AI Skills Hub - Browse 180,000+ Agent Skills

Analyze Factory knowledge base to identify missing, shallow, or stale content

Skill definition file generation skill

Verify understanding and alignment before major implementations

Generate slide decks, audio podcasts, infographics, and video overviews from NotebookLM notebooks. Customizable by audience, format, language (80+), orientation, and visual themes. Use when asked to generate slides, create podcast, make infographic, video overview, or automate NotebookLM content creation.

Aggregate flat building elements into hierarchical construction documents with 4-level cost breakdown structure.

A comprehensive skill for creating/deleting project folders and downloading files from URLs into them.

当用户完成 writing-plans 计划、从用户故事或问题继续流程、或明确提到"创建任务"/"task issue"时使用

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

Capture session learnings and save to skills, guidelines, or reference docs

Bulletproof LinkedIn inbox monitoring with progressive autonomy. Monitors messages hourly, drafts replies in your voice, and alerts you to new conversations. Supports 4 autonomy levels from monitor-only to full autonomous.

Validate Context Engineering Template (project-specific)

Implement Series-style batch indicators with mathematical precision. Use for new StaticSeries implementations or optimization. Series results are the canonical reference—all other styles must match exactly. Focus on cross-cutting requirements and performance optimization decisions.

Manages mementos for session persistence - save and restore context across /clear and /compact

Bilingual EN/FR content validation using next-intl. Use when adding translated content, testing language switching, or validating message key coverage before deployment.

Write Python in n8n Code nodes with _input/_json syntax and standard library.

Architectural patterns for n8n workflows - webhook, API, database, AI agent, scheduled.

Validates specification completeness and quality by checking for mandatory sections, [NEEDS CLARIFICATION] markers, testable criteria, and clear scope boundaries. Use this skill when you need to check if spec is complete, validate specifications, review spec.md, or check specification quality. Ensures specifications are ready for architecture and implementation phases.

Validate environment setup before starting development. Use to catch config issues early.

Insert urgent work as a decimal phase between existing phases, adding mid-milestone work, or creating intermediate phases. Triggers include "insert phase", "add urgent phase", "create decimal phase", "insert between phases", and "urgent work".

Extract and process content from PDFs and DOCX files. Handles large files, OCR for scanned documents, page splitting, and markdown conversion. Use when: (1) Processing PDF references in notes, (2) Extracting text from large documents for analysis, (3) Converting DOCX to markdown, (4) Handling scanned/image PDFs with OCR, (5) Integrating with Obsidian or note-taking workflows, (6) Splitting large documents into manageable chunks. Invoke with: /process-document, /extract-pdf, /extract-docx, or say "use document-processor skill to..."

This skill prefers using GitHub chat tools because they can be permanently allowed in VS Code and avoid terminal pager/editor issues. If chat tools are unavailable (or repo context is unknown), fall back to the repo wrapper script `scripts/pr-github.sh`.

Safely rebase the current feature branch on top of the latest origin/main. Use when preparing a branch for PR, UAT, or release.

Export and analyze VS Code Copilot chat logs for retrospective metrics. Extracts model usage, tool invocations, approval patterns, and timing data.

Defines coding standards, test patterns, and language conventions for this project. Use this when writing code, comments, documentation, or git commit messages.

Integrate Red Hat Ansible Automation Platform (AAP) with HashiCorp Vault Enterprise for dynamic SSH credential management. Use when: (1) Configuring Vault SSH secrets engine with AppRole auth for AAP, (2) Creating AAP credentials backed by Vault signed SSH certificates, (3) Provisioning infrastructure with Terraform/Ansible for AAP-Vault integration, (4) Setting up multi-tenant credential management, (5) Configuring golden images to trust Vault SSH CA, (6) Implementing credential rotation strategies. Based on HashiCorp validated pattern.

