AI Skills Hub - Browse 180,000+ Agent Skills

Provides current project state, architecture overview, and structured metadata

GitHub Actions workflow creation, debugging, and optimization for CI/CD pipelines. Use when setting up automated builds, deployment pipelines, debugging workflow failures, or optimizing build performance.

Comprehensive testing workflow for Next.js App Router with Vitest, React Testing Library, and Playwright E2E tests. Use when writing tests, debugging failures, or improving coverage.

Use when you have a detailed implementation plan and need to execute it task by task with verification, testing, and atomic commits.

Use for ANY technical issue — test failures, bugs, unexpected behavior, performance problems, build failures, integration issues. Especially when under time pressure, when 'just one quick fix' seems obvious, or when previous fixes didn't work.

Use when performing any git operations — branching, committing, merging, rebasing, resolving conflicts. Ensures clean history, atomic commits, and proper branch management.

Use during any implementation work — new features, bug fixes, refactors, behavior changes. Enforces the RED-GREEN-REFACTOR cycle. No production code without a failing test first.

Use when designing, reviewing, or auditing APIs — REST, GraphQL, RPC, WebSocket. Covers endpoint design, request/response contracts, versioning, error handling, pagination, and documentation.

Use when changing existing code — restructuring, renaming, extracting, inlining, or migrating. Ensures behavior is preserved through methodical, test-backed transformations.

Use when about to claim work is complete, fixed, passing, or done. Requires running verification commands and confirming output before making any success claims. Evidence before assertions, always.

Use during production incidents — outages, security breaches, data corruption, performance degradation. Provides structured triage, mitigation, resolution, and post-mortem processes.

This skill generates comprehensive diagram and MicroSim reports for the geometry course by analyzing chapter markdown files and creating table and detail reports. Use this skill when working with an intelligent textbook (specifically geometry-course) that needs updated visualization of all diagrams and MicroSims across chapters, including their status, difficulty, Bloom's Taxonomy levels, and UI complexity.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use n8n-mcp MCP tools for node search, validation, templates, and workflow management.

Write n8n expressions with {{}} syntax, $json/$node variables, and webhook data access.

Configure n8n nodes with operation-aware property dependencies and required fields.

Interpret n8n validation errors, warnings, and profiles to fix workflow issues.

Map incoming and outgoing dependencies for modules using LSP.

Generate standardized checkpoint reports for multi-phase implementation projects. Use this skill when pausing implementation at strategic milestones (phase completion, user story completion, critical features) to create comprehensive progress reports with task breakdowns, metrics, knowledge base entries, and resume instructions.

Download an arXiv paper by title or ID. Searches Semantic Scholar and converts to markdown.

Initialize a new project with deep context gathering and project.md. Triggers include "new project", "start project", "initialize project", "create project", "begin project", "setup project".

Add a milestone to an existing project, starting a new milestone cycle, creating the first milestone after project init, or defining what's next after completing work. Triggers include "add milestone", "new milestone", "start milestone", "create milestone", "first milestone", "next milestone", and "milestone cycle".

Show what's new in Kata since the installed version, displaying changelog entries, checking for Kata updates, or reviewing recent changes. Triggers include "what's new", "whats new", "show changes", "changelog", "recent changes", and "what changed".

Add planned work discovered during execution to the end of the current milestone in the roadmap. This skill appends sequential phases to the current milestone's phase list, automatically calculating the next phase number. Triggers include "add phase", "append phase", "new phase", and "create phase". This skill updates ROADMAP.md and STATE.md accordingly.

Create an Azure DevOps pull request using az devops tooling; include the repo’s linear-history merge preference and ask the Maintainer if merge options differ.

Regenerate test snapshot files after intentional markdown output changes. Use after modifying templates or rendering logic.

Generate the comprehensive demo markdown artifacts from the current codebase. Use before UAT to ensure test artifacts reflect the latest code.

Comprehensive OpenTUI skill for building terminal user interfaces. Covers the core imperative API, React reconciler, and Solid reconciler. Use for any TUI development task including components, layout, keyboard handling, animations, and testing.

