skill should be used when the user asks to "create an agent", "write a subagent", "generate agent definition", "add agent to plugin", "write agent frontmatter", "create autonomous agent", "build subagent", needs agent structure guidance, YAML frontmatter configuration, invocation criteria with examples, or wants to add specialized subagents to Claude Code plugins with proper capabilities lists and tool access definitions.

Use when designing or reviewing web UI, implementing forms/buttons/inputs, fixing visual hierarchy issues, creating color systems, building layouts, or when interface feels cluttered, hard to read, or users don't know what to click.

Multi-agent workflow orchestration with state persistence, handoff patterns, and resumable workflows. Use when building multi-agent workflows, coordinating complex tasks, or implementing resumable processes. Triggers: 'orchestration', 'workflow', 'context save', 'handoff', 'multi-agent'.

Design RESTful APIs following Grey Haven standards - FastAPI routes, Pydantic schemas, HTTP status codes, pagination, filtering, error responses, OpenAPI docs, and multi-tenant patterns. Use when creating API endpoints, designing REST resources, implementing server functions, configuring FastAPI, writing Pydantic schemas, setting up error handling, implementing pagination, or when user mentions 'API', 'endpoint', 'REST', 'FastAPI', 'Pydantic', 'server function', 'OpenAPI', 'pagination', 'validation', 'error handling', 'rate limiting', 'CORS', or 'authentication'.

Format commit messages according to Grey Haven Studio's actual commitlint configuration (100 char header, lowercase subject, conventional commits). Use when creating git commits or reviewing commit messages.

Build LLM-powered applications and pipelines using proven methodology - task-model fit analysis, pipeline architecture, structured outputs, file-based state, and cost estimation. Use when building AI features, data processing pipelines, agents, or any LLM-integrated system. Inspired by Karpathy's methodology and production case studies.

Guide for integrating REST APIs into GraphQL supergraphs using Apollo Connectors with @source and @connect directives. Use this skill when the user: (1) mentions "connectors", "Apollo Connectors", or "REST Connector", (2) wants to integrate a REST API into GraphQL, (3) references @source or @connect directives, (4) works with files containing "# Note to AI Friends: This is an Apollo Connectors schema".

Guide for using Apollo Rover CLI to manage GraphQL schemas and federation. Use this skill when: (1) publishing or fetching subgraph/graph schemas, (2) composing supergraph schemas locally or via GraphOS, (3) running local supergraph development with rover dev, (4) validating schemas with check and lint commands, (5) configuring Rover authentication and environment.

Debug failed Render deployments by analyzing logs, metrics, and database state. Identifies errors (missing env vars, port binding, OOM, etc.) and suggests fixes. Use when deployments fail, services won't start, or users mention errors, logs, or debugging.

Validate GDScript changes by refreshing Godot cache and checking diagnostics. Use after creating or editing GDScript files.

This skill should be used when working with Rust code, reviewing Rust code, managing Rust dependencies, creating Rust projects, or fixing Rust compilation errors. It provides strict coding standards (especially FAIL FAST error handling), workspace architecture guidance, dependency management automation, and common Rust patterns.

IDA Pro 逆向分析。通过 IDAPython 脚本获取反汇编、反编译、字符串、导入表、交叉引用等信息。

Take screenshots and interact with the rendered Jekyll website

Comprehensive validation system for Claude Code plugins to ensure compliance with official plugin development guidelines and prevent installation failures

CUDA kernel development, debugging, and performance optimization for Claude Code. Use when writing, debugging, or optimizing CUDA code, GPU kernels, or parallel algorithms. Covers non-interactive profiling with nsys/ncu, debugging with cuda-gdb/compute-sanitizer, binary inspection with cuobjdump, and performance analysis workflows. Triggers on CUDA, GPU programming, kernel optimization, nsys, ncu, cuda-gdb, compute-sanitizer, PTX, GPU profiling, parallel performance.

Master user interviews including interview guide design, questioning techniques, active listening, probing, avoiding leading questions, and interview analysis. Use when conducting user interviews, designing interview guides, researching user needs, discovering problems, validating assumptions, or gathering qualitative insights. Covers interview best practices, question types, and interviewing techniques from Teresa Torres and Erika Hall.

Master research synthesis including qualitative analysis, affinity diagramming, theme identification, pattern recognition, and insight extraction. Use when synthesizing research, analyzing interviews, identifying patterns, extracting insights, organizing findings, or translating research into action. Covers synthesis methods, affinity mapping, thematic analysis, and insight generation techniques.

Search and analyze X (Twitter) using xAI Grok 4 via OpenRouter with Live Search. Trigger on prompts that explicitly or implicitly ask to "search Twitter/X", "what's trending", "tweets from @handle", "hashtag #…", "what are people saying", or that require tweet-level activity/engagement from X.

