AI Skills Hub - Browse 180,000+ Agent Skills

Visualizes Product Manager thoughts (Why, What, How, User Journey) into an editable Excalidraw diagram. Use when the user asks to "visualize specs", "create a PM diagram", or "map out product thoughts".

High-quality voice synthesis with 18 personas, 32 languages, sound effects, batch processing, and voice design using ElevenLabs API.

Send push notifications and manage Pocket Alert resources via the pocketalert CLI. Use when the user wants to send push notifications, manage applications, devices, webhooks, or API keys through Pocket Alert. Handles message sending, application management, device management, webhook creation, and API key operations.

写文章并发布到 CSDN。使用浏览器自动化 + 扫码登录。支持通过 Telegram 发送二维码，无需 VNC。

Export Clawdbot skills as standalone, deployable microservices. Use when you want to dockerize a skill, deploy it to Railway or Fly.io, or create an independent API service. Generates Dockerfile, FastAPI wrapper, requirements.txt, deployment configs, and optional LLM client integration.

Access and analyze Hevy fitness tracking data including workouts, routines, and exercise templates via the command line.

SEO keyword research and competitor analysis via Keywords Everywhere API. Use when you need to get search volume, CPC, competition data for keywords, find related keywords (PASF), analyze what keywords a domain/URL ranks for, or retrieve backlink data.

Validate and safeguard OpenClaw config updates (openclaw.json or openclaw config set/apply). Use this skill whenever changing gateway config, models, channels, agents, tools, sessions, or routing. Enforces backup, schema validation, and safe rollback before restarts.

Real-time WhatsApp voice message processing. Transcribe voice notes to text via Whisper, detect intent, execute handlers, and send responses. Use when building conversational voice interfaces for WhatsApp. Supports English and Hindi, customizable intents (weather, status, commands), automatic language detection, and streaming responses via TTS.

Interact with ClickUp project management platform via REST API. Use when working with tasks, spaces, lists, assignees, or any ClickUp workflow automation. Handles pagination, subtasks, and common query patterns. Use for task management, reporting, automation, or any ClickUp-related queries.

x402 Singularity Layer - Enable AI agents to deploy monetized API endpoints, consume paid services via USDC payments, manage credits, and participate in a self-sustaining agent economy. Supports Base and Solana networks.

Browse, search, and analyze Chia NFTs via the MintGarden API.

Hybrid memory strategy combining OpenClaw's built-in vector memory with Graphiti temporal knowledge graph. Use when you need to recall past context, answer temporal questions ("when did X happen?"), or search memory files. Provides decision framework for when to use memory_search vs Graphiti.

Generate hand-drawn style diagrams, flowcharts, and architecture diagrams as PNG images from Excalidraw JSON

Enable and configure Moltbot/Clawdbot memory search for persistent context. Use when setting up memory, fixing "goldfish brain," or helping users configure memorySearch in their config. Covers MEMORY.md, daily logs, and vector search setup.

Send messages, photos, and files via Telegram Bot API. Use when you need to send notifications, alerts, or content to Telegram chats, channels, or groups. Supports text formatting, media, and inline keyboards.

Use when user wants to be reminded about something at a specific time or recurring schedule. Creates cron-based reminders delivered via iMessage, Discord, or other configured channels.

Monitor and analyze Weights & Biases training runs. Use when checking training status, detecting failures, analyzing loss curves, comparing runs, or monitoring experiments. Triggers on "wandb", "training runs", "how's training", "did my run finish", "any failures", "check experiments", "loss curve", "gradient norm", "compare runs".

Track personal expenses with natural language. Log spending, view reports, search transactions. Works with any AI model.

Enable agents and skills to challenge users for fresh two-factor authentication proof before executing sensitive actions. Use this for identity verification in approval workflows - deploy commands, financial operations, data access, admin operations, and change control.

WeChat Reading (微信读书) CLI tool for fetching notes and highlights. Use when: (1) user asks about weread/微信读书 notes or highlights, (2) fetching today's or recent reading notes, (3) exporting book highlights, (4) managing reading bookshelf, (5) any task involving reading notes from WeChat Reading.

