AI Skills Hub - Browse 180,000+ Agent Skills

通过 figma-developer-mcp（stdio）连接 Figma MCP，支持列出工具、调用工具、排查 MCP 交互问题；当需要在命令行与 Figma 文件/节点交互或调试 MCP 行为时使用。

使用 Python3 作为 MCP Client 直接拉起并连接 chrome-devtools-mcp 控制 Chrome 浏览器，用于网页自动化、调试、性能分析、截图/快照、表单填充等任务；当用户需要在浏览器中执行步骤或获取页面信息时使用。

将飞书云文档导出为 Markdown，基于 lark-cli get-blocks 解析块结构，下载图片/画板缩略图到 assets/ 并生成相对路径引用。

生成和校验飞书画板可用的 PlantUML（安全子集）。当用户需要根据自然语言生成 PlantUML，或提供 PlantUML 并要求在飞书画板可用/降级修复/去除不兼容语法时使用。

Archive one or more meetings into the brain repo by importing Zoom transcript folders (~/Documents/Zoom/*) and/or downloaded Teams .vtt files (~/Downloads/*.vtt), then generating a transcript markdown file, an executive summary, and creating meeting notes. Use when the user says "archive meeting", "archive my last meeting", "process these transcripts", or similar.

Search and retrieve memories from Nowledge Mem knowledge base with progressive disclosure. This skill should be used when the user asks to search memories, recall past knowledge, find saved information, look up conversation history, expand thread details, or mentions keywords like "记忆", "知识库", "之前说过", "我保存的", "历史对话".

Downloads Defold bob.jar and runs smoke test builds. Use when asked to build, test build, or verify Defold project compiles.

Building decay and upkeep systems for survival games. Use when implementing timer-based decay, Tool Cupboard patterns (Rust-style protection radius), resource upkeep costs, or server performance management through automatic cleanup. Balances gameplay and server health.

Platform-specific building systems for mobile, VR, and accessibility. Use when implementing touch controls for building games, VR spatial input, colorblind-friendly feedback, or cross-platform building mechanics. Covers input adaptation and inclusive design patterns.

Structural validation and damage systems for Three.js building games. Use when implementing building stability (Fortnite/Rust/Valheim style), damage propagation, cascading collapse, or realistic physics simulation. Supports arcade, heuristic, and realistic physics modes.

Three.js 3D building system with spatial indexing, structural physics, and multiplayer networking. Use when creating survival games, sandbox builders, or any game with player-constructed structures. Covers performance optimization (spatial hash grids, octrees, chunk loading), structural validation (arcade/heuristic/realistic physics modes), and multiplayer sync (delta compression, client prediction, conflict resolution).

Builder user experience systems for Three.js building games. Use when implementing prefab/blueprint save/load, undo/redo command patterns, ghost preview placement, multi-select, or copy/paste building mechanics. Covers the UX layer that makes building feel responsive and intuitive.

Networking systems for multiplayer building games. Use when implementing networked construction, delta synchronization, client prediction, or conflict resolution. Server-authoritative model with optimistic client prediction for responsive gameplay.

Terrain interaction systems for Three.js building games. Use when implementing slope handling, foundation anchoring (Valheim pattern), terrain modification, auto-leveling, or pillar/support generation. Integrates with structural-physics for ground-based stability.

Spatial indexing and world streaming for Three.js building games with thousands of pieces. Use when optimizing building games, implementing spatial queries, chunk loading, or profiling performance. Includes spatial hash grids, octrees, chunk managers, and benchmarking tools.

Run gdUnit4 tests for Godot projects. Use after implementing features, fixing bugs, or modifying GDScript files. USE PROACTIVELY to verify code changes.

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

Generate AI images using Midjourney through the Legnext API. Use this skill when users request Midjourney-style image generation, visual content creation, or ask to create/generate images with natural language descriptions. Handles prompt engineering, API calls, task polling, and result retrieval.

Use when generating or updating Table of Contents in markdown files. Supports multiple files, glob patterns, configurable header levels, and various insertion modes. Triggered by "generate toc", "update toc", "table of contents", "add toc to markdown".