Use when automating browsers, testing pages, taking screenshots, checking UI, verifying login flows, or testing responsive behavior

Build ChatGPT Apps using the Apps SDK and MCP. Use when users want to: (1) Evaluate if their product should become a ChatGPT App (2) Design and implement MCP servers with widgets (3) Test apps locally and in ChatGPT (4) Prepare for App Store submission Triggers: "ChatGPT app", "Apps SDK", "build for ChatGPT", "ChatGPT integration", "MCP server for ChatGPT", "submit to ChatGPT"

Execute a single Solana MCP tool call over the /mcp HTTP endpoint using a TypeScript script. Use when a user needs transaction, instruction, or account analysis from the command line with explicit arguments.

ArkTS language learning and development assistant providing syntax reference, TypeScript migration guidance, and high-performance programming practices. Use when Claude needs help with: (1) Learning ArkTS basic syntax (declarations, types, functions, classes, generics, modules), (2) Migrating from TypeScript to ArkTS (syntax constraints, type system differences, incompatible features), (3) ArkTS high-performance programming optimization (memory, loops, arrays, exception handling), (4) Resolving ArkTS compile errors or runtime issues, (5) Language-related questions in HarmonyOS/OpenHarmony application development.

Fix React hydration issues where user input typed before hydration gets wiped/cleared when React takes over. Use when (1) users report input fields clearing on page load, (2) working with SSR/SSG React apps (Next.js, Remix, Astro) that have controlled inputs, (3) auditing forms for hydration safety, or (4) building new forms in statically rendered React apps.

Use when defining or updating Go CLI i18n rules in this repo, especially around locale files, env-based language selection, and key naming.

Expert guidance for building MCP (Model Context Protocol) servers using the TypeScript SDK. Use when developing MCP servers, implementing tools/resources/prompts, or working with the @modelcontextprotocol/sdk package. Covers server initialization, request handlers, Zod schemas, error handling, and JSON-RPC patterns.

This skill should be used when debugging visual CSS and layout issues in the tweakpane-table plugin, specifically for investigating column alignment problems between table headers and data rows. Use when columns don't align, widths appear incorrect, or visual inspection of rendered output is needed.

Agentic MCP - Three-layer progressive disclosure for MCP servers with Socket daemon. Use when the user needs to interact with MCP servers, query available tools, call MCP tools, or manage the MCP daemon process. Provides socket-based communication for efficient server interaction with three-layer progressive disclosure API.

Advanced 2025 Claude Code plugin features. PROACTIVELY activate for: (1) Agent Skills with progressive disclosure (2) Hook automation (PreToolUse, PostToolUse, etc.) (3) MCP server integration (4) Repository-level configuration (5) Team plugin distribution (6) Context efficiency optimization Provides cutting-edge plugin capabilities and patterns.

Extract physical observables with error estimates from completed DQMC simulations. Use when computing density, double occupancy, spin correlations, structure factors, or any measured quantity from simulation data.

Execute DQMC Monte Carlo sweeps on HDF5 simulation files. Use when running simulations, checkpointing long runs, using the queue system for multiple files, or checking simulation status.

Create HDF5 simulation files for DQMC with specified physical parameters. Use when setting up new simulations, specifying lattice size, interaction strength U, chemical potential mu, temperature (via dt and L), or number of Monte Carlo sweeps.

Bash Automated Testing System (BATS) for TDD-style testing of shell scripts. Use when: (1) Writing unit or integration tests for Bash scripts, (2) Testing CLI tools or shell functions, (3) Setting up test infrastructure with setup/teardown hooks, (4) Mocking external commands (curl, git, docker), (5) Generating JUnit reports for CI/CD, (6) Debugging test failures or flaky tests, (7) Implementing test-driven development for shell scripts.

Initialize Claude Code project settings with standard hooks and language-specific permissions. Use when setting up a new project for Claude Code or adding standard configuration to an existing project.

Generate Claude Code permissions config from session history. Use when setting up autonomous mode, configuring .claude/settings.json, avoiding --dangerously-skip-permissions, or analyzing what permissions a project needs. Reads session logs to extract Bash commands and MCP tools actually used, then generates appropriate allow/deny rules.

Comprehensive library of proven prompting patterns, frameworks, and examples for different use cases. This skill should be used when creating prompting guides, analyzing prompt effectiveness, teaching prompting techniques, or troubleshooting prompting issues. Use when writing about prompting, explaining prompting concepts to others, or improving existing prompts.

Auto-generates standardized README documentation from SKILL.md files, validates consistency (frontmatter, descriptions, terminology), and creates usage examples. Use when documenting individual skills, generating docs for multiple skills in a directory, or validating skill quality standards.

Manage backlog tasks using the Backlog.md CLI. Use for creating, editing, viewing, and searching tasks in your backlog.