Fetch and summarize YouTube video transcripts. Use when asked to summarize, transcribe, or extract content from YouTube videos. Handles transcript fetching via residential IP proxy to bypass YouTube's cloud IP blocks.

Track and nag about Microsoft Outlook email and (optionally) Microsoft Teams messages on a Windows machine, without relying on web versions. Use when the user asks to: (1) monitor inbox/mentions and remind them on Telegram/Teams until dismissed, (2) draft short, personable, low-jargon email replies from an existing Outlook thread, (3) surface action items from the last N days (default 7). Works via Outlook Desktop automation (COM) and optionally Microsoft Graph for Teams if configured.

Query Last.fm listening data, show now playing, sync scrobble history to local DB, and deploy a personal "now playing" web dashboard. Use when user asks about current music, listening stats, scrobble history, or wants to set up a Last.fm dashboard.

Track a shared contact's location via Apple Find My with street-level accuracy. Returns address, city, and context (home/work/out) by reading map landmarks. Supports configurable known locations and vision fallback for unknown places.

A simple command-line interface for controlling Spotify playback from a Raspberry Pi (or any Linux system).

Parse and generate MLSCP (Micro LLM Swarm Communication Protocol) commands. Use when communicating with other agents efficiently, parsing compressed commands, or generating token-efficient instructions. Reduces token usage by 70-80% compared to natural language.

YOLOv8-based camera surveillance with object detection. Works with any IP camera supporting RTSP streams or HTTP snapshots (Hikvision, Dahua, Reolink, Amcrest, Unifi, and more). Detects 80+ object types (person, car, dog, etc.) and sends notifications with snapshots. Use for motion detection, night watch routines, or security monitoring.

Trade on the Molt Trader simulator and compete on the leaderboard with automated strategies.

Systematically borrow ideas from unrelated industries to solve problems. Innovation often comes from adjacent fields. Use when user says "cross-pollination", "how would X solve this", "borrow ideas from", "what can we learn from", "think outside the box", "how would Disney/Apple/Amazon do this", "different industry", "steal ideas".

Uncover the real "job" customers hire your product to do. Goes beyond features to understand functional, emotional, and social motivations. Use when user says "jobs to be done", "jtbd", "why do customers", "what job", "customer motivation", "what problem", "user needs", "why do people buy".

Query and curate knowledge-base using ByteRover CLI. Use `brv query` for knowledge retrieval, `brv curate` for adding context, and `brv push/pull` for syncing.

For headless/automated operation, set these environment variables: - MS365_MCP_CLIENT_ID - Azure AD app client ID - MS365_MCP_CLIENT_SECRET - Azure AD app secret - MS365_MCP_TENANT_ID - Tenant ID (use "consumers" for personal accounts)

Create, manage, and deploy Voice.ai conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.

Text-to-Speech service using Doubao (Volcano Engine) API with 200+ voices, interactive voice selection, and multilingual support

Interact with Twitter/X — read tweets, search, post, like, retweet, and manage your timeline.

Comprehensive Bitcoin blockchain interaction via Maestro APIs. Supports 7 API services with 119 endpoints including blockchain indexing, Esplora compatibility, RPC access, event management, market prices, mempool monitoring, and wallet operations. Handles BTC transactions, UTXOs, addresses, blocks, metaprotocols (BRC20, Runes, Inscriptions/Ordinals), webhooks, and real-time data.

Implements a Clawdbot extension tool that downloads Feishu files by message_id and file_key, streams to disk with sha256, size limits, and path traversal protection. Use when the user asks to build or update the feishu_file_fetch tool, Feishu file download workflow, or Clawdbot extension handling message_id/file_key inputs.

Search Korean news articles using Naver Search API. Use when searching for Korean news, getting latest news updates, finding news about specific topics, or preparing daily news summaries. Supports relevance and date-based sorting.

Manage productivity with FlowMind — goals, tasks (with subtasks), notes, people, and tags via REST API. Use when the user wants to create, list, update, or delete goals, tasks, notes, contacts, or tags; manage focus/priorities; track progress; or organize their productivity workspace through FlowMind.

