AI Skills Hub - Browse 180,000+ Agent Skills

Edits, processes, and renders videos using FFmpeg and Remotion. Handles video stitching, transitions, captions, teasers, and transcription. USE THIS SKILL WHEN: - User mentions video, clip, footage, mp4, mov, avi, mkv, or any video format - User wants to combine, stitch, concatenate, merge, or join video files - User asks about transitions, fades, crossfades, or effects between clips - User needs captions, subtitles, TikTok-style captions, or word highlighting - User wants a teaser, trailer, highlight reel, or short preview from longer video - User mentions FFmpeg, ffprobe, or any ffmpeg command or error - User mentions Remotion, OffthreadVideo, TransitionSeries, or any Remotion error - User asks about video transcription, whisper, speech-to-text for video - User encounters "inputRange must be strictly monotonically increasing" error - User encounters "delayRender was called but not continued" error - User sees any video encoding, codec, or rendering error - User asks about video duration, resolution, fps, frame rate, or video analysis - User asks how to trim, cut, or extract portions of video - User has .mp4, .mov, .captions.json files or video folders - User is confused about video processing implementation - Any error occurs in a video-editor project directory - User asks about thumbnails, graphics, overlays, or visual assets for video - User needs to generate images or graphics for video content - User mentions title cards, lower thirds, end screens, or chapter graphics

Converts documents to markdown (PDFs, Word docs, PowerPoint, Confluence exports) with Windows/WSL path handling. Activates when converting .doc/.docx/PDF/PPTX files to markdown, processing Confluence exports, handling Windows/WSL path conversions, extracting images from PDFs, or working with markitdown utility.

Convert documents and files to Markdown using markitdown with Windows/WSL path handling. Supports PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), HTML, CSV, JSON, XML, images (with EXIF/OCR), audio (with transcription), ZIP archives, YouTube URLs, or EPubs. Use when converting files to markdown, processing Confluence exports, handling Windows/WSL path conversions, extracting images from PDFs, or working with markitdown utility.

Extract Claude Code work history and update daily notes. Use when user asks to update daily file with today's work, sync work history, record activities, or generate daily summary from Claude Code history.

Extracts Mermaid diagrams from markdown files and generates high-quality PNG images using bundled scripts. Activates when working with Mermaid diagrams, converting diagrams to PNG, extracting diagrams from markdown, or processing markdown files with embedded Mermaid code.

This skill should be used when managing documentation files in an Obsidian vault, including creating session artifacts, moving planning documents from project directories to the vault, updating document lifecycle states (active → processed → archived), searching for documents by tags or content, and automating archival of old documents. Integrates with task-startup/task-wrapup workflows for any coding project.

Search technical documentation using executable scripts to detect query type, fetch from llms.txt sources (context7.com), and analyze results. Use when user needs: (1) Topic-specific documentation (features/components/concepts), (2) Library/framework documentation, (3) GitHub repository analysis, (4) Documentation discovery with automated agent distribution strategy | Dùng khi tìm tài liệu, hướng dẫn, docs, documentation, api docs, tham khảo.

High-performance web crawler for discovering and mapping website structure. Use when users ask to crawl a website, map site structure, discover pages, find all URLs on a site, analyze link relationships, or generate site reports. Supports sitemap discovery, checkpoint/resume, rate limiting, and HTML report generation.

透過 E-utilities/Datasets API 查詢 NCBI Gene。按符號/ID 搜尋，擷取基因資訊（RefSeqs、GO、位置、表型），批次查詢，用於基因註解和功能分析。

使用可擴展演算法（GRNBoost2、GENIE3）從基因表達資料推斷基因調控網路（GRN）。適用於分析轉錄體學資料（bulk RNA-seq、單細胞 RNA-seq）以識別轉錄因子-標靶基因關係和調控交互作用。支援大規模資料集的分散式運算。

Get daily A/B test updates in Slack for multiple brands. Use when you want morning summaries of all your Intelligems tests, need to monitor tests across multiple stores or clients, or want automated Slack notifications with key metrics like revenue per visitor, profit per visitor, and conversion rates. Perfect for agencies managing multiple brands.