List Telegram groups and channels. Use when user asks about available groups, channels, or wants to discover what's accessible.

Design CLI tools with consistent UX patterns.

Update issue title and description via Fractary CLI

List comments on issues with optional filtering via Fractary CLI

Create new issues in work tracking systems via Fractary CLI

Search and list issues via Fractary CLI

Orchestrates complete single-document workflows with automatic validation and indexing in a write→validate→index pipeline

Cloudflare R2 storage handler for fractary-file plugin

Local filesystem storage handler for fractary-file plugin

Google Cloud Storage handler for fractary-file plugin

Matches targets against configured patterns for work-ID-free planning

Core utilities for FABER workflow management - config loading, state management, status cards

Provision, configure, and manage OpenClaw AI agent instances running inside Firecracker microVMs. Use when creating new VM instances, controlling VM lifecycle (start/stop/restart/destroy), debugging guest services, checking instance health, or modifying VM provisioning scripts.

Kamailio SIP server configuration and troubleshooting. Use when Claude needs to: (1) Edit or create Kamailio configuration files (.cfg) (2) Debug SIP routing logic (request_route, failure_route, reply_route) (3) Work with Kamailio pseudo-variables ($ru, $fU, $avp, $xavp, $dlg_var) (4) Configure modules (tm, dialog, acc, sqlops, jansson, http_client, rr, sl, mqueue, rtimer) (5) Understand SIP message flow and transaction handling (6) Validate configuration syntax Triggers: "kamailio", "SIP routing", "kamailio.cfg", SIP-related pseudo-variables

Symfony 7.4 YAML component reference for parsing and dumping YAML files. Use when working with YAML parsing, YAML dumping, Yaml::parse, Yaml::dump, Parser, Dumper, YAML flags, PARSE_CUSTOM_TAGS, DUMP_OBJECT, TaggedValue, or any YAML-related Symfony code. Triggers on: Yaml, YAML parsing, YAML dumping, Yaml::parse, Yaml::dump, Parser, Dumper, YAML flags, PARSE_CUSTOM_TAGS, DUMP_OBJECT.

Symfony 7.4 Process component reference for executing commands in sub-processes. Use when working with Process, external commands, shell execution, async processes, timeout, signals, mustRun, fromShellCommandline, getOutput, getErrorOutput, isSuccessful, subprocess management, or any command execution-related Symfony code.

Symfony 7.4 Filesystem component reference for file and directory operations. Use when working with filesystem utilities, file operations, directory creation, copy, remove, chmod, chown, symlink, mirror, tempnam, dumpFile, appendToFile, readFile, or Path manipulation (canonicalize, join, makeAbsolute, makeRelative). Triggers on: Filesystem, file operations, directory creation, copy, remove, chmod, symlink, Path, dumpFile, appendToFile, readFile, mirror, makePathRelative.

Symfony 7.4 Intl component reference. Triggers on: Intl, internationalization, locales, countries, currencies, languages, timezones, ICU, number formatting, Locale, Scripts, i18n, localization

Use to install Space-Agents in a project. Creates .space-agents/ directory and SQLite database. Run once per project.

Converts Postman collection JSON files to Apache JMeter JMX test plans. Use when converting API collections exported from Postman to JMeter load test scripts. Supports GET, POST, PUT, DELETE methods with JSON body, form data, and response assertions.

Use when creating Mermaid diagrams - covers flowcharts, sequence diagrams, and AST visualization

Use when working with docusaurus-plugin-glossary to configure, manage glossary terms, troubleshoot issues, and explain features

通用产品功能评估方法论与工具集。用于：(1) 设计新功能的评估标准体系，(2) 创建评分Prompt实现LLM-as-a-Judge，(3) 分析人工与模型评分一致性，(4) 迭代优化评估标准和Prompt。适用于AI功能评测、对话质量评估、软硬件产品体验评估等场景。当用户需要设计评估体系、创建评分标准、分析评测数据或优化评测流程时使用此skill。

Use when building telephony, messaging, or video applications; implementing voice AI agents; working with SWML call flows; debugging webhook callbacks or call state issues; setting up real-time WebSocket communication; encountering authentication 401/403 errors; or troubleshooting SWAIG function errors - provides REST API patterns, SDK examples, and production-tested workflows for modern SignalWire communication systems

Guidance for building polished CLIs and TUIs with the Artisanal Dart package. Use when users ask for terminal UIs, live dashboards, log viewers, interactive input, or CLI tools with subcommands using Artisanal.