Probe which emoji reactions are accepted in a specific Telegram chat/message, record an allow/deny list, and optionally remove test reactions afterwards.

Use when the user needs Xcode build/test/run workflows, simulator or device control, UI automation, screenshots/video, logs, or LLDB debugging through XcodeBuildMCP tools. Includes discovery of projects/schemes, session defaults, and common simulator/device workflows.

Make and receive USDC payments over HTTP using the x402 protocol (Coinbase). The Stripe for agents — pay for services, sell your own, check balances. Works on Base network (mainnet + testnet).

Use swiftfindrefs (IndexStoreDB) to list every Swift source file referencing a symbol. Mandatory for “find references”, “fix missing imports”, and cross-module refactors. Do not replace with grep/rg or IDE search.

Process multiple AI inference requests asynchronously using the Doubleword batch API.

AI-powered atomic habit tracker with natural language logging, streak tracking, smart reminders, and coaching. Use for creating habits, logging completions naturally ("I meditated today"), viewing progress, and getting personalized coaching.

Read, send, search, and manage Slack messages via the slk CLI. Use when the user asks to check Slack, read channels, send Slack messages, search Slack, check unreads, manage drafts, view saved items, or interact with Slack workspace. Also use for heartbeat Slack checks. Triggers on "check slack", "any slack messages", "send on slack", "slack unreads", "search slack", "slack threads", "draft on slack".

Verify AI agent identity and reputation via ERC-8004 on-chain registries

Archive your X (Twitter) bookmarks into categorized markdown files with AI-generated summaries.

Manage tasks in Obsidian via TaskNotes plugin API. Use when user wants to create tasks, list tasks, query by status or project, update task status, delete tasks, or check what they need to do.

Accept payments on any website using moneydevkit. Use when building a site that sells something, adding a checkout/paywall, or integrating payments into a Next.js or Replit app. Supports fixed pricing, pay-what-you-want, products, customers, and orders. Bitcoin Lightning under the hood — works globally, no bank account needed.

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.

Bridge tokens across chains using LI.FI's aggregated bridge/DEX routing.

Contribute to and reference Clawpedia, the collaborative knowledge base for AI agents

Integrate Mayar.id payment platform via MCP (Model Context Protocol) for Indonesian payment processing.

Integrate Mayar.id payment platform via MCP (Model Context Protocol) for Indonesian payment processing.

Security audit and inspection skill for Clawdbot skills. Use this when you need to check skills for security vulnerabilities before installation, perform regular security audits on installed skills, verify skill description matches actual behavior, scan for prompt injection attempts, check for hardcoded secrets or credentials, verify no malicious intent in skill code or documentation, review file access patterns for potential configuration or secrets exposure, or audit dependencies for known vulnerabilities. This skill provides automated scanning tools and manual security checklists for comprehensive skill security assessment.

Detect and reject indirect prompt injection attacks when reading external content (social media posts, comments, documents, emails, web pages, user uploads). Use this skill BEFORE processing any untrusted external content to identify manipulation attempts that hijack goals, exfiltrate data, override instructions, or social engineer compliance. Includes 20+ detection patterns, homoglyph detection, and sanitization scripts.

This skill should be used when analyzing HTML/CSS websites for SEO optimization, fixing SEO issues, generating SEO reports, or implementing SEO best practices. Use when the user requests SEO audits, optimization, meta tag improvements, schema markup implementation, sitemap generation, or general search engine optimization tasks.

Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.

Use this skill to find high-quality dividend growth stocks (12%+ annual dividend growth, 1.5%+ yield) that are experiencing temporary pullbacks, identified by RSI oversold conditions (RSI ≤40). This skill combines fundamental dividend analysis with technical timing indicators to identify buying opportunities in strong dividend growers during short-term weakness.