Post content to WeChat Official Account (微信公众号). Supports both article posting (文章) and image-text posting (图文).

Auto-invoke gencast to generate podcasts from documents when user mentions podcast, audio, or dialogue generation

文章の事実確認と参照検証を行う統合スキル。主張の洗い出し、外部ソースでの検証、参考文献の整備までを一貫して実行。文書レビュー、記事校正、レポート確認、学術論文チェック時に使用。

Mueve un ejercicio validado desde En-Desarrollo a Nuevos-Ejercicios después de completar el Ciclo de Validación.

Fetch claude-code-plugins repo and convert plugins to OpenCode format. Usage: /sync-from-claude-plugins [plugin-names...] (default: all available plugins)

Create and manipulate Teenage Engineering EP-133 K.O. II sampler project files (.ppak/.pak). Use when: (1) Creating beats/patterns for EP-133, (2) Generating .ppak project files, (3) Assigning samples to pads, (4) Programming drum patterns and sequences, (5) Working with EP-133 backup files. Triggers: EP-133, KO2, K.O. II, .ppak, .pak, sampler project.

Create and manage cron jobs (recurring events, repeating workflows, scheduled tasks). Use when user asks to schedule something to run automatically, create recurring tasks, set up periodic jobs, or manage cron entries.

Extract and analyze YouTube video content (transcripts + metadata). Use when the user explicitly requests to analyze, summarize, extract wisdom from, or get context from a YouTube video. Supports wisdom extraction, summary, Q&A prep, key quotes, and custom analysis. Does NOT auto-trigger on YouTube URLs - only when analysis is explicitly requested.

Smart dependency updates across ecosystems (npm/bun/pnpm, uv/poetry, cargo). Use when upgrading dependencies, fixing vulnerabilities, or performing proactive maintenance. Supports intelligent batching, risk assessment, and outcome tracking for continuous improvement.

CLI for Raindrop.io bookmark management - search, create, update, delete, bulk operations. Use when working with Raindrop.io bookmarks or when the user mentions bookmarks, link saving, or Raindrop.

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.

Access macOS productivity apps (Calendar, Contacts, Mail, Messages, Reminders, Voice Memos). Use when user asks about calendar events, contacts, emails, iMessages, reminders, or voice transcription.

Invoke Claude Code CLI from Python orchestrators and shell scripts. Use when asked to "spawn claude as subprocess", "automate claude cli", "run claude headless", "configure --allowedTools", "set up claude hooks", or "parallel claude invocation". Covers permissions, directory access (--add-dir), hooks, sandbox mode, and async patterns.

実装完了後のテスト、lint、ベストプラクティスレビューを自動実行するスキル。 以下の状況で使用: (1) ユーザーが「実装完了」「完了」「できた」「終わった」「実装した」「書き終わった」などと発言した時 (2) ユーザーが明示的に「/post-impl-validator」を実行した時 (3) ファイル編集後に「コミットして」「PRを作成」「プッシュして」「push」などと依頼された時 (4) ユーザーが「テストを実行して」「テストして」「lintを確認して」「lintかけて」と個別に依頼した時 (5) ユーザーが「レビューして」「チェックして」「検証して」と品質確認を求めた時 (6) ユーザーが「これで問題ない?」「大丈夫?」と確認を求めた時

Web開発プロジェクト・タスクの開始時に必要なドキュメント群を作成するスキル。 以下の状況で使用: (1) ユーザーが「新しいプロジェクトを始めたい」「タスクを開始したい」「プロジェクトをセットアップして」と依頼した時 (2) ユーザーが明示的に「/task-starter」を実行した時 (3) 新機能開発、リファクタリング、バグ修正などのタスクで計画・ドキュメント整備が必要な時 (4) 「ドキュメント構造を作って」「プロジェクトの骨組みを用意して」と依頼された時 (5) 「タスク管理用のフォルダを作成して」「開発の準備をして」と依頼された時 (6) 「TODOリストを整理したい」「作業計画を立てたい」と相談された時 (7) 「仕様書のテンプレートが欲しい」「タスク分割を手伝って」と依頼された時

Framework for building AI agents that work effectively across multiple context windows on complex, long-running tasks. Use when building agents for multi-hour/multi-day projects, implementing persistent coding workflows, creating systems that need state management across sessions, or when an agent needs to make incremental progress on large codebases. Provides initializer and coding agent patterns, progress tracking, feature management, and session handoff strategies.

Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use for web browsing, form submission, web scraping, or UI testing. NOT for static content (use curl/wget).

Comprehensive guide for creating, configuring, and using Claude Code hooks. MUST Use when creating hooks, implementing PreToolUse/PostToolUse/Stop hooks, or configuring event-driven automation. Do not use for general automation, workflow management, or task execution.

Automates Tauri WebView debugging using official plugins (tauri-plugin-log + screenshots) with process verification, automated screenshots, console logs, and state analysis. Use when debugging Tauri apps, investigating WebView issues, analyzing runtime errors, or troubleshooting UI problems.

Use when analyzing website traffic, investigating SEO issues, diagnosing high bounce rates, evaluating content performance, or optimizing site conversions - proactive SEO consultant with Plausible Analytics access that investigates patterns, fetches actual page content, and provides specific actionable recommendations based on real data analysis

Jira Cloud integration for issue management and search. This skill should be used when working with Jira tickets, searching issues with JQL, creating or updating issues, adding comments, or transitioning issue status. Covers REST API v3 and Jira Query Language.

This skill generates planning documents (기획서) in PowerPoint format from analyzed screen data and project artifacts. It should be invoked by the /auto-draft skill during Phase 4 to create the final PPT output. Not intended for direct user invocation.

Guide for creating new Transmissions applications with decision support for core vs remote development

Generate project documentation including CONTENTS.md navigation files and AGENTS.md instructions. Use when creating documentation structure, project indexes, or AI agent configuration files.

Fine-tune LLMs using Red Hat training-hub library with SFT, LoRA, and OSFT algorithms. Use when preparing JSONL datasets, running training jobs, configuring hardware, scaling to clusters, evaluating models, or deploying with vLLM.

This skill should be used for Jira backlog refinement via text conversation. It pulls non-ready tickets, facilitates requirements discussion, and marks tickets ready when complete.

QA 테스트 요청 스킬. Use when (1) 태스크카드 테스트 요청, (2) QA 담당자 할당, (3) 테스트 범위 지정, (4) Slack 알림 전송.

SEMO 라우팅 구조 시각화. Use when (1) /SEMO:routing-map 커맨드, (2) "라우팅 구조", "SEMO 구조", "설치된 패키지" 키워드, (3) Agent/Skill 전체 목록 확인 요청.

.claude 디렉토리 구조 검증 및 자동 수정. Use when: (1) SEMO 업데이트 후 무결성 체크, (2) 심링크 깨짐 의심 시, (3) version-updater에서 자동 호출, (4) 새 세션 시작 시.

Use PROACTIVELY when you need to create, update, configure, or validate Claude hooks for various events and integrations

Convert MCP servers to Claude Code skills with progressive disclosure. Use when creating a skill from an MCP server, updating an existing MCP skill, or converting MCP documentation to skill format. Accepts MCP documentation URLs, npm package names, or direct connection info.

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

计算股票技术指标（MA、MACD、RSI、BOLL等）。适用于技术分析、量化回测、趋势判断等场景。支持单个指标计算或批量计算所有指标，返回包含指标值的DataFrame。

获取中国A股和ETF市场数据。使用场景：(1) 查询股票历史数据，(2) 获取ETF净值走势，(3) 指定时间范围的数据提取。支持通过股票代码和天数参数获取OHLCV（开盘价、最高价、最低价、收盘价、成交量）数据。

Use for DevOps and infrastructure work. Covers Docker multi-stage builds, Kubernetes manifests and Helm charts, GitOps with ArgoCD/Flux, GitHub Actions CI/CD pipelines, and container security. Activate when working with Dockerfile, k8s manifests, helm charts, CI workflows, or deployment configuration.

