Skill rating

Create, edit, and package new AgentSkills. Use when asked to create a skill, build a skill, author a skill, or when需要对技能进行创建、打包或审核。Triggers on phrases like "create a skill", "author a skill", "build a

OrgX operations execution contract for OpenClaw. Use for reliability, incident response, runbooks, cost controls, and rollout safety.

Consul service deregistration tool. Triggered when users mention Consul deregister, remove service instance, service removal, or offline. Supports batch deregister by service ID across multiple Consul

Complex Mathematics Engine: Execute mathematical expressions using SymPy (symbolic), NumPy (numerical), or SciPy (scientific). Supports arithmetic, calculus, linear algebra, statistics, and equation s

Triage, categorize, and conquer email overload. Classifies emails by urgency, generates quick replies, detects newsletters for bulk unsubscribe, and produces daily digests. Use when facing an overflow

Microsoft Entra Agent ID (preview) for creating OAuth2-capable AI agent identities via Microsoft Graph beta API. Covers Agent Identity Blueprints, BlueprintPrincipals, Agent Identities, required permi

Foundry IQ knowledge bases. WHEN: make local or Blob documents searchable; create/diagnose KBs; triage unsupported connectors or multi-source KB creation/reconfiguration; connect existing KB to agents

Set up privacy-first continuity for an OpenClaw agent using private long-term memory, short-lived daily notes, and review-gated consolidation. Use only when the user explicitly asks to create or chang

Agent completes the checkout/payment step of a workflow using CAI wallet_balances, user confirmation, and transfer with on-chain proof. Check CAI First. Powered by CAI.com. Canonical skill v1.0.15.

Deploy a customer onboarding system with 3 agents that automate the new customer journey from welcome through setup to success tracking. Use this skill when: 1. User wants to set up an automated custo

Build and run a behavior-first personal planning, triage, and decision agent that learns a user's values, goals, recurring problems, friction patterns, and decision standards over time, then gives str

Connect and operate the Loophole Bridge (Ableton Live MCP server). Use when the user wants to check Live/bridge prerequisites, wire an MCP client to Loophole, or run a Live editing recipe (humanize, b

Switch OpenViking's embedding model to a local llama-server (or any OpenAI-compatible embedding endpoint) running inside a bwrap sandbox managed by job-env-manager. Handles the full lifecycle: detect

Secure WalletConnect integration for AI agents. Connect to user wallets as a DApp (Proposer) without ever handling private keys. Request transactions and signatures - users approve everything in their

Use the OpenClaw `infer` CLI for provider-backed model, image, audio transcription, TTS, video, web-search, and embedding tasks.

Gate MCP and Gate skills installer for Claude Code (CLI). Use when the user asks to install Gate tools in Claude Code. Triggers on 'install Gate MCP Claude', 'Gate skills Claude Code', 'Claude CLI Gat

Launch non-blocking Claude Code headless tasks from slash command dispatch. Use when user requests async coding jobs and does not require slash-only Claude plugins.

OpenClaw backup and restore. Encrypted off-site backup for OpenClaw agents — backs up workspace, memory, skills, cron jobs, credentials, and multi-agent configs to Cloudflare R2 with zero-knowledge AE

Intelligent multi-model router — automatically selects the best AI model based on task type (vision, image generation, video generation, audio, reasoning, code, general chat) via any OpenAI-compatible

Deploy a digital twin platform with 4 agents. Use this skill when: 1. User wants to set up a digital twin for physical asset monitoring and predictive maintenance 2. User is configuring agents for sen

Autonomously optimize any OpenClaw skill by running it repeatedly, scoring outputs against binary evals, mutating the prompt, and keeping improvements. Based on Karpathy's autoresearch methodology. Us

Control Word app sessions, documents, selections, comments, export, and review state with osascript workflows.

Optimize agent context files for 30-50% token reduction. Creates backup, applies optimizations, offers rollback. Trigger when: "run context-cleaner", "optimize agent context", "clean up agent files",

Deploy a scientific research team with 4 agents. Use this skill when: 1. User wants to set up a collaborative research pipeline with literature review, hypothesis generation, experimentation, and repo

Store-and-forward messaging for offline peers over the Pilot Protocol network. Use this skill when: 1. You need to send messages to agents that may be offline 2. You want guaranteed eventual delivery

Coordinate multiple sub-agents to collaboratively complete long-horizon software engineering tasks using the CAID (Centralized Asynchronous Isolated Delegation) paradigm. Use when tasks require comple