批量生成和维护前端组件库文档的自动化工具。专为 Monorepo 组件库设计（如 atom-ui-mobile），通过对比组件文件和文档的修改时间，自动生成任务清单并批量生成符合规范的完整组件文档。支持以下场景：(1) 定期批量更新组件文档，(2) 单个组件文档维护，(3) 新组件文档初始化。自动识别主要组件文件，跳过 index.ts、store、hooks 等辅助文件，文档路径为组件目录下的 index.zh-CN.md。

Systematic debugging framework with root cause investigation, tracing, defense-in-depth validation, and verification. Use when: 'bug', 'test failure', 'unexpected behavior', 'error', 'not working', 'broken', before proposing fixes, when encountering any technical issue

Discover, create, and validate headless adapters for agent integration. Includes scaffolding tools and schema-driven compliance testing.

Use when changes to claude-voice code need to be deployed from the project repo to the local installation at ~/.claude-voice

Observe and troubleshoot WhatsApp in Kapso: debug message delivery, inspect webhook deliveries/retries, triage API errors, and run health checks. Use when investigating production issues, message failures, or webhook delivery problems.

Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as 'Deploy my app', 'Deploy this to production', 'Create a preview deployment', 'Deploy and give me the link', or 'Push this live'. No authentication required - returns preview URL and claimable deployment link.

Posts content and articles to X (Twitter). Supports regular posts with images/videos and X Articles (long-form Markdown). Uses real Chrome with CDP to bypass anti-automation. Use when user asks to "post to X", "tweet", "publish to Twitter", or "share on X".

AI image generation with OpenAI and Google APIs. Supports text-to-image, reference images, aspect ratios, and parallel generation (recommended 4 concurrent subagents). Use when user asks to generate, create, or draw images.

Convert tasks.md into GitHub issues with proper dependencies. Use when user says "/spec-taskstoissues", "create GitHub issues", "convert tasks to issues" after /spec-tasks when using GitHub for project management.

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

Use when: 'write in my style', 'imitate my writing', 'replicate my voice', 'match my tone', 'style transfer', 'few-shot style', 'write like me', 'capture my voice', or getting LLMs to replicate writing style from examples.

Restrict what OpenClaw can access on your machine using OS-level sandboxing. Use when: protecting credentials (SSH keys, API tokens) from the gateway process, limiting network to approved domains, preventing unauthorized file writes, hardening OpenClaw deployment, setting up SRT sandbox, troubleshooting sandbox issues. Works with: healthcheck skill for full security posture.

Extended memory for you and your agents. Query AI conversations from Claude.ai, ChatGPT, and other sources.

Send notifications via WhatsApp, email, or Discord when tasks complete or fail. Use this skill to alert the user about orchestrator results. Triggers: "notify", "send message", "alert user", "tell me when done", "send notification", "message me"

Guide for creating effective skills that extend Claude's capabilities with specialized knowledge, workflows, and tool integrations.

Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.

Presentation creation, editing, and analysis for PowerPoint files (.pptx) with support for layouts, templates, and visual design.

Implement hook-based history compaction in fast-agent (rolling window, context threshold truncation, tool-result clearing, summary prompt compaction). Use when adding or extending compaction hooks and wiring them into agent cards.

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.

将内容和文章发布到 X (Twitter)。支持带图片/视频的常规推文和 X 文章（长篇 Markdown）。通过真实的 Chrome CDP 绕过自动化检测。当用户提到 "post to X", "tweet", "publish to Twitter", 或 "share on X" 时使用。

Generate images using Google Gemini API. Use when user asks to generate, create, or make images, pictures, photos, or visual content. Also for editing images, image-to-image generation, or any AI image creation requests.

Generate optimized Apple App Store metadata recommendations with ASO best practices. Use this skill when analyzing app listings, optimizing metadata (title, subtitle, description, keywords), performing competitive analysis, or validating App Store listing requirements. Triggers on queries about App Store optimization, metadata review, or screenshot strategy.

Extract printed or handwritten text from PDF documents using Groq's Llama 4 Scout vision model.

Extract printed or handwritten text from images using Groq's Llama 4 Scout vision model.