Use for electrical power systems engineering. Covers thermal rating models (CIGRE TB 601, IEEE 738), conductor temperature limits, catenary physics (sag, tension, clearance), electrical properties (resistance, reactance), and standards compliance (CIGRE, IEEE, IEC). Activate when working with transmission line calculations, thermal modeling, or conductor physics validation.

Use when working with Linear issues (ART-XX, issue identifiers), tracking work items, creating session notes, managing project context, or when user mentions Linear, projects, sprints, cycles, or issue tracking. Triggers on: "work on ART-", "linear", "session note", "track this", issue identifiers, project names. Commands: /linear-load, /linear-track, /linear-save, /linear-focus, /linear-verify.

Help a user use Mozilla SOPS (getsops/sops) safely and effectively: encrypt/decrypt/edit secrets files (YAML/JSON/ENV/INI/binary), set up and troubleshoot `.sops.yaml`, choose key backends (age/PGP/AWS KMS/GCP KMS/Azure Key Vault/Vault), rotate keys, use `sops set/unset/extract/exec-env`, and fix common workflow issues. Use when a request mentions SOPS, `sops`, `.sops.yaml`, secret encryption, age recipients/keys, PGP fingerprints, KMS/Key Vault/Vault, or Git diff with SOPS.

Extract text from PDF files for manipulation, search, and reference. Use when needing to read PDF content, extract text from documents, search within PDFs, or convert PDF to text for further processing. Supports multiple extraction methods (pdfplumber, PyMuPDF, pdfminer) with automatic fallback.

Reviews Pull Requests that add or modify compliance frameworks. Trigger: When reviewing PRs with compliance framework changes, CIS/NIST/PCI-DSS additions, or compliance JSON files.

Use when asked to create, search, update, or transition Jira tickets. Use when user mentions KANBAN, SCRUM, AGRHELP, or MOD projects. Use when needing ticket status, assignments, or board views.

Auto-invoke gencast to generate podcasts from documents when user mentions podcast, audio, or dialogue generation

Deploy complete hackathon infrastructure from scratch including WorkAdventure, LiveKit, Coturn, and Jitsi. Use when setting up for a new event, recovering from accidental destruction, or first-time deployment. Covers pre-flight checks, Terraform bootstrap, map sync, and service verification.

Diagnose and fix issues with running hackathon infrastructure. Use when services are unhealthy, users report problems, OAuth fails, video doesn't work, or maps don't load. Covers SSH access, Docker logs, TLS certificates, and network connectivity troubleshooting.

Safely tear down hackathon infrastructure. Use when the event is over, doing cleanup, or need to start fresh. Covers Terraform destroy (preferred) and manual AWS cleanup (when state is corrupted). Includes verification steps to ensure complete removal.

Scrape transcripts from all videos on a YouTube channel. Use when the user wants to download, extract, or scrape captions/subtitles/transcripts from YouTube channels, playlists, or multiple videos. Handles both manual and auto-generated captions with resume support for large channels.

SQLite vector DB for work log storage and semantic search. Use for indexing work logs, generating embeddings, semantic search, and DB maintenance.

通过Windows串口（COM口）控制多品牌交换机；支持ZTE/华为/H3C/锐捷/思科设备；自然语言指令转换为CLI命令

智能简历助手,通过五个AI代理提供全流程求职支持:(1)故事挖掘-发现经历亮点;(2)职位推荐-匹配合适岗位;(3)简历优化-针对JD定制内容;(4)模拟面试-实战演练与反馈;(5)能力提升-差距分析与计划。适用于简历创建、优化、面试准备、职业规划等求职相关任务。

Host static files on subdomains with optional authentication. Use when you need to serve HTML, images, CSS, JS, or any static content on a dedicated subdomain. Supports file upload, basic auth, quota management, and automatic SSL via Caddy. Commands include sf sites (create/list/delete), sf upload (files/directories), sf files (list/delete).

Build, deploy, monitor, and troubleshoot production Nexla data pipelines via Python SDK or REST API. Use for flow setup, data transformation pipelines, schema management, access control, credential rotation, batch operations, error recovery, monitoring, CI/CD integration, and operational troubleshooting.

