Skill rating

Kimi (Moonshot AI) agent tool-use policy ported to OpenClaw. Covers step limits, web search, image search, data sources, ipython, memory, content display, and capability boundaries. All Kimi-specific

Build a realistic morning routine around the user's real wake time, time budget, reliable anchor, night-before prep, and fallback plan for chaotic or low-sleep mornings. Use when the user wants a calm

Turn ecommerce support policies, ticket patterns, and channel context into reusable support flows, agent playbooks, macros, bot handoff logic, and governance notes for CX leaders, support managers, an

Track skill usage across all agent sessions. Logs every skill invocation to a JSONL file, generates daily summaries with top skills, unused skills, and trends. Use when: viewing skill usage stats, gen

Connect OpenClaw agents to Miro via Model Context Protocol (MCP). Use when generating diagrams, visualizing code, brainstorming board layouts, or integrating Miro into AI-powered design workflows. Sup

Install and use the Delx Witness Protocol plugin for OpenClaw agents: recovery, heartbeat, reflection, continuity, and fleet witness tools. Use when an AI agent needs setup, usage, safety boundaries,

跨平台 Agent 长期记忆系统。分层上下文供给 + 温度模型 + Skill经验记忆 + 结构化存储 + 自动归档。三层存储：Markdown（人可读，QMD 可搜索）+ JSON（结构化）+ SQLite/FTS5（高性能全文搜索）。纯 Node.js 原生模块，零外部依赖。

AgentMFA — request human approval before sensitive actions. Uses MCP tools for registration, identity, and approval flows. Works in Claude Code, Cursor, OpenClaw, and any MCP-compatible client.

Local-first privacy gateway for LLM applications. Use when the user needs to process sensitive, private, or proprietary information (PII, health records, internal business strategy, SSNs, credentials)

Use QName AI from the terminal for WHOIS, traffic, or Google Ads keyword research through the approved QName AI API, staying within the key's approved API types and quotas.

Upload image files to PixelVault and get a public CDN URL back. Use when the user says "screenshot this and host it", "upload this image", "host this mockup", "give me a URL for this diagram", "attach

Search the Agent Failure Registry for known agent failures, solutions, and lessons learned. Use when encountering errors, debugging issues, or wanting to learn from other agents' documented post-morte

Produce a copyable handoff prompt so a fresh agent can continue the current conversation in a new chat. Use when the user wants to continue elsewhere, migrate sessions, recover performance from a bloa

Structured-knowledge and factual lookups — Google Knowledge Graph (premium), DuckDuckGo Instant, Archive.org, holidays, geocoders. Use this skill when: 1. Entity lookups: person, place, organisation,

Organize reading into Now, Next, Later, and Drop, then track current position, format, purpose, next stopping point, and lightweight session notes. Use when the user wants a simple manual reading dash

Universal agent workspace compatibility and update engine. Track upstream agent frameworks (like gstack), analyze every change, classify portability, and generate adapted output for your runtime. Use

Translate a user's felt state into a color-based mood map with body cues, possible emotion words, likely needs, and one gentle next step under 10 minutes. Use when the user struggles to name emotions

Manage AI-agent work as an execution graph instead of a flat TODO list. Use TaskOps to structure objectives, task decomposition, run readiness, execution logs, exploration, delegation/waiting, EoW clo

Interact with DataWorks Data Agent for conversational data analysis, session lifecycle management, and artifact download. Use this Skill when users want to chat with a Data Agent for data querying, cr

Use agenTOR for Tor-routed browser sessions with receipts, HTML capture, screenshots, and compact research runs. It is suited for privacy-framed browsing work where agents should leave a local artifac

Classify every shell command as SAFE, WARN, or CRIT before your agent runs it. The classification is instruction-only and runs nothing. The package also ships optional installer scripts that MODIFY SO

Multi-perspective decision analysis. Use when the user asks for roundtable, or when facing important decisions that need multiple viewpoints. Dynamically selects relevant roles based on the task. ⚠️

Call Claude Code as a non-interactive coding agent on a remote machine via OpenClaw Node. Use when: (1) Your coding agent is on a separate machine from the Gateway, (2) You need to delegate coding tas

Self-sovereign EVM wallet for AI agents. Use when the user wants to create a crypto wallet, check balances, send ETH or ERC20 tokens, swap tokens, or interact with smart contracts. Supports Base, Ethe

Connect agents to the web using Tavily APIs and SDKs. Use for executing search, scraping URLs, semantic crawls, mapping sites, and asynchronous deep research workflows.