Thrivve Partners Monte Carlo simulation to forecast story/task completion based on historical throughput. Use when the user asks "how many stories/tasks will be completed by [date]" with historical daily throughput data. Requires at least 10 days of throughput history and a future target date. Provides probabilistic forecasts at specified confidence levels (default 85%).

Thrivve Partners Monte Carlo simulation to forecast completion date based on remaining work and historical throughput. Use when the user asks "when will I complete [N] stories/tasks" with historical daily throughput data. Requires at least 10 days of throughput history, a count of remaining items, and optional confidence level (default 85%).

Native Claude SDK integration pattern using TypeScript hooks. This skill should be used when implementing hooks, working with Claude SDK, debugging hook lifecycle issues, or integrating with Claude Code/Cursor IDE settings.json.

Transcribe Vaam videos using Google Gemini AI. Takes a Vaam share URL, downloads the video, and returns a full text transcription. Supports any language without translation.

Without PTY mode, command output will not be visible even though commands execute successfully.

Convert saved articles to engaging AI-generated podcasts. Integrates with Notion database, fetches articles, generates two-host conversation scripts, and produces 15+ minute podcasts using AI TTS. Triggers: read later podcast, article to podcast, notion podcast, saved articles audio, convert article podcast, ai podcast generator, url to podcast

Sets up professional Python library projects with modern tooling (pyproject.toml, uv, ruff, pytest, pre-commit, GitHub Actions). Use when creating new Python libraries, modernizing existing projects to pyproject.toml, configuring linting/testing/CI, or setting up Makefiles and pre-commit hooks.

Use MCP tools and workflows from the cursor_workflow system for task management, git operations, and automated workflows. Use when working with AutoTask tasks, git operations, or when the user mentions task management, commits, or automated workflows.

Planejar e manter documentação técnica do projeto (README, quickstart, ADRs, docs internas, exemplos de tool calls e troubleshooting) alinhada ao código; usar quando o pedido exigir clareza documental e não usar para implementar lógica de runtime ou infraestrutura.

根据当前项目 package.json 版本与 Git 提交记录生成中文版本日志。用于用户提出“生成版本日志”“生成 changelog”“发布新版本并生成更新记录”等请求时，自动读取当前版本号、定位上一版本、汇总版本区间 commit，并更新 docs/changelogs_cn.json（新增版本、生成中文 summary、按类型归类变更）。

将 docs/changelogs_cn.json 的当前版本日志生成适合英文母语者阅读的英文版本，更新 docs/changelogs_en.json，并在当前项目创建 release 提交；随后同步中英文 changelog 到同级仓库 ../chatlab.fun 并创建文档提交。用于用户提出“同步版本日志”“生成并同步 changelog”“发布前同步中英文日志”等请求。仅创建 commit，不执行 push。

Read and manage Kubera.com portfolio data (net worth, assets, debts, allocation, holdings). Use when a user asks about their finances, net worth, portfolio, investments, holdings, asset allocation, or wants to update asset values in Kubera. Works with any AI agent or CLI that can run Python scripts.

Swap tokens and read pool state on Uniswap V4 (Base, Ethereum). Use when the agent needs to swap ERC20 tokens or ETH via Uniswap V4, get pool info (price, tick, liquidity, fees), find available pools for a token pair, set up Permit2 approvals for the Universal Router, or execute exact-input swaps. Supports Base and Ethereum mainnet. Requires `cast` (Foundry CLI) and Python 3. Write operations need a private key.

Claude Code 슬래시 명령어(커맨드) 생성 및 수정을 위한 통합 관리 스킬. 사용자가 커스텀 슬래시 명령어를 생성, 수정, 업데이트할 때 사용합니다. 예시 트리거 - "명령어 만들어줘", "커맨드 생성", "명령어 수정해줘", "커맨드 업데이트", "/command 생성", "command 만들기", "create command", "update command", "modify command", "슬래시 명령어 추가/수정". 반드시 사용자로부터 명령어 이름, 용도, 범위(프로젝트/개인)를 수집해야 합니다.

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.