AI-powered web search and research using Exa API. Use when you need: (1) High-quality web search with semantic understanding, (2) Advanced search with specific filters (domain, date, topic), (3) Website crawling and content extraction, (4) Company research and LinkedIn search, (5) Deep research on complex topics. Alternative to Brave Search for better semantic results.

Review backend pull requests for correctness, security, performance, maintainability, and test coverage using GitHub CLI plus local repository inspection. Use when asked to review service-layer/API/database changes, audit backend branch diffs, summarize backend risk, or produce actionable must-fix/should-fix feedback.

CNKI 中国知网操作指南。检索论文、获取文献信息。用户需要检索 CNKI 论文或操作 CNKI 网站时使用此技能。

Guide for creating Claude Code plugins, including directory structure, manifest configuration, component types, and initialization scripts. Use when users want to create, build, or understand Claude Code plugins.

基于百度飞桨 PaddleOCR-VL-1.5 的文档识别技能。当用户需要对 PDF、PNG、JPG、BMP、TIF 等格式的文档进行 OCR 文字识别时使用此技能。支持文字、表格、公式、图表识别，输出 Markdown 格式结果。

Interact with Moltbook - the social network for AI agents. Use when you need to browse feed, create posts, comment, vote, or subscribe to submolts. Handles the auth redirect bug automatically.

創建高品質 MCP（Model Context Protocol）伺服器的指南，使 LLM 能夠透過精心設計的工具與外部服務互動。在使用 Python（FastMCP）或 Node/TypeScript（MCP SDK）建構 MCP 伺服器以整合外部 API 或服務時使用。

项目知识库管理器 - 将保险业务项目文档(数据分析、PPT报告、技术方案)转化为结构化、可迁移的知识资产。支持:(1)自动生成2类标准化模板(项目启动/技术方案);(2)从Markdown/代码仓库智能提取技术决策和可复用模式;(3)统一文档格式标准;(4)生成可跨项目复用的知识库。触发场景:用户要整理项目文档、创建知识库、生成项目模板、提取技术经验、标准化现有文档时使用。

Manage templates.yaml registry entries with schema validation. Use for adding, updating, or removing Railway deployment templates.

Comprehensive Claude Code hook patterns for automation, state management, and external integration. Use when implementing hooks for validation, workflow gates, MCP integration, or state machines.

Protocol-based workflow enforcement with validation dependencies and anti-bypass protection

Context isolation for query-type MCP tools (LSP, search, database) via external CLI. Use when MCP query results consume too many context tokens.

Process any content source (YouTube, websites, EPUBs, markdown) into structured summaries. Use when user provides URLs for transcription, has books/EPUBs to process, or wants batch summarization of any content type.

Create Google Ads assets and account elements. Use for generating RSAs (responsive search ads), sitelinks, callouts, and other extensions from landing page content. Also for creating campaigns, ad groups, keywords, and negative keywords. Triggers include "create RSA", "generate sitelinks", "write headlines", "create campaign", "add negatives".

Fetch Slack messages and threads by URL. Auto-detects threads and returns structured JSON (message text, author, datetime, thread replies if present) ready for LLM processing. Use when needing to extract Slack context for analysis, documentation, or backlog items.

Safely restart the OpenClaw Gateway with context preservation, health monitoring, and failure notification. Use when the agent needs to restart the Gateway (config changes, model switches, plugin reloads, or any reason requiring a restart). Handles pre-restart context saving, guardian process spawning, gateway restart triggering, post-restart verification, and fallback notifications.

Diagnose and fix claude-mem installation issues. Checks PM2 worker status, database integrity, service health, dependencies, and provides automated fixes for common problems.

Configure Static Application Security Testing (SAST) tools for automated vulnerability detection in application code. Use when setting up security scanning, implementing DevSecOps practices, or automa

Agent definition file generation skill

指南：创建高质量的 MCP（模型上下文协议）服务器，使 LLM 能够通过精心设计的工具与外部服务交互。在构建 MCP 服务器以集成外部 API 或服务时使用，无论是 Python（FastMCP）还是 Node/TypeScript（MCP SDK）。

掌握高级提示工程技术，以最大化生产环境中LLM的性能、可靠性和可控性。在优化提示、改进LLM输出或设计生产提示模板时使用。

Posts content to WeChat Official Account (微信公众号) via Chrome CDP automation. Supports article posting (文章) with full markdown formatting and image-text posting (图文) with multiple images. Use when user mentions "发布公众号", "post to wechat", "微信公众号", or "图文/文章".

