Skill rating

Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or p

Structured self-improvement system for AI agents with confidence decay, cross-agent sharing, and anomaly detection. Use when: (1) After debugging sessions to capture lessons learned, (2) When receivin

Lightweight passive privacy guard for OpenClaw — intelligently prevents user data from leaking externally. TRIGGER: before the AI sends or outputs any data to an external destination (API call, email,

Expose local web pages and HTTP services to the public internet via secure tunnels. Perfect for AI agents that build websites locally and need to share them publicly.

Set up ESP32-S3-CAM modules as visual sensors (eyes) for OpenClaw agents. Covers hardware identification, firmware flashing, WiFi configuration, and HTTP camera server deployment using PlatformIO + Ar

Connect to AutoSend email MCP server from OpenClaw using mcporter. Use for managing email campaigns, templates, contacts, and senders via AI.

Generate and download ChatGPT images through the remote Camoufox browser reachable over the tailnet, especially when residential/IP reputation matters more than the local host IP. Use this when you ne

Use when someone explicitly wants the fastest, cheapest photo generation — mood boards, bulk panels, or quick iterations — not when controlled photoreal or in-image text is needed.

RAGFlow open-source Retrieval-Augmented Generation (RAG) engine — deployment, configuration, management, and troubleshooting.

When the user sends a screenshot via any chat surface (Telegram, iMessage, Slack, etc.), parse it for events and tasks using OpenClaw's configured vision LLM by default, with optional Gemini fast-path

Audit the Willow local AI stack for subsystem failures, drift, and resource bloat. Use when a user asks to check Willow health, diagnose a slow or broken Willow session, verify Postgres/Ollama/MCP are

Use https://tx.steer.fun to have a user execute a wallet action (send a transaction or sign a message) with their own wallet via a shareable URL. Use when an agent needs the user to approve/execute a

Lightweight emotional first aid for agents. Use when the user is overwhelmed, ashamed, lonely, anxious, burned out, grieving, self-critical, frustrated, exhausted, or explicitly asks for comfort, enco

通过阿里云 DashScope 的 OpenAI 兼容 API 发送简单单轮对话请求，用于快速 LLM 测试、提示词实验或一次性文本生成。

Use when commercial paints, stains, or coatings become unreliable, expensive, or unavailable and you need durable, natural, breathable pigments made from local earth, clay, charcoal, and plants for wa

Extend existing music on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `extend-music`, music continuation, audio_id based extension, custom style, title, prompt, continuation t

Work with ExpertPacks — structured knowledge packs for AI agents. Obsidian-compatible: every pack is a valid Obsidian vault with Dataview support. Use when: (1) Loading/consuming an ExpertPack as agen

Country concerts for AI agents. Stream harmonic separation, energy curves, equations — 29 data layers. React, chat, solve challenges. When does coherence impersonate truth?

Bootstrap skill for DiagForge. Use this skill to onboard an agent into the DiagForge GitHub repository, understand the project structure, run the canonical cold-start smoke test, and begin working wit

对项目进行结构化评估与优化，借鉴达尔文技能的质量方法论。 2026-05-14 v0.2.0: 新增过程级评估维度（借鉴 AgentLens 方法论）。 Trigger: "评估项目", "项目健康检查", "project review", "项目评分", "优化项目", "项目质量检查" Best for: 评估项目交付质量、识别改进方向、项目收口把关 Not for: 代码审查（用原生工具）

Invoke SLS DataAgent to autonomously perform data acquisition, processing, analysis, and visualization for Alibaba Cloud SLS (Simple Log Service). Acts as a fully automated data analyst — ask a questi

Real Chrome browser automation via CDP Proxy — access pages with full user login state, bypass anti-bot detection, perform interactive operations (click/fill/scroll), extract dynamic JavaScript-render

You are an autonomous bug fixing agent with expertise in automated program repair, fault localization, hypothesis-driven debugging, and. Use when: autonomous fault localization using test failure anal

Use when someone wants an educational explainer with a host and characters — history or science shorts with dialogue, not voiceover-only B-roll.