워크플로우 초기화 스킬. prompt.txt 읽기, 시나리오 분기, 제목 생성, init-workflow.sh 통합 스크립트 실행을 수행합니다.

Expert guidance for creating, writing, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

Edit, process, and render videos using FFmpeg and Remotion. Handles 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, merge, or join video files - User asks about transitions, fades, crossfades, or effects between clips - User needs captions, subtitles, or TikTok-style word highlighting - User wants a teaser, trailer, or highlight reel from longer video - User mentions FFmpeg, ffprobe, Remotion, or related errors - User asks about video transcription or whisper speech-to-text - User asks about video duration, resolution, fps, or trimming - User has .mp4, .mov, .captions.json files or video folders - User asks about thumbnails, overlays, title cards, or graphics for video

This skill should be used when working on the lawyer-app project (劉尹惠律師事務所), including Payload CMS content management, Next.js development, Coolify deployment, E2E testing, or content migration. Use when user mentions "lawyer app", "律師網站", "Payload CMS articles", "lawyer deployment", or "lawyer testing".

This skill should be used when the user asks to develop features for the "台股看盤" stock app, work with TWSE/Yahoo Finance APIs, manage portfolio or watchlist functionality, build ETF analysis features, or debug stock-related components. Activate when user mentions stock.jurislm.com, terry90918/stock repo, or Taiwan stock market app development.

CMX Starter Kitのカスタムコンポーネント作成・管理スキル。 MDXコンテンツ内で使えるカスタムReactコンポーネントの定義（JSON）、実装（TSX）、エクスポート、同期の全ワークフローを提供。 トリガー: 「コンポーネントを作成」「カスタムコンポーネントを追加」「MDXコンポーネントを作りたい」 「FeatureCardのようなコンポーネントが欲しい」「CMXにコンポーネントを同期」など。

Run the charity evaluation pipeline - extraction, 4-stage V2 workflow, Supabase patterns, versioning. Use when working on collectors, scrapers, pipeline code, database queries, or debugging data flow.

Agent Skills標準に準拠したスキルを作成し、distディレクトリに出力する。 ユーザーが「スキルを作りたい」「スキルを作成して」と言ったとき、 または /create-skill コマンドで呼び出されたときに使用する。 スキル以外のファイル作成には使用しない。

Deploy and test Linux CTF challenges across cloud providers (AWS, Azure, GCP). Use when testing CTF setup, validating challenges work correctly, running the full test suite, or verifying services survive VM reboots.

S3-compatible object storage integration for marketing assets. Works with Cloudflare R2, AWS S3, MinIO, Backblaze B2, DigitalOcean Spaces.

Build 3D web apps with Three.js (WebGL/WebGPU). 556 searchable examples, 60 API classes, 20 use cases. Actions: create 3D scene, load model, add animation, implement physics, build VR/XR. Topics: GLTF loader, PBR materials, particle effects, shadows, post-processing, compute shaders, TSL. Integrations: WebGPU, physics engines, spatial audio.

Activate for marketing analytics, KPI tracking, reporting dashboards, attribution analysis, and performance optimization. Use when analyzing campaign data, creating reports, or measuring marketing ROI.

Economic sovereignty for AI agents. Create wallets, acquire any asset on any chain. Uses Bungee for all mainnet cross-chain routing. CCTP direct for testnet only. Supports ERC20 (Permit2) and native tokens. Treasury management, payments, portfolio tracking — all self-directed.

Securely run commands that require secrets from the pass password store. Use this when a command needs API keys, tokens, passwords, or other credentials. Secrets are injected as environment variables and are NEVER visible in command output or logs.

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.

Mermaid diagram conventions — semantic colors, layout patterns, validation.

스킬 생성, skill creation, 에이전트 스킬, skill builder, 스킬 최적화, TDD 테스트, 합리화 방지. TDD 기반 스킬 생성 + OpenClaw 스킬 저장소 관리. MCP 통합, 한국 현지화.