Manage JIRA tickets. Use it when the user mentions JIRA with ticket IDs like FOO-123.

全面的文档创建、编辑和分析，支持跟踪更改、评论、格式保留和文本提取。当 Claude 需要处理专业文档（.docx 文件）时：(1) 创建新文档，(2) 修改或编辑内容，(3) 处理跟踪更改，(4) 添加评论，或任何其他文档任务

全面的电子表格创建、编辑和分析，支持公式、格式、数据分析和可视化。当 Claude 需要处理电子表格（.xlsx、.xlsm、.csv、.tsv 等）时：(1) 创建带有公式和格式的新电子表格，(2) 读取或分析数据，(3) 在保留公式的同时修改现有电子表格，(4) 在电子表格中进行数据分析和可视化，或 (5) 重新计算公式

一套用于使用现代前端 Web 技术（React、Tailwind CSS、shadcn/ui）创建复杂的多组件 claude.ai HTML 工件的工具集。适用于需要状态管理、路由或 shadcn/ui 组件的复杂工件，不适用于简单的单文件 HTML/JSX 工件。

Generate idiomatic Typst (.typ) code, edit existing Typst files, and answer Typst syntax questions. Use when working with Typst files (*.typ) or when the user mentions Typst markup, document creation, or formatting.

Routes API requests through the user's residential proxy to bypass cloud IP blocks. TWO use cases - (1) Runtime fallback when direct curl/fetch fails with 403/blocked errors, use fetch.py for quick retry. (2) Template for building new skills that need proxy routing, copy proxy_helper.py into the new skill.

Guide for designing SKILL.md files with bundled resources and progressive disclosure. Use when: (1) Creating new Skills, (2) Reviewing Skill quality, (3) Refactoring existing Skills for better context efficiency. Triggers: "create skill", "skill design", "SKILL.md"

Guide for designing Agent frontmatter and system prompts with proper tool selection. Use when: (1) Creating new Agents/Subagents, (2) Defining Agent roles and triggers, (3) Selecting tools and permission modes, (4) Writing system prompts. Triggers: "agent design", "create agent", "subagent", "agent frontmatter"

Verify open reading frames (ORFs) in plasmid sequences. Use when the user asks about verifying protein coding sequences, checking if an ORF is present in a plasmid, finding where a protein is encoded, or doing six-frame translation analysis.

Generate expected plasmid maps by combining vector backbones with insert sequences. Essential for clone verification workflows.

Calculate reaction buffer recipes accounting for protein stock contributions. Use when the user asks about designing reaction buffers, calculating buffer volumes, compensation buffers, or setting up biochemistry experiments with proteins.

Codon optimize protein sequences for expression using IDT's API. Use when the user asks to codon optimize genes, sequences, or accessions for a target organism (insect, E. coli, mammalian, yeast) or vector (438, 1-, pVEX).

Query and manage Quartzy lab inventory, order requests, and webhooks. Use when the user asks about lab supplies, reagent inventory, placing orders, checking order status, or creating new order requests in Quartzy.

Parse SnapGene .dna files. Use when the user asks to read, convert, or extract information from SnapGene files, or needs to convert .dna to GenBank/FASTA format.

Predict optimal construct boundaries for protein expression. Use when the user asks about domain boundaries, construct design, truncations, which region of a protein to express, or identifying disordered regions.

Design PCR primers for molecular cloning. Use when the user asks about designing primers, LIC cloning primers, sequencing primers, Gibson assembly primers, or working with NCBI accession codes for cloning.

Guidelines for assembling and purifying macromolecular complexes for structural biology.

Generate Excalidraw diagrams (.excalidraw JSON files) for whiteboarding, flowcharts, architecture diagrams, sequence diagrams, mind maps, wireframes, and org charts. Use when user requests diagrams, visual documentation, system architecture visualization, process flows, or any hand-drawn style diagram. Triggers on requests mentioning Excalidraw, diagram creation, flowcharts, architecture diagrams, sequence diagrams, wireframes, or visual documentation.

Generate slack summaries of vLLM CI SIG Slack channel activity for the RHAIIS midstream release team

This skill should be used when the user wants to visualize data. It intelligently selects the most suitable chart type from 26 available options, extracts parameters based on detailed specifications, and generates a chart image using a Python script.

Pattern for building MCP servers in Next.js with mcp-handler, shared Zod schemas, and reusable server actions.

Reference for asciinema v3 NDJSON format. TRIGGERS - cast format, asciicast spec, event codes, cast header, cast structure, parse cast file. Use when understanding or parsing .cast files.

Convert .cast to .txt for analysis. Supports batch mode. TRIGGERS - convert cast, cast to txt, strip ANSI, batch convert, bulk convert, iTerm2 logs, timestamp index. Use when preparing recordings for Claude Code.