TypeScript patterns for full-stack Next.js applications. This skill should be used when implementing type-safe API contracts, utility types, Zod schema integration, tRPC type inference, or type derivation patterns. Covers RouterOutputs/RouterInputs, branded types, discriminated unions, and server-first typing strategies.

Guide for implementing Claude Code hooks - automated scripts that execute at specific workflow points. Use when building hooks, understanding hook events, or troubleshooting hook configuration.

Build Claude Code framework components (agents, slash commands, skills, plugins) following standardized templates. Use when creating new agents, commands, skills, or plugins for the multiagent framework.

Clerk authentication integration patterns for Next.js and Convex. Invoke for: user authentication, session management, JWT templates, webhook handling, middleware configuration, protected routes, Convex auth integration.

Sentry error tracking and production observability. Invoke when: - New Next.js project without error tracking → Suggest setup - Deploying to Vercel → "Add observability before deploying" - Discussing error handling, try/catch → "Track these in production" - Production bug, users reporting errors → Triage with scripts - Setting up monitoring, configuring alerts, reviewing PII handling Scripts: detect_sentry.sh, init_sentry.sh, list_issues.sh, triage_score.sh Keywords: Sentry, production errors, error tracking, triage, alerts, observability, Session Replay, PII redaction, source maps, monitoring

Environment variable management across Vercel, Convex, and other platforms. Invoke for: trailing whitespace issues, cross-platform parity, Invalid character errors, webhook secrets, API key management, production deployment, dev vs prod configuration.

Hotwire（Turbo + Stimulus）を使用してRuby on Railsの管理画面を実装し、PlaywrightによるE2Eテストを含めた完全な実装を行うスキル

Grasshopper 參數化建模工作流程工具。當需要通過 MCP 協議與 Grasshopper 交互、創建和管理組件、建立連接、設置參數、執行完整建模工作流程時使用。適用於：(1) 從 MMD 文件創建 Grasshopper 定義, (2) 執行 placement_info.json 工作流程, (3) 批量管理組件和連接, (4) 參數化建模的自動化流程, (5) 解析 component_info.mmd 和 part_info.mmd 文件

Inspect GitHub PR checks with gh, detect merge conflicts/update-branch requirements, list reviewer feedback, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan + code changes; for external checks (e.g., Buildkite), only report the details URL and mark them out of scope.

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effective context management.

Get a pre-meeting briefing for any account. Usage: /brief {account name}. Returns checklist progress, hours remaining, last interaction, missed comms, and open to-dos.

Queries local Granola meeting cache for meeting history, context, and attendee information. Use when preparing for meetings, researching past interactions with a person or company, finding past discussions on a topic, tracking engagement, or when user mentions Granola, meeting notes, meeting history, or attendees.

Query articles using category filters and BM25 keyword search

Manage Raindrop.io bookmarks, collections, tags, and highlights via API. Use when user mentions raindrop, bookmarks, saving links, organizing URLs, bookmark collections, or web highlights.

Comprehensive web research via Parallel Search API. Use when user requests parallel search for deep multi-source research, technical analysis, learning new topics, current events, or comparative studies. Returns LLM-ready ranked URLs with extended excerpts (up to 30K chars). Single API call handles multiple query angles with automatic deduplication.