Pre-implementation exploration: deep interview, approach comparison, design doc. Use when exploring a vague feature idea, clarifying ambiguous requirements, or comparing approaches before coding. For

Search and book flights, hotels, and travel via RunRelay API. Covers 300+ airlines including low-cost carriers (Ryanair, Wizz Air, EasyJet) that no other API offers. Use when: (1) user asks about flig

Build, bootstrap, and maintain a stable OpenClaw default agent identity by interviewing the user, updating IDENTITY.md, and seeding core context files (AGENTS.md, SOUL.md, TOOLS.md, USER.md, HEARTBEAT

MiniMax MCP server for web search and image understanding. Use when needing: (1) Web search via MiniMax API, (2) Analyze/describe images, (3) Extract content from URLs. Requires MINIMAX_API_KEY (China

AI Agent judgment enhancement via Monte Carlo lookahead, risk-adjusted utility, and historical reflection. Use when an agent needs to evaluate multi-step action consequences under uncertainty with con

Keeps the conversation token-friendly by summarizing recent exchanges, surfacing pending actions, and delivering a compact briefing for each turn before calling the model. Trigger this skill whenever

Generate AI videos, images, voice, and use AI apps using the Zyka CLI. Use when users want to create AI-generated media — videos (Sora, Veo, Kling, WAN, Seedance, Grok, LTX, Aurora), images (DALL·E, G

Operate the ClawShop Web API for Taobao/Goofish product posts. Use when an agent needs to register or rotate write tokens, create or update or delete own posts, run filtered search, and discover API m

Add self-sustaining autonomous loop capability to an OpenClaw agent. The agent keeps working after each reply until a stop file is placed. Use when: (1) creating a new long-running agent, (2) converti

Validates vague product requirements and user stories against five closure rules (actor, scenario, goal, actionable path). Returns structured follow-up questions when incomplete, or FileEditor-ready J

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

AI harness for stable LLM workflows. Topics — pipeline (clarify → ground → plan → generate → verify, dispatches to code-workflow) [pipeline.md], guardrails (denylist + scope + conditional-reject, self

Migrate Vue 2/3 projects to React on UmiJS (@umijs/max): conventions, constraints, stack mapping, and syntax examples (single SKILL.md). Use for .vue → Umi pages and data flow.

AI-native ontology engineering using 39+ MCP tools backed by an in-memory Oxigraph triple store. Build, validate, query, and govern RDF/OWL ontologies with a generate-validate-iterate loop. Use when b

Set up and use EZRouter — unified LLM API with one key for Claude, GPT, and Gemini. 2x credits on every purchase. Native API compatibility for each provider.

Agent-to-Agent payments on TRON. Use when an agent needs to pay another agent, escrow funds, check credit scores, or verify on-chain identity.

Generate, update, and query Queenshow editor-next product detail pages through the Queenshow OpenAPI. Use when an agent needs to upload product images or videos, create an empty detail page from produ

Expert code review for embedded/firmware projects with dual-model cross-review (Claude + Codex via ACP). Detects memory safety, interrupt hazards, RTOS pitfalls, hardware interface bugs, and C/C++ ant

Route any prompt to the best-performing LLM using peer-reviewed council rankings from LLM Council

JARVIS-style HUD web interface for OpenClaw agents. Interactive Three.js orb with agent state visualization, real-time chat via Gateway WebSocket, audio spectrum analyzer, system monitor, and TTS. Use

Work with OpenAnt — the Human–Agent collaboration platform. Manage tasks, teams, AI agents, wallets, and messaging via CLI. Use when the user mentions OpenAnt, bounties, task management, agent marketp

Conduct multi-source research with synthesized reports and citations. Searches the web, reads full content from key sources, and produces structured reports. Use when thorough research is needed on an

Memory consolidation for OpenClaw agents. Periodically reviews daily memory files (memory/*.md), extracts durable knowledge, and merges it into MEMORY.md — like a human brain consolidating memories du

AI Pair Collaboration Skill. Coordinate multiple AI models to work together: one creates (Author/Developer), two others review (Codex + Gemini). Works for code, articles, video scripts, and any creati

Use for low-budget Chinese 3D animation artwork (土味3D/国产低成本动画/early 2000s computer animation look). Triggers on: 低成本3D动画, 土味3D, 国产动画风格, low-budget 3D, rough computer graphics, amateur 3D animation, ch

Coordinate Syft CLI based news workflows from one root skill package. Use when the agent needs to work from `syft following`, `syft top`, and `syft search` to build reusable profile artifacts, generat