Stream long-form content to markdown files with resume capability. Writes content incrementally with section markers, enabling recovery if context limits are hit. Use when generating long documents (over 1000 lines), B-SPEC or specification writing, multi-section reports, any task where context compaction may occur mid-generation, or when user explicitly requests streaming output. Commands: init, write, status, resume, finalize, repair.

Conduct Fault Tree Analysis (FTA) to systematically identify and analyze causes of system failures using Boolean logic gates. Top-down deductive method for safety and reliability engineering. Use when analyzing system failures, evaluating safety-critical designs, calculating failure probabilities, identifying minimal cut sets, assessing redundancy effectiveness, or when user mentions "fault tree", "FTA", "system failure analysis", "minimal cut sets", "safety analysis", "failure probability", "AND/OR gates", or needs to trace failure pathways from top event to basic events. Supports qualitative structure analysis and quantitative probability calculations.

Conduct Pareto Analysis (80/20 Rule) to identify the vital few causes driving the majority of problems. Guides data collection, category definition, chart creation, cumulative percentage calculation, and prioritization. Generates professional Pareto charts (SVG) and HTML reports with quality scoring. Use when prioritizing defects, complaints, failures, or improvement opportunities; when user mentions "Pareto", "80/20 rule", "vital few", "trivial many", "prioritization", or needs to identify which factors contribute most to a problem.

Use when creating Docusaurus plugins (remark, rehype, theme, content, lifecycle) to extend markdown, modify HTML, or add custom functionality

Analyze and improve Terraform provider test coverage using terraform-plugin-testing v1.13.3+ patterns. Use when (1) analyzing test coverage gaps, (2) adding missing tests (drift detection, import, idempotency), (3) converting legacy patterns to modern state checks, (4) tracking optional field coverage, (5) verifying test quality, or (6) validating example accuracy. Supports automated coverage analysis, guided pattern improvements, and example testing.

创建具有自定义系统提示和工具配置的专业化 Claude Code 子代理。当用户要求创建新的子代理、自定义代理、专业助手，或为 Claude Code 配置特定任务的 AI 工作流时使用。

创建和配置 Claude Code 钩子以自定义代理行为。当用户需要以下操作时使用：(1) 创建新钩子，(2) 配置自动格式化、日志记录或通知，(3) 添加文件保护或自定义权限，(4) 设置工具执行前后的操作，(5) 询问钩子事件如 PreToolUse、PostToolUse、Notification 等。

创建生产级 Node.js CLI 工具的完整解决方案,包含 15+ 个优化点和 104KB 专业模板。当用户需要构建命令行工具时使用:(1)创建新的 CLI 项目,(2)选择合适的框架和依赖,(3)实现完整 CLI 功能(配置管理、进度条、版本检查、输出格式化等),(4)配置测试和打包,(5)应用最佳实践(POSIX 兼容、TTY/CI 检测、错误处理、Shell 补全)

This skill should be used when working with xterm.js terminal implementations, React-based terminal applications, WebSocket terminal communication, or refactoring terminal-related code. It provides battle-tested patterns, common pitfalls, and debugging strategies learned from building production terminal applications.

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

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Brainstorm ideas and design workflows with a beads expert. Use when: 'help me plan', 'how should I structure this', 'what beads features', 'brainstorm', 'before I create tasks', 'design my workflow'. For ideation BEFORE creating issues.

Controls Chrome browser: takes screenshots, clicks buttons, fills forms, downloads images, inspects pages, captures network requests, checks console errors, debugs API issues. Use when: 'screenshot', 'click', 'fill form', 'download image', 'check browser', 'look at screen', 'capture page', 'check for errors', 'debug network', 'API failing', 'console errors'. Provides MCP tool discovery for 70 tabz_* browser automation tools.

CLI tool for capturing agent trajectories. Execute prompts against headless CLI agents via schema-driven adapters, capture full trajectories (tools, thoughts, plans), and output structured JSONL for downstream scoring.

Go backend development standards using DDD architecture, ent ORM, fx DI, and kiwi-lib utilities. Covers project structure, domain design, API/application/infrastructure layers, database workflow, and coding requirements.

Use this skill when querying Fold for project context, storing memories, searching codebases, or retrieving AI-ready context. Triggers on keywords like memory search, context retrieval, project knowledge, codebase search, semantic search, or any MCP tool interaction with Fold.