Slack メッセージを編集する。「メッセージ編集」「さっきのを修正」「メッセージ修正」「訂正して」「編集して」「メッセージを直す」「内容を変更」などで起動。User Token があれば自分の投稿を編集可能、なければ Bot 投稿のみ編集可能。

Comprehensive n8n v2.0 reference for building workflow automation. Use this skill when working with n8n workflows, especially for (1) creating workflow JSON files for import, (2) implementing human-in-the-loop approval workflows with Wait nodes, (3) troubleshooting Execute Sub-Workflow node issues, (4) setting up API credentials (LinkedIn, Anthropic, NewsAPI), (5) building orchestrator patterns with sub-workflows, (6) using expressions in nodes, (7) understanding MCP server limitations, or (8) any n8n workflow development task.

Use when generating multiple curriculum-aligned concept files in parallel (5+ concepts) - researches curriculum, creates concept list, spawns parallel generation agents, orchestrates review loop until all pass

Guide for creating effective subagents (custom agents). Use when users want to create a new subagent that can be dispatched via Task tool for autonomous work. Covers frontmatter fields (name, description, tools, model, permissionMode, skills), prompt design, and when to use subagents vs skills.

Validates beads issues after creation. Checks dependencies, PRD mapping, order. Use when: after creating issues in project-init, before TDD loop. Triggers: "validate beads", "check issues", "verify tasks".

Advanced subagent troubleshooting. Use when subagent calls fail, return bad output, or need voting for critical decisions.

Comprehensive Confluence documentation management. Use when asked to "upload to Confluence", "download Confluence pages", "convert Markdown to Wiki Markup", "sync documentation to Confluence", "search Confluence", "create Confluence page", "update Confluence page", "export Confluence", "publish to Confluence", or "Confluence CQL query". Handles Wiki Markup conversion, Mermaid/PlantUML diagrams, image handling, large document uploads without size limits, and Git-to-Confluence sync with mark CLI.

Execute GitHub CLI (gh) commands for repository management, issues, pull requests, workflows, and releases. Use when the user wants to interact with GitHub repositories, create/manage issues or PRs, trigger workflows, or perform any GitHub operations. Covers both solo developer workflows and team collaboration patterns.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Automates visual regression testing for Storybook components using cloud-based snapshot comparison. Use when setting up visual testing, catching UI regressions, or reviewing component changes.

Use when encountering any bug, test failure, or unexpected behavior (including race conditions, deadlocks, concurrency issues) - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) with specialized techniques for deep call stack tracing and concurrency debugging

Comprehensive Vitest testing framework guide with strong emphasis on Jest-to-Vitest migration. Covers automated migration using codemods, configuration setup, API differences, best practices, and troubleshooting. Use when migrating from Jest, setting up Vitest, writing tests, configuring test environments, or resolving migration issues. Primary focus is seamless Jest migration with minimal code changes.

Integrate RubyCritic to analyze Ruby code quality and maintain high standards throughout development. Use when working on Ruby projects to check code smells, complexity, and duplication. Triggers include creating/editing Ruby files, refactoring code, reviewing code quality, or when user requests code analysis or quality checks.

Displays progress dashboard showing phase completion, blocked tasks, and remaining work estimate. Provides at-a-glance view of implementation status. Run anytime to check progress.

Write or repair Codex skills (SKILL.md) so they follow the Agent Skills spec, have strong trigger descriptions, and use references/scripts/assets appropriately. Use when asked to create a new skill, refactor an existing skill, or diagnose why a skill is not being discovered.

Plan and implement macOS recents/frequents for files, folders, and apps using Spotlight metadata, LaunchServices, and app-side telemetry. Use when selecting data sources, shaping Spotlight queries, defining ranking strategies, or documenting limits like kMDItemLastUsedDate.

Render and preview JSON files in browser with syntax highlighting, collapsible tree view, and search

Render and preview CSV files in browser with interactive sorting, filtering, and column statistics

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Hedera Token Service (HTS) smart contract development. Use when creating, managing, or interacting with Hedera-native tokens via Solidity contracts. Triggers include HTS tokens, Hedera token creation, HTS precompile, token minting/burning on Hedera, KYC/freeze/pause token controls, custom fee schedules, NFT collections on Hedera, or any token operations using the 0x167 precompile.