Execute Preflight phase for /itp:go workflow - create ADR (MADR 4.0), design spec from global plan, verify checkpoint. Use when creating ADRs, design specs, or when /itp:go invokes Preflight phase. Triggers - ADR creation, design spec, MADR format, preflight verification.

Create ASCII diagrams for any GitHub Flavored Markdown file using graph-easy. Use for READMEs, design docs, specifications, or any markdown needing architecture diagrams. Zero external dependencies for rendering - pure text output embeds directly in markdown.

Log experiment metrics, parameters, and artifacts using MLflow Python API. Query and analyze runs with DataFrame operations. Use when user mentions "log backtest", "MLflow metrics", "experiment tracking", "log parameters", "search runs", "MLflow query", or needs to record strategy performance.

Use when writing markdown intended for PDF output, creating PDFs from markdown, or printing PDFs. Invoke EARLY when authoring markdown for PDF to prevent mistakes (manual heading numbers, manual ASCII diagrams, inline annotations). Also use for PDF generation with Pandoc/XeLaTeX, section numbering, table of contents, bibliography, landscape/portrait orientation, printing (one-sided, duplex, simplex, lpr), fixing diagrams breaking across pages, code block page breaks, or double numbering issues. Triggers on - markdown for PDF, write document for printing, create printable doc, pandoc, xelatex, print PDF, PDF generation.

Creates modern LaTeX tables with tabularray package for fixed-width columns, proper alignment, and clean syntax. Use when creating tables or working with column layouts.

Installs and configures complete LaTeX development environment on macOS with MacTeX, Skim viewer, and SyncTeX support. Use when setting up new machine, installing LaTeX, or configuring PDF viewer.

Universal link validation using lychee for Claude Code sessions. Runs at session end to detect broken links and path policy violations.

Get current Claude Code session UUID and registry info. TRIGGERS - current session, session uuid, session id, what session, which session.

Orchestrates the full Ralph autonomous agent pipeline from requirements gathering to execution. Use when building new features, platforms, or complex tasks that need structured development through spec-interview, PRD generation, and autonomous implementation.

Snap.as API Documentation

Write.as API Documentation

Bundle code context for AI. ALWAYS use --limit 49k unless user explicitly requests otherwise. Use for creating shareable code bundles and preparing context for LLMs.

Create new Agent Skills for Claude Code. Use when user wants to create a skill, add a new capability, document a CLI workflow, or asks how skills work.

Convert PDF books to EPUB format for e-readers. Use when user asks to convert PDF to EPUB, create an e-book from PDF, make PDF readable on Kindle/phone/tablet, or extract book content from PDF. Handles: chapter detection, image extraction with optimization, footnotes/endnotes with hyperlinks, reading order for multi-column layouts. Validates conversion quality automatically.

Investigate environment variables that can be set when building Python wheels for a given project. Analyzes setup.py, CMake files, and other build configuration files to discover customizable build environment variables.

Reference FilamentPHP v4 documentation for patterns, methods, and implementation examples

Reference documentation for docker-local architecture, commands, and configuration

Scaffold Filament plugins with Plugin class, ServiceProvider, Resources, and Pest tests

Génère des trésors BFRPG par type (A-U). Pièces, gemmes, bijoux et objets magiques. Utilise les tables officielles avec probabilités. Indispensable après un combat victorieux.

Lance des dés pour jeux de rôle (Basic Fantasy RPG). Supporte d4, d6, d8, d10, d12, d20, d100. Notation standard comme 2d6+3, 4d6kh3 (keep highest). Avantage et désavantage. Utilisez pour tout jet de dé en session de JdR.

Génère des noms de personnages fantasy selon la race et le sexe. Supporte nains, elfes, halfelins, humains et PNJ (tavernier, marchand, garde, noble, mage, méchant). Utilisez pour nommer joueurs et PNJ.

Create flexible annotation workflows for AI applications. Contains common tools to explore raw ai agent logs/transcripts, extract out relevant evaluation data, and llm-as-a-judge creation.

Python project scaffolding and development with modern tooling. Use when creating new Python projects, setting up virtual environments, configuring dependencies, or working with Flask web applications. Triggers on mentions of Python setup, uv, Flask, pytest, or project initialization.

Comprehensive skill for interacting with Grafana's HTTP API to manage dashboards, data sources, folders, alerting, annotations, users, teams, and organizations. Use when Claude needs to (1) Create, read, update, or delete Grafana dashboards, (2) Manage data sources and connections, (3) Configure alerting rules, contact points, and notification policies, (4) Work with folders and permissions, (5) Manage users, teams, and service accounts, (6) Create or query annotations, (7) Execute queries against data sources, or any other Grafana automation task via API.

渲染网页 URL，去噪提取正文并输出为 Markdown（默认）或其他格式/原始 HTML，以减少 Token。

查询、检索与阅读 Confluence 文档/页面。