Search personal markdown knowledge bases, notes, meeting transcripts, and documentation using QMD - a local hybrid search engine. Combines BM25 keyword search, vector semantic search, and LLM re-ranking. Use when users ask to search notes, find documents, look up information in their knowledge base, retrieve meeting notes, or search documentation. Triggers on "search markdown files", "search my notes", "find in docs", "look up", "what did I write about", "meeting notes about".

Develops and maintains the Options Day Trader Agent (ODTA) - an autonomous AI trading system for Indian NSE F&O markets built with Google ADK, DuckDB, and Angel One API. Use when implementing agent features, debugging trading logic, adding tools, modifying agent hierarchy, or working with MCP broker integration. Expert in ADK agent patterns, risk callbacks, session state management, and paper trading simulation.

This skill should be used when working with the LiveKit bytes design system. It provides comprehensive reference for the three-tier component hierarchy, design tokens, component catalog, CVA patterns, and Radix UI composition patterns.

自动处理 Google Scholar Alerts 邮件,基于 MEMORY.md 过滤论文,生成 Markdown 日报。使用场景:用户说'生成scholar日报'、'处理scholar邮件'、'今天的scholar日报',或使用/scholar-daily命令。

Run Ralph orchestrator with Claude Code backend for autonomous task completion. Use when executing iterative AI agent workflows, automating multi-step coding tasks, or running Ralph in OpenClaw's non-interactive environment. Required for any Ralph orchestration tasks.

Create and manage Claude Code plugins with proper structure, manifests, and marketplace integration. Use when creating plugins for a marketplace, adding plugin components (commands, agents, hooks), bumping plugin versions, or working with plugin.json/marketplace.json manifests.

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.

You are running inside a ddev-claude container with a network firewall. Outbound traffic is blocked by default, and only whitelisted domains are allowed.

Scrape LiveNation AU and Ticketmaster AU for concert announcements, tour dates, venues, and ticket prices. Track competitor activity with daily CSV exports and change detection. Use when Kiara needs to monitor what events competitors are announcing, track ticket prices, or compare tour listings between LiveNation (announcements) and Ticketmaster (sales).

Read tool returns plain text only — fonts, colors, alignment, borders, styles are lost.

| Route | Trigger | Route File | |-------|---------|------------| | **HTML** (default) | All PDF creation requests | `routes/html.md` | | **LaTeX** | User explicitly requests LaTeX, .tex, or Tectonic | `routes/latex.md` | | **Process** | Work with existing PDFs (extract, merge, fill forms, etc.) | `routes/process.md` |

Guide for creating custom skills in SaaS Factory. Use when you need to create a new skill to extend Claude's capabilities with specialized knowledge, workflows, or tools.

Debug AI traces, find exceptions, analyze sessions, and manage prompts/datasets via Langfuse. Use when debugging AI, finding exceptions, analyzing traces/sessions, or managing prompts and datasets.

Text-to-speech synthesis using Microsoft Edge's free TTS service. Use when users request converting text to audio, generating speech from text, creating audio files, or mention TTS, text-to-speech, voice synthesis, or want to convert txt files to mp3/wav. Supports Chinese and other languages with multiple voices, adjustable speed and volume.

エイトハンドレッド（800）社のブランドデザインに沿ったPowerPointプレゼンテーションを作成するスキル。一流コンサルティングファームのようにデザイン・レイアウトを工夫し、ストーリーや論理構造が直感的にわかるスライドを作成する。ダークグリーン(#1B3928)をメインカラーとし、Meiryo UIフォント、クリーンでミニマルなレイアウトを特徴とする。「800風のスライドを作成」「エイトハンドレッドのデザインでプレゼンを作って」「800社のテンプレートでPPTX作成」「スライドを作成」「提案書を作成」などのリクエスト時に使用。

Configure, explore, and optimize Nx monorepo workspaces. Use when setting up Nx, exploring workspace structure, configuring project boundaries, running tasks, analyzing affected projects, optimizing build caching, or implementing CI/CD with affected commands. Keywords - nx, monorepo, workspace, projects, targets, affected, build, lint, test.

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL.

특정 테이블의 DDL 변경 이력을 버전별로 조회합니다