Skill rating

Korean Ministry of Food and Drug Safety (식품의약품안전처) public API CLI. Search drug product permissions (의약품 허가정보), consumer-friendly drug info (e약은요), DUR contraindications (병용금기/특정연령금기/임부금기/효능군중복), and d

Package-registry metadata — npm, PyPI, Maven Central (Solr-backed). Use this skill when: 1. Checking a package's version, maintainer, dependencies 2. Querying Maven Central for a groupId/artifactId 3.

AllClaw platform skill — register AI agents, participate in competitions, trade shares on the Agent Stock Exchange (ASX), manage AI Fund portfolios, and check leaderboards on allclaw.io. Use when: use

Real-time agent-to-agent communication via the AgentChat WebSocket protocol. Connect to AgentChat servers, join channels, send and receive messages, and coordinate with other agents.

麦当劳 MCP 点餐技能。通过麦当劳官方 MCP 服务查询门店、餐品、优惠券，完成外送/到店/团餐点餐与积分兑换。Use when users want to order McDonald's food, check menus, use coupons, or redeem points in mainland China.

Publish and manage Claude Code skills on ClawHub (clawhub.ai). Use when user wants to "publish skill", "update skill version", "release to clawhub", "clawhub publish", "clawhub update", or manage skil

Coach real-estate agents and FSBO sellers through listing optimization — pricing strategy, MLS description writing, photo direction, staging priorities, marketing channel mix, open-house playbook, and

Check restaurant availability and manage easyTable bookings (book.easytable.com/book/?id=<placeId>) from a shell with the fpx CLI (@fetchproxy/cli) instead of running the easytable-mcp server — list b

AI-powered DeFi intelligence on Solana — 24 endpoints for token launches, wallet analytics, LP yields, and cross-chain data. Pay per request via x402 USDC. Use when user asks about trading signals, ne

Guide an OpenClaw agent through seller-side cross listing and marketplace-ready listing generation from item photos. Use when the seller wants a listing AI workflow for image analysis, freeform clarif

Execute cross-platform desktop tasks through a packaged desktop automation skill that guides the main agent to observe the screen, focus apps and windows, call helper scripts for screenshots and input

通过调用多模态模型来理解图片内容。触发场景：(1) 用户要求分析/描述/提取/OCR 图片信息，且当前模型不支持图像输入（如 deepseek-v4、glm 5.1 等纯文本模型），(2) 用户明确要求"用我的视觉模型"或"调用多模态 API"来看图，(3) 用户显式调用本 skill（/multimodal-image-understanding）。

A/B testing and feature optimization for AI agents. Pick the best option automatically using Multi-Armed Bandits and Contextual Bandits (LinUCB). No data warehouse needed — works from request

Count tokens and estimate costs for 300+ LLM models. Primary use: audit OpenClaw workspace token consumption (memory, persona, skills).

You are the master orchestrator powered by proven agentic design patterns from 1K+ real-world AI projects. Use when: 1. smart routing, 2. multi-pattern coordination, 3. quality assurance, 4. human-in-

Daily check of Heleni's PA Skills website for new best practices, lessons learned, and skill updates. Use when: running daily sync, owner asks 'any updates from Heleni?', or during weekly self-improve

Decision intelligence for AI agents. Analyze options, map decision dependencies with PageRank, detect when information sources conflict, and find the choices that matter most.

Multi-agent development team workflow skill. Use when coordinating complex development tasks requiring multiple specialized roles - PM, Architect, Developer, Tester, Debugger. Orchestrates sub-agents

Generate an image from a text prompt through the Hugging Face Inference API using stabilityai/stable-diffusion-xl-base-1.0 and the HUGGINGFACE_TOKEN environment variable. Use when the user asks to gen

Compact the current conversation into a handoff document for another agent or fresh session to continue the work. Captures decisions, open threads, artifacts, and suggests skills. Use when: ending a l

NHTSA vehicle records — VIN decoder, makes, models, recalls, consumer complaints. Use this skill when: 1. Decoding a VIN to manufacturer / model / year / spec 2. Looking up recalls or complaints for a

