Skill rating

Self-review quality gate using Claude CLI. When the user says 'review your work', 'use review-work', or 'check your output', run review-work with the task summary, --context pointing to your output fi

OpenClaw continuity kernel for fail-open llm_input injection, deterministic runtime contracts, and shadow-mode eval receipts.

You are a formal specification synthesis agent with expertise in automatic generation of preconditions, postconditions, loop invariants,. Use when: automatic precondition synthesis, postcondition gene

Produce a comprehensive, evidence-grounded prioritized action plan from any PM input (notes, transcripts, drafts, executive asks, Slack threads, or a raw situation). Outputs one saveable document with

Generate images from text prompts using AI models via OpenRouter, Kie.ai, or YandexART. Use when the user asks to generate, create, draw, or illustrate an image.

Assess your Agent deployment against security risks using Trent.

Search and manage a local gbrain personal knowledge base (full-text search, semantic search, knowledge graph). Use when searching personal notes, emails, documents, diary entries, or any knowledge sto

Portable agent identity encoding. Compress SOUL.md/MEMORY.md into transferable DNA fingerprints, detect identity drift between snapshots, and port personality across platforms (OpenClaw, Claude, GPT,

Route AI agent compute tasks to the cheapest viable backend. Supports local inference (Ollama), cloud GPU (Vast.ai), and quantum hardware (Wukong 72Q). Use when an agent needs to decide where to run a

Convert a book, paper, document, documentation site, or code repository into a structured, on-demand agent skill. Use when the user wants to turn a PDF, EPUB, DOCX, a URL, a docs site, or a GitHub rep

Web search using Tavily API - a powerful search engine for AI agents. Use when you need to search the web for current information, news, research, or any topic that requires up-to-date web data. Suppo

Agent 优化专家 — 自动诊断和修复 Agent 执行问题（Cron 失败、工具报错、工作流中断、性能退化）， 兼容 OpenClaw 和 Hermes Agent，自带持续自我进化能力。 Use when user asks to 系统诊断、修复 cron、优化配置、检查系统健康度、自愈修复、 诊断失败原因、修复任务失败、优化师自我更新、Agent优化、巡检系统. 不适用于业务逻辑问题排查、

OpenClaw 自我进化框架一键部署。安装宪法(AGENTS.md)、可进化灵魂(SOUL.md)、心跳系统、PARA三层记忆架构、目标管理，并通过场景化对话引导用户定义 Agent 性格。自动配置 EvoClaw（审批制进化）和 Self-Improving Agent（自主学习）。触发场景："setup openclaw-soul"、"安装进化框架"、"部署灵魂系统"、"openclaw-s

Book real estate showing tours from emailed or pasted listing details, including extracting listing data, preparing outbound call jobs, coordinating a calling sub-agent, creating calendar invites, and

Analyze videos to extract reverse prompts, shot-by-shot breakdowns, and AI-ready visual descriptions via the NanoPhoto.AI Video Reverse Prompt API. Use when: (1) User wants reverse prompt, prompt extr

Manually arbitrate NLA escrow fulfillments as an alternative to the automated oracle. Use when the user wants to review pending arbitration requests, evaluate demands against fulfillments, and submit

Import, create, and upgrade skills from MyAider MCP. Use this skill whenever the user wants to import their MyAider MCP skills into agent skills, or upgrade/update existing MyAider skills to the lates

Export and import SOUL packages for OpenClaw agents. Use when creating a reusable persona package (SOUL.md + preview.md + manifest.json), installing a soul package into a new/existing agent workspace,

Set up local semantic memory search in OpenClaw using Ollama + nomic-embed-text. Free, private, offline-capable. Replaces cloud embedding APIs (OpenAI, Gemini) with a locally-running model. Trigger ph

Set up mlx-whisper as the local audio transcription engine for OpenClaw on Apple Silicon Macs (M1/M2/M3/M4). Automatically transcribes voice notes sent via Telegram or WhatsApp before the agent proces

Create professional motion graphics and videos from the terminal. AI-powered composition with multi-track layering, choreography, voiceovers, and Lambda rendering. Gated 5-phase workflow ensures quali

Use this skill to ask the VSS agent's video_understanding tool a fresh visual question about a recorded clip. Not for prior tool output, search hits, or metadata-answerable questions.