Guide for DynamoDB single-table design using OneTable ORM. Use when designing database schemas, writing DAL functions, creating queries, or handling schema evolution in DynamoDB.

TanStack React Query expert for data fetching and mutations in React applications. Use when working with useQuery, useMutation, cache invalidation, optimistic updates, query keys, or integrating server actions with React Query via @saas4dev/core hooks (useServerActionQuery, useServerActionMutation, useServerActionInfiniteQuery). Triggers on requests involving API data fetching, server state management, cache strategies, or converting fetch/useEffect patterns to React Query.

Guide for Zod schema validation patterns in TypeScript. Use when creating validation schemas, defining types, validating forms, API inputs, or handling validation errors.

VC 투자 분석 및 Exit 프로젝션 자동화 스킬. 투자 검토 엑셀 파일을 분석하여 IS요약, Cap Table, 투자조건을 파싱하고 PER 기반 Exit 프로젝션을 생성합니다. 사용 시점: (1) 투자 검토 엑셀 파일 분석 요청, (2) Exit 프로젝션/밸류에이션 요청, (3) PER 멀티플 기반 수익률 분석, (4) 투자 수익률/IRR 계산, (5) 스타트업 재무제표 분석

Hoist RegExp creation outside render or memoize with useMemo(). Apply when using regular expressions in React components or frequently called functions.

MIR 智能投資導師。提供專業的個股診斷、技術指標分析、自動化圖表產生並上傳 R2，以及 LINE 通知推播。當用戶要求進行股票分析、技術診斷、或查看觀察清單時使用。

Breakdown の examples/ を実行し、ユーザー視点での動作確認を行う。

Generate custom quality checklists that validate REQUIREMENTS quality (not implementation). Use when user says "/spec-checklist", "create checklist for [domain]" to validate specification completeness before implementation.

Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.

Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and sequential image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".

Iterate on a PR until CI passes. Use when you need to fix CI failures, address review feedback, or continuously push fixes until all checks are green. Automates the feedback-fix-push-wait cycle.

Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.

Build and distribute Expo development clients locally or via TestFlight

Expert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.

Automatic decryption and decoding tool using AI. Use when user says "解密", "decrypt", "decode", "crack", "破解密码", or provides encrypted/encoded text that needs to be deciphered. Supports 50+ encryption types including Base64, Caesar, Vigenere, XOR, Morse code, binary, hashes, and more.

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

Build WhatsApp automations with Kapso workflows: configure WhatsApp triggers, edit workflow graphs, manage executions, deploy functions, and use databases/integrations for state. Use when automating WhatsApp conversations and event handling.

Create or update a feature specification from a natural language description. Use when user says "/spec-specify", "create a spec", "write a specification", "I want to build...", or describes a new feature to implement. This is the FIRST step in the Spec-Driven Development workflow.

Suite of tools for creating elaborate, multi-component HTML artifacts using modern frontend technologies (React, Tailwind CSS, shadcn/ui).

Design tools that agents can effectively discover, understand, and use.

Toolkit for interacting with and testing local web applications using Playwright. Verify frontend functionality, debug UI behavior, capture screenshots, and view browser logs.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.

Build, test, and automate iOS applications using accessibility-driven navigation and structured data.

Execute Hugging Face Hub operations using the `hf` CLI for downloading models/datasets, uploading files, managing repositories, cache, and cloud compute.

Add structured evaluation results to model cards with support for README extraction, Artificial Analysis API, and custom evaluations using vLLM/lighteval.

Create and manage datasets on Hugging Face Hub with SQL-based querying, transformation, and streaming row updates.

Comprehensive YouTube channel analysis using YouTube Data API v3. Analyze your own channel's performance metrics, content strategy, upload patterns, engagement rates, video performance, and growth trends. Use when users want to (1) Analyze their YouTube channel performance, (2) Get insights on video engagement and metrics, (3) Understand upload patterns and optimal posting times, (4) Identify top-performing content types, (5) Generate channel health reports, (6) Track subscriber and view growth patterns. Requires user's YouTube Data API v3 key.

This skill should be used when the user asks to "animate elements", "add animations", "create transitions", "use anime.js", "implement motion", "add scroll animations", "create timeline animations", "stagger animations", "animate SVG", "add draggable elements", or needs guidance on anime.js v4 patterns, easing, performance, or React/Next.js animation integration.