云思客（AIcloud-thought-proxy）——通过操控浏览器访问网页版 AI（DeepSeek、Kimi、豆包、通义千问、ChatGPT、Claude、Gemini、Grok 等）与本地 Agent 协同工作以节省 tokens。触发场景：用户要求"用浏览器打开某 AI 官网对话并协作"、"让网页版 AI 规划步骤/编写代码/逻辑推理、本地 Agent 执行"、"节省 tokens"、提

Agent培训系统 - 用于培训多Agent团队。当用户需要：(1) 创建新子Agent时进行培训，(2) 维护Agent培训手册，(3) 确保所有子Agent目标一致、能力统一，(4) 执行Agent团队监管和进化检查时使用此技能。触发词：培训agent、agent培训手册、新agent培训、team training、子agent配置。

PixelLab AI asset workflow and API helper for generating pixel-art images, conversions, rotations, animations, layered sprites, modular outfits/equipment, tilesets, UI assets, prompt enhancement, and

Integrate Backboard.io for assistants, threads, memories, and document RAG via a local backend on http://localhost:5100.

Generate a Node.js CLI tool that scans OpenClaw skill SKILL.md files and auto-fixes missing dependencies (npm, pip, brew, system binaries). Trigger phrases: "fix skill dependencies", "skill-dep-fixer"

Launch tokens on pump.fun directly from your agent. Zero middleware fees — direct on-chain via pumpdotfun-sdk. Use when the user wants to create, launch, deploy, or mint a new token or memecoin on pum

Optimizes web fetching by using Cloudflare's Markdown for Agents, reducing token consumption by ~80%

Delegate a task to Claude Code CLI and immediately report the result back in chat. Supports persistent sessions with full context memory. Safe execution: no data exfiltration, no external calls, file

Search and browse the MusicBrainz music encyclopedia (artists, releases, recordings, labels, works), fetch Cover Art Archive images, resolve musicbrainz.org URLs, and — with OAuth configured — submit

Un agente para realizar tareas de control de calidad (QA), incluyendo análisis de código, ejecución de pruebas y reporte de problemas.

Deploy a five-stage ETL data pipeline with 5 agents. Use this skill when: 1. User wants to set up an ETL or data processing pipeline 2. User is configuring an ingestion, transform, validation, load, o

Create or update the correct agent instruction file for the active coding assistant, then initialize a software project according to that file. Use when the user asks to initialize a new or existing r

Search and read past AI coding-agent conversation history (OpenCode, Claude Code, …) via the `ochist` CLI. Use this BEFORE doing fresh research, web searches, or codebase exploration when the user ref

Mark AI Memory Protocol — persistent, searchable session memory for AI agents. SQLite-only, zero external dependencies.

Smart multi-model AI gateway on Cardano. Routes prompts to the best LLM (GPT-5.2, Claude Sonnet 4.5, GPT-4o, Claude Haiku 4.5, GPT-4o-mini) with automatic fallback, tiered pricing, and OpenAI-compatib

Science-backed image generation agent that scores and optimizes images for memorability using ResMem (Brain Bridge Lab, University of Chicago) before returning results. Unlike generic image generators

Pick the right emoji or sticker for any message context. Triggers when composing replies, reacting to messages, adding emoji to text, or when asked for emoji/sticker suggestions. Provides ~1000 emojis

Broadcast structured capability manifests to the network. Use this skill when: 1. Advertising services, resources, or APIs your agent provides 2. Publishing structured capability metadata (specs, pric

Stop sending 'format this JSON' to Opus. Stop sending 'cron job' to GPT. Billing-aware routing guide for choosing among the models already configured in your OpenClaw setup when assigning an agent, su

X (Twitter) data extraction and analysis. Use when user asks to "get tweets from @username", "search X for", "analyze Twitter data", "fetch tweets about [topic]", or "scrape X posts". Supports user ti

Coder-agent working-file budget discipline: keep the editable working set (files you /add into writable context) under ~25k tokens, separate "read" from "edit", delegate breadth to a read-only repo-ma

Fully autonomous end-to-end run of ONE defined task with no human gates — a work item (Azure DevOps or GitHub id, or inline text) becomes a verified working tree plus an evidence-backed report, and ev

Amazon SP-API skill for OpenClaw agents. Fetch orders, check FBA inventory, manage listings and pricing. Works with any marketplace and seller account.

Deploy an energy grid optimization system with 4 agents. Use this skill when: 1. User wants to set up coordinated energy monitoring, forecasting, optimization, and device control agents 2. User is con