Lifecycle hook system for context injection (before-prompt), post-edit actions (after-file-edit), and git operations (after-build). Use when implementing hooks, enabling library context loading, injecting RAG patterns, or implementing agent auto-activation. Must be fast (<100ms) and use tsx runtime (not ts-node).

Query and monitor Unraid servers via the GraphQL API. Use when the user asks to 'check Unraid', 'monitor Unraid', 'Unraid API', 'get Unraid status', 'check disk temperatures', 'read Unraid logs', 'list Unraid shares', 'Unraid array status', 'Unraid containers', 'Unraid VMs', or mentions Unraid system monitoring, disk health, parity checks, or server status.

Instruction-accurate emulator development for the Linx ISA (QEMU-like). Use when building decode/execute, handling exceptions/interrupts, implementing memory/MMU/devices, adding GDB-style debugging, or building differential/conformance tests against the Linx spec or RTL.

Configure figma-developer-mcp server for Claude Code. This skill should be used when the user wants to set up Figma MCP integration, configure Figma API access, or troubleshoot Figma MCP connection issues. Triggers include "configure Figma MCP", "set up Figma integration", or "connect Claude to Figma".

Make HTTP API calls with authentication, retry logic, and error handling

Create visual presentations, slide decks, and explanatory diagrams in Excalidraw. Use when user asks to create a presentation, slide deck, visual explainer, pitch deck, comparison diagram, process flow, or any multi-slide visual content. Supports two output modes — generating .excalidraw JSON files OR injecting slides directly into excalidraw.com via Chrome browser automation (clipboard JS injection + paste). Combines presentation design expertise with Excalidraw technical implementation.

This skill should be used when the user asks to "build synonyms", "generate synonyms", "create legal synonyms", "taxonomy generate", "build taxonomy", "expand synonym database", "add synonyms to taxonomy", "populate synonym table", "legal term expansion", "生成同義詞", "建立同義詞", "擴充同義詞資料庫", "法律術語擴展", or mentions specific categories like "civil_debt synonyms", "criminal synonyms", "procedural synonyms", "labor synonyms". Claude Code generates Taiwan legal synonyms directly using its knowledge and inserts them into the legal_synonyms table.

Bidirectional conversion between Word (.docx) and Markdown (.md) with configurable style mapping, validation, and round-trip fidelity. Use when working with document conversion, Word files, Markdown generation, or when the user mentions DOCX, document formatting, style mapping, or needs to convert documents between formats.

Git operations with conventional commits. Use for staging, committing, pushing, PRs, merges. Auto-splits commits by type/scope. Security scans for secrets.

Port ESLint rules to rslint (a Go-based linter). Use when users want to port/migrate/implement an ESLint rule, add a new lint rule, or mention "port rule" or specific ESLint rule names like "no-unused-vars", "no-console", etc. Supports both single-rule and batch-rule porting. This skill guides through the complete workflow from setup to PR submission.

Web search using Kagi Search API. Use when the user needs to search the web, find information, look up documentation, research topics, or get current facts. Provides high-quality search results without ads.

CNKI 中国知网操作指南。检索论文、获取文献信息。用户需要检索 CNKI 论文或操作 CNKI 网站时使用此技能。

企智通项目全栈开发。后端 NestJS + Prisma，前端 React + TanStack Router + Shadcn UI。核心约定：CRUD 用抽屉、头部含搜索/主题/i18n/用户、文本 i18n 化、@ApiTags 英文、分页响应用 data 字段。开发前后端功能时使用此技能。

Render Mermaid diagrams as SVG and PNG using the Beautiful Mermaid library. Use when the user asks to render a Mermaid diagram.

Fitbit fitness data integration. Use when the user wants fitness insights, workout summaries, step counts, heart rate data, sleep analysis, or to ask questions about their Fitbit activity data. Provides AI-powered analysis of fitness metrics.

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.