Parse WhatsApp chat exports into structured JSON data with participants, timestamps, and messages

List available personas from all storage locations

Write BDD requirements in Gherkin format. Guides the user through the process.

Create GitHub releases with properly formatted release notes. Use when: (1) Publishing a new version/release, (2) Generating release notes from commits, (3) User mentions release, 发版, 发布版本, or asks to create a GitHub release.

Guides development with supastarter for Next.js only (not Vue/Nuxt): tech stack, setup, configuration, database (Prisma), API (Hono/oRPC), auth (Better Auth), organizations, payments (Stripe), AI, customization, storage, mailing, i18n, SEO, deployment, background tasks, analytics, monitoring, E2E. Use when building or modifying supastarter Next.js apps, adding features, or when the user mentions supastarter Next.js, Prisma, oRPC, Better Auth, or related Next.js stack topics.

USE WHEN: 用戶詢問 SHOPLINE Payments 金流串接、導轉式付款流程、建立結帳交易（sessionUrl）、 returnUrl 回跳處理、Webhook 簽章驗證、交易查詢、退款/請款/取消操作， 或整合 LINE Pay、信用卡、ATM、街口支付（JKO）等台灣在地付款方式。 DO NOT USE WHEN: 詢問其他金流服務（如綠界 ECPay、藍新 NewebPay、TapPay）、 非台灣地區金流、或 SHOPLINE 電商平台非金流相關功能。

Trade leveraged long/short positions on Solana via Asgard Finance. Use when the user wants to open, close, or manage margin positions on SOL, ETH, or other tokens using lending protocols like Kamino, Marginfi, Solend, or Drift.

Translate LangChain/LangGraph patterns into Agently code (model control + TriggerFlow).

Process PGMQ embedding jobs in supabase/functions/embedding_ft; fetch row content, call AWS SageMaker embedding endpoint, and write embeddings back to Postgres. Use when debugging or extending the FT embedding worker, adjusting auth/env, or changing queue semantics.

Better Auth TypeScript/JavaScript authentication library. Use when implementing auth in Next.js, React, Express, or any TypeScript project. Covers email/password, OAuth, JWT, sessions, 2FA, magic links, social login with Next.js 16 proxy.ts patterns.

Better Auth JWT verification for Python/FastAPI backends. Use when integrating Python APIs with a Better Auth TypeScript server via JWT tokens. Covers JWKS verification, FastAPI dependencies, SQLModel/SQLAlchemy integration, and protected routes.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Create server-side database triggers with proper execution timing, recursion prevention, and validation patterns. Use when implementing Before/After/Async business rules, preventing recursive rule execution, or enforcing data validation on database operations.

Generate MIDI files with GM instruments and music theory. Use when creating music, composing melodies, or generating MIDI files.

ProcessWire custom page classes — extending the Page class with template-specific logic. Use when creating, editing, or working with custom page classes in ProcessWire, or when the user mentions page classes, typed pages, or template-specific PHP classes.

Use this skill when creating, improving, or optimizing prompts for Claude. Applies Anthropic's best practices for prompt engineering including clarity, structure, consistency, hallucination reduction, and security. Useful when users request help with writing prompts, improving existing prompts, reducing errors, increasing consistency, or implementing specific techniques like chain-of-thought, multishot prompting, or XML structuring.

Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields

한글(HWP/HWPX) 문서를 다양한 포맷(Text, HTML, ODT, PDF)으로 변환하고, Markdown/HTML을 HWPX로 생성하는 작업을 도와줍니다. LLM/RAG 파이프라인을 위한 문서 처리, 청킹, LangChain 연동을 지원합니다.

Use safe-rm command to safely 'remove' files by renaming them to .obsolete instead of permanent deletion. Reversible, collision-safe, hook-compliant.

Uses shared scripts from [openapi-toolkit](../../../../../.claude/shared/openapi-toolkit/README.md).

Uses shared scripts from [openapi-toolkit](../../../../../.claude/shared/openapi-toolkit/README.md).