Use the RSSaurus command-line client (Go binary `rssaurus`) to interact with https://rssaurus.com from the terminal: authenticate (`rssaurus auth login/whoami`), list feeds/items, print item URLs for piping, open URLs, and perform triage actions (mark read/unread, bulk mark-read, save/unsave). Use when asked to automate RSSaurus tasks from CLI, debug token/config issues, or demonstrate command usage.

Locate places using flexible query formats - free-form search or structured address components. Returns coordinates, addresses, and optional street-level photos. Use for geocoding addresses or finding specific named places.

Plan multi-waypoint journeys with route optimization, feasibility analysis, and time budget constraints. Use when you need to plan trips with multiple stops or check if an itinerary is achievable.

Work with control theory problems, LTI systems, controller design, and system dynamics using slicot

This skill defines how to run the repository's **single** Copilot CLI subagent (**`compilers-expert`**) safely and reproducibly via `./run-subagent.sh`.

A powerful video downloader powered by [yt-dlp](https://github.com/yt-dlp/yt-dlp).

Develop, debug, and deploy Apify Actors - serverless cloud programs for web scraping, automation, and data processing. Use when creating new Actors, modifying existing ones, or troubleshooting Actor code.

Add W&B Weave observability and LLM tracing to any project. Use when instrumenting LLM calls for token visibility, latency tracking, cost analysis, or debugging. Supports TypeScript/Node.js and Python projects. Weave provides automatic tracing for OpenAI, Anthropic, and 20+ LLM providers with minimal code changes.

agent-browser で DreamCore V2 に自動ログインするスキル。Google OAuth をバイパスして Supabase Magic Link でログインします。

DreamCore にゲームをデプロイするスキル。

Use when adding automated tests for LLM contracts, schema compliance, or regression checks.

Harden OpenClaw (workspace + ~/.openclaw): run openclaw security audit, catch prompt-injection/exfil risks, scan for secrets, and apply safe fixes (chmod/exec-bit cleanup). Includes optional config.patch planning to reduce attack surface.

AI 图像生成和处理工作流。通过提示词生成图像，支持文生图、图生图、批量生成、图床管理、长图合并、PPT 打包。核心特性是逐张确认生成，避免浪费 API 额度。

Extract, transcribe, and process long-format PDF documents. Use when the user needs to read, search, or convert PDF files from the docs/ directory. Handles text-based and scanned PDFs with OCR fallback. Supports table extraction, markdown conversion, and cross-document search. Essential for processing normative documents, SINAPI manuals, SUS guides, and PNCP references.

Generate brand-consistent images using the Ideogram API. Reads brand guidelines from docs/brand/image-constitution.md and dynamically builds optimized prompts. Use when the user asks to generate, create, remix, or make images, graphics, visuals, or illustrations that should match their brand style.

Reusable validation patterns for infrastructure deployments. Use when asked to validate Azure resources, check K8s cluster health, verify Terraform state, detect drift, run compliance checks.

Techniques for achieving reproducible LLM inference outputs. Use when: requiring exact reproducibility, batch-invariant inference, RL training reproducibility, consistent heuristic evaluation. Supports: SGLang deterministic mode, seed configuration, validation.

AutoHD (Automated Heuristics Discovery) methodology for LLM-based heuristic generation. Use when: generating heuristic functions, evolving candidates, implementing inference-time search guidance, creating executable Python heuristics. Supports: heuristic proposal, evaluation, evolution, convergence testing.

Project analysis patterns for extracting structure and conventions from source code. Use when: analyzing source code, detecting frameworks, extracting patterns, "analyze project", "learn from example", project inspection, framework detection, dependency analysis, architecture recognition. Supports: AST parsing, config detection, dependency analysis.

Quest debugging and profiling tool orchestration. Use when: debugging VR apps, LogCat streaming, GPU profiling, ovrgpuprofiler, scrcpy mirroring, MQDH integration, crash analysis, "show logs", "debug session", "profile GPU", "screen mirror", Immersive Debugger, DebugMember, performance analysis. Supports: ADB tools, Meta Quest Developer Hub, wireless debug.