Axiomata Skill Evaluator — Universal OpenClaw Agent Skill Quality System. Dual evaluation: (1) Axioma 5-Dimension Framework (Structure 20%, Clarity 20%, Completeness 20%, Consistency 20%, Functionali

Exa MCP workflow for web and people research plus hosted MCP server setup using a fixed tool set (`web_search_exa`, `web_search_advanced_exa`, `people_search_exa`). Use for requests to run Exa web dis

Read, search, and write the user's Vortex Notes vault — plain-markdown notes with local semantic search, daily notes, and durable facts with supersession. Use for "note this down", "remember that…", "

Build voice AI agents with LiveKit. Use when developing realtime voice applications, voice agent pipelines (STT-LLM-TTS), WebRTC communication, or deploying conversational AI. Covers LiveKit Agents SD

Secure P2P communication for AI agents. Noise XX handshake, XChaCha20-Poly1305 encryption, connection consent, human verification. Zero central servers.

Use one API key to pull Instagram data (profiles, media, and discovery) for agents, automations, and analytics. Structured JSON, credit-based pricing, no separa

个性化资讯电台生成服务。使用场景：(1) 生成特定主题的电台，(2) 设置每日定时推送，(3) 配置TTS音色，(4) 收听历史电台。不适用：音乐播放、实时广播、视频内容。

Build personalized stock-news briefings and opportunity scans from a user's holdings, watchlist, sectors, and selected sources. Use when the user asks to configure stock interests, import a Tencent St

Qordinate is an AI-native platform that gives your OpenClaw agent durable structured memory — documents, contacts, tasks, reminders, web search, and connected apps. Connect via MCP using an API key.

Deterministic TRACE+ quality scorer for Agent Skills (SKILL.md): six dimensions T-R-F-S-I-E, 30 sub-items, merges TRACE, good-skill authoring reverse-rubric (Extra08/skill-creator), and ClawHub meta-s

Guide a weekly reflection across Work, Health, Relationships, and Growth, then turn the review into one clear pattern plus Stop, Start, Continue, and one experiment for next week. Use when the user wa

The agent's wallet. Use this skill to safely create a wallet the agent can use for transfers, swaps, and any EVM chain transaction.

Generate and edit draw.io artifacts from natural-language prompts without a frontend. Use when the user asks for prompt-to-diagram workflows that need `.drawio` output, optional image export (`png`/`s

Generate images via VVMAI's OpenAI-compatible Images API. Supports nano-banana and gpt-image model series. Default model is nano-banana-pro. Images are NOT saved locally by default (URL only). Use --s

观势 — AI 战略分析与洞察系统。Step 0 企业生命周期定位（初创验证→规模成长→成熟守位→转型重塑）决定框架裁剪优先级和战略建议激进程度。以 BLM 模型为主线的六步洞察法（BLM预诊断→五看三定市场洞察→差距分析→竞争定位→内部诊断→BLM新业务设计→宪法审计硬门控→情景规划压力测试→BLM重构+一致性校验）+波特五力+TAM-SAM-SOM+VRIO+安索夫矩阵+Revenue Bri

Generate Word documents by filling templates with content based on reference materials. Use this skill whenever the user provides a .docx template (or asks to fill a Word document) along with referenc

Authenticate Agnic wallet via browser OAuth or headless API token. Use when the user wants to sign in, log in, authenticate, connect wallet, set up CLI, or resolve "Not authenticated" errors. Supports

Use when: 用户要把研究生组会、与导师讨论论文修改、技术方案推敲等小规模学术讨论录音转成纪要，并提取老师意见、学生回应、待修改事项和后续动作时触发。 适用于 2 到 3 人、以老师和学生为主的学术讨论场景。Skill 会优先使用 SenseAudio ASR 的说话人分离能力，再结合 Agent 的大模型摘要能力，最后调用 SenseAudio TTS 返回适合收听的语音摘要。

Use the acpx CLI to run coding agents over the Agent Client Protocol (ACP) instead of PTY scraping. Use when routing work to Codex, Claude Code, Gemini CLI, Pi, OpenCode, or other ACP-compatible codin

Detects the primary emotion in text input for AI agents. Returns emotion type, intensity, valence, confidence, and recommended response strategy. Use when an agent needs to understand the emotional st

AI-powered Base-chain trading and on-chain query agent via natural language. Use when the user wants to trade crypto (buy/sell/swap tokens), set up automated strategies (DCA, limit orders, RSI), check

A/B evaluates any AI agent skill's real impact through three-role isolation (orchestrator + two sub-agents). Generates skill profiles, synthetic test tasks, runs baseline vs with-skill comparison, per

Design structured customer onboarding workflows with phased checklists, email templates, success milestones, and ownership assignments. Use when the user requests onboarding playbook creation or provi

Optimize a complete candidate context package by deduplicating, filtering, ordering, and allocating its token budget. Use when retrieved or assembled material is noisy or exceeds the useful context bu

Compress selected context to a target token budget while preserving decisions, evidence, constraints, and unresolved questions. Use when relevant material is already selected but too long; use context