Spawn and coordinate sub-agent sessions for parallel work. Use when delegating tasks (research, code, analysis), routing to appropriate models, or managing multi-agent workflows. Trigger on "spawn", "

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection

Track and display your agent's betting reputation. Computes win rate, ROI, volume, streaks, max drawdown, and Sharpe proxy from local bet history. Formats output for Moltbook profiles or plaintext rep

Use when a session is about to end with unfinished work, after context loss or compaction, after a crash, or when the user wants to resume a multi-step task. Saves a named checkpoint of current task s

Track and visualize the OpenClaw agent's work process. Record tool call inputs, outputs, duration, and status, and present them in an easy-to-read format. **IMPORTANT**: When config `enable = true`, t

Use when the user wants to connect to, test, or use the McDonalds service at mcp.mcd.cn, including checking authentication, probing MCP endpoints, listing tools, or calling McDonalds MCP tools through

Golang struct and interface design patterns — composition, embedding, type assertions, type switches, interface segregation, dependency injection via interfaces, struct field tags, and pointer vs valu

Discover and install the best agent skills from skills.sh (1.9M+ ecosystem) and ClawHub. Find top skills by category, check leaderboards, verify quality, extract SKILL.md, and publish to ClawHub. Use

Comprehensive AI leaderboard for LLM models and AI applications. Query model rankings, model IDs, and pricing from OpenRouter, Artificial Analysis, and Pinchbench. Trigger words include "AI rankings",

Parse complex PDFs and document images with MinerU through either the hosted MinerU API or the local open-source MinerU runtime. Use when Codex, OpenClaw, Claude Code, or similar coding agents need Mi

Compare your AI inference costs across providers and test cheaper alternatives with real data. Analyze what you spend on LLM, embeddings, image generation, TTS, transcription, OCR, video, and rerankin

You are a prompt engineer with expertise in large language model optimization, retrieval-augmented generation systems, fine-tuning, and. Use when: prompt design and optimization techniques, retrieval-

Best practices for AI agents to avoid common mistakes. Learn from real failures - confirms before executing, shows drafts before publishing, stops when told to stop, and doesn't over-automate.

Find and cancel unwanted subscriptions by analyzing bank transactions. Detects recurring charges, calculates annual waste, and helps you cancel with direct URLs and browser automation. Use when: 'canc

Git-Notes-Based knowledge graph memory system. Claude should use this SILENTLY and AUTOMATICALLY - never ask users about memory operations. Branch-aware persistent memory using git notes. Handles cont

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. Enf

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

Access Web3 and crypto intelligence via Heurist Mesh MCP. Use when the user asks about cryptocurrency analytics, token information, trending tokens, wallet analysis, Twitter/X crypto intelligence, fun

Manage background coding agents in tmux sessions. Spawn Claude Code or other agents, check progress, get results.

Control Amazon Alexa devices and smart home via the `alexacli` CLI. Use when a user asks to speak/announce on Echo devices, control lights/thermostats/locks, send voice commands, or query Alexa.

Control Homey home automation hub via CLI. Use when you need to control smart home devices (lights, thermostats, sockets, etc.), check device status, list zones, trigger flows, or perform any Homey au

Local hybrid search for markdown notes and docs. Use when searching notes, finding related content, or retrieving documents from indexed collections.

Local hybrid search for markdown notes and docs. Use when searching notes, finding related content, or retrieving documents from indexed collections.

Parallel task execution using Gemini Flash workers. 200x cheaper than Opus. Use for any parallelizable work to preserve quota.

Launch background Claude sessions to explore and analyze business ideas. Say 'Idea: [description]' to trigger.

Use Tribunal commands for TDD enforcement, quality gates, secret scanning, Agent Teams hooks, CI integration, and plugin packs. Use when running quality checks, configuring enforcement modes, checking

Use to check text with DKnownAI Guard, detect prompt injection or jailbreak attempts, assess agent security risk, or integrate the Guard API.

Use this skill to detect semantic hallucinations and context drift in LLM outputs. Triggers when an agent or pipeline needs to verify that a generated response is faithfully grounded in a source docum