LSP-enable a Python or TypeScript repository for fast-agent development. Use when setting up a new project with LSP code navigation tools, creating agent cards with LSP function tools, or configuring ty (Python) or typescript-language-server (TypeScript) integration.

Nuxt SEO meta-module with robots, sitemap, og-image, schema-org. Use when configuring SEO, generating sitemaps, creating OG images, or adding structured data.

Guide for adding a new reward function to AReaL. Use when user wants to create a reward function.

Manages distributed workloads and file sharing across Tailscale SSH-connected machines. Automates remote command execution, intelligent load balancing, file synchronization workflows, host health monitoring, and multi-machine orchestration using sshsync. Activates when discussing remote machines, Tailscale SSH, workload distribution, file sharing, or multi-host operations.

Collect a single Schwab MCP data snapshot (accounts, quotes, indicators, option chains) with a five-minute cache so trading agents can reuse consistent inputs. Use whenever an options persona needs fresh risk, market, or chain data before recommending trades.

Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.

Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.

Creates Next.js 16 API routes with auth, validation, and tenant scoping. Use when creating API endpoints.

Update copier template version. Use when checking for template updates, running copier update, or applying template changes to the project structure.

Guide for adding a new email parser service to parse payment/purchase notification emails. Use when adding support for a new service's email format to extract transaction data (title, price, date, description).

WhatsApp integration using Baileys library with QR code pairing, send/receive messages, media support (photos, videos, voice), typing indicators, and read receipts. Use when user mentions WhatsApp or wants to send WhatsApp messages.

Send and receive Telegram messages with bot polling, typing action, photo support, and voice message transcription. Use when user mentions Telegram, wants to send messages, or handle voice messages.

Generate Brazilian PIX payment QR codes with BR Code format, CRC16 validation, and QR code image generation. Use when user mentions PIX, Brazilian payments, or QR code generation.

MANDATORY security gate for installing ClawHub skills. Whenever the user asks to install, add, or download a skill from ClawHub, ALWAYS use this skill's safe-install-plus.sh instead of running clawhub install directly. Also use when the user asks to scan, audit, or check existing skills for security issues. Detects prompt injections, malware payloads, macOS supply chain attacks, data exfiltration, and Gatekeeper bypass attempts.

Use when asked to check, read, triage, or act on user feedback

Deploy the project to a target environment.

Complete guide for creating valid Warp JSON definitions for the Warp Protocol

Create and manage database migrations with Entity Framework Core, including schema changes, data seeding, and rollback strategies

Set up scheduled background jobs using Quartz.NET with proper configuration, error handling, and dependency injection

ADA system health check - verifies dependencies for capture and analysis

Build, trace, and analyze application performance. Use when profiling apps, finding slow functions, or debugging performance issues.

Use when you've developed a broadly useful skill and want to contribute it upstream via pull request - guides process of branching, committing, pushing, and creating PR to contribute skills back to upstream repository

Search previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search

This skill provides access to a project's recorded technical decisions and architectural patterns. Use this skill to understand established patterns, validate proposals against decisions, and cite decisions when reviewing code or specifications. Works with any project that maintains a decisions registry.

Generate complete Dimm City-themed Wretched & Alone solo journaling games in .game.md format. Use when user requests creating a Dimm City game, generating a campaign file, or building a themed solo RPG. Creates 52-card games with proper mechanical balance, rich creaturepunk atmosphere, auto-validation, and supports iteration. Maintains exact card distribution (1 Primary Success, 4 Failure Counters, 3 Narratives, 16 Challenges, 28 Events) per Wretched & Alone SRD.

Execute pattern search, template matching, and todo generation for faster feature development. This skill should be used when planning features, estimating effort, researching similar implementations, or creating implementation roadmaps with the /plan command.

Context persistence layer for agent memory, conversation history, and semantic search. Use when storing agent memories, implementing vector search with Supabase pgvector, enforcing privacy isolation (User > Team > Project > Public), or caching with Redis. Enables long-term context retention across sessions.

Detect OPERA phases and coordinate multi-agent workflows. This skill should be used for workflow coordination, phase transitions, determining which agents to use, or understanding the current development stage.