Expert guidance for MCP (Model Context Protocol) server integration. Use when: MCP servers, external tools, .mcp.json, transport types, model context protocol, "create MCP", "add MCP server", MCP config. Supports: stdio, http, sse transports, environment variables.

Expert guidance for designing Claude Code custom subagents. Use when: creating agents, subagent design, agent frontmatter, tool scoping, permission modes, agent orchestration, "create agent", "build agent", agent template, delegation patterns. Supports: frontmatter schema, tool restrictions, skill injection.

Execute AdCP Signals Protocol operations with signal agents - discover audience signals using natural language and activate them on DSPs or sales agents. Use when users want to find targeting data, activate audience segments, or work with signal providers.

Analyze, optimize, and slice 3D models for printing. Works with 3MF files saved from Bambu Studio GUI. Use when the user wants to check print settings, optimize for speed/strength, or get print estimates.

Standard Operating Procedure for /specify phase. Covers classification, research depth, clarification strategy, and roadmap integration.

Standard Operating Procedure for /clarify phase. Covers question generation, prioritization, structured formats, and spec integration.

Generate dismech definitions from OHDSI/ATLAS cohort definitions or other computable phenotype logic. Use when converting OMOP cohort JSON, drafting PheKB-style phenotype algorithms, or mapping FHIR/CQL/OMOP rules into dismech `definitions` blocks.

Mine Disease Trajectories (DT/DisTraj) outputs for comorbidity/trajectory candidates, including parsing DT JSON/TSV, extracting directed pairs, filtering by sex or significance, and mapping signals into dismech comorbidity YAML.

Benchmarking AI models with Nvidia Aiperf and analyzing benchmark results. Use when the user wants to run performance benchmarks on LLM inference endpoints, analyze Aiperf CSV/JSON benchmark output files, generate performance reports from benchmark data, compare model performance metrics like TTFT, ITL, throughput, or set up benchmark configurations for vLLM, TGI, or other inference servers. Triggers on keywords like aiperf, benchmark, TTFT, ITL, throughput, inference performance, model benchmark.

Skill para garantizar el desarrollo seguro, eficiente y efectivo de aplicaciones Angular 21.1+.

Pilot the Compass Rust binary to parse README structures or check system dependencies.

This skill should be used when the user asks to "automate mobile app", "test mobile UI", "scrape mobile app data", "tap button on phone", "interact with iOS Simulator", "control Android Emulator", "use mobile-mcp tools", "click on mobile screen", or when developing skills/commands that use mobile-mcp. Provides tool selection, workflow patterns, and selective reference loading for the mobile-mcp MCP server.

Prismaを使用したDBスキーマ変更とマイグレーション管理。schema.prismaの編集、マイグレーション生成・適用、型定義作成を行う。Use when user wants to "add table", "modify schema", "create migration", "add column", "Prismaでマイグレーション", or needs database schema changes with Prisma.

Small, safe refactorings before feature work using Kent Beck's "Tidy First?" patterns (guard clauses, extract helper, move to model, etc.). Invoke as `/cga-tf-refactoring [file]` or use when preparing code for changes, like "tidy this file before adding feature", "refactor before implementing", "clean up structure before modifying", "整理してから機能追加", "リファクタリングしてから変更". NOT for large refactorings or code without tests.

Standards for service-to-service authentication and API calls. Use when creating new services, adding API routes, implementing auth middleware, or calling other microservices.

Diagnoses and fixes Unity Assembly Definition (.asmdef) errors, specifically missing references and DLL linking issues.

Use when the user asks you to "send a message to an agent in another project", "spawn agents in a project", "check on agents", "watch progress", "see if any agent has questions", or mentions NTM/tmux agent orchestration across /data/projects/PROJECT. Provides a deterministic JSON-only workflow using NTM robot APIs plus bundled scripts.

Process inline {edit annotations} in Obsidian vault notes. Use when the user says "edit my notes", "process annotations", "run edit", "fix my annotations", or has left {curly brace instructions} in markdown files for batch processing.

Help users conduct effective usability testing. Use when someone is planning user tests, designing prototype validation, preparing usability studies, or trying to understand why users struggle with their product.