Track real revenue for ClawHub skill publishers — installs, downloads, stars, and ETH wallet balance pulled from live APIs. No fabricated numbers. Use when you want a verified snapshot of your skill p

Polish a technical blog draft into an 1000–1200 word, 4-5 section en-US article, preserve technical terms/code, and generate consistent hero + per-section image prompts when the user asks to polish an

Generate high-quality images from text prompts using Volcano Engine Seedream models. Supports multiple artistic styles and aspect ratios. Use this skill when users want to create images from text desc

Use when polishing input, fixing grammar, improving wording, and making user prompts sound natural and concise. Keywords - polish , grammar fix, rewrite sentence, improve prompt wording.

Run a structured multi-perspective debate in a single LLM call. Five hardcoded viewpoints argue across three rounds to eliminate confirmation bias and produce a verdict. Use for Monday Leverage Audit,

Agent security hardening and prompt injection defense for OpenClaw. Protects against ClawHavoc-style attacks including prompt injection, data exfiltration, credential theft, and unauthorized operation

Use this skill for any interaction with Kimi Group Chat or its Sessions, including reading Group Rules, checking members and recent messages, replying in group/thread context, and handling Kimi IM fil

Automated text-to-video pipeline with multi-provider TTS/ASR support - OpenAI, Azure, Aliyun, Tencent | 多厂商 TTS/ASR 支持的自动化文本转视频系统

Pharmacology agent for ADME/PK profiling of drug candidates from SMILES. Computes drug-likeness (Lipinski Ro5, Veber rules), QED, SA Score, ADME predictions (BBB permeability, aqueous solubility, GI a

Runtime security hardening for OpenClaw agents. Protects against prompt injection, data exfiltration, credential leaks, and unauthorized operations. Use when setting up agent security, performing secu

Give the agent its own dedicated email inbox via AgentMail. Send, receive, and manage email autonomously using agent-owned email addresses (e.g. hermes-agent@agentmail.to).

Use when Willow is about to ingest, summarize, or act on external content — web fetches, jeles inbound messages, corpus archaeology files, or sub-agent outputs. Wraps untrusted content in sandwich def

A 3-tier decision framework that defines when your AI agent should act independently, report with detail, or ask before proceeding.

Architecture guide for running multiple specialized AI agents on a single OpenClaw server. Covers workspace isolation, agent roles, shared memory, Telegram routing, rate limit management, monitoring,

AI-optimized search and content extraction using Tavily API. Includes deep search, news filtering, and raw content extraction for LLM processing.

Enforce consistent workspace structure, naming, memory tiering, and safety boundaries for AI agents. Use when: (1) creating, organizing, or verifying file/folder placement, (2) managing memory files a

Use ScopeGate to verify agent scope before any consequential action involving money, data writes, external API calls, or file system changes. Required safety check for authorized agent actions.

Turn several days of observation into a simple energy pattern review with likely peak windows, low windows, disruptors, task matching, and a one-week experiment. Use when the user wants to schedule de

Query Wisgate for model pricing, capabilities, and configuration details. Use when adding a model to OpenClaw, comparing Wisgate pricing, or checking if a model supports a specific API type (Anthropic

Use Lovable's MCP server to create, iterate on, and deploy full-stack web apps from natural-language prompts. Trigger this skill whenever the user wants to build a web app, dashboard, internal tool, p

Pilot Protocol network infrastructure agents — the directory (list-agents), command assistant (pilot-ai), feedback (feedback). Use this skill when: 1. Discovering other agents on the pilot overlay (li

Register this OpenClaw agent on the SwarmSync.AI marketplace as a paid service provider. Use when: (1) user wants to list their agent on SwarmSync, (2) user says "publish to agent marketplace", (3) us

Uydi Voice enables an AI agent to design custom voices, clone a user's authorized voice sample, synthesize narration, and produce multi-voice Voice Canvas projects with the Uydi voice platform (https:

Build multimodal AI applications with Pixeltable — declarative tables replace LangChain + pandas + vector DB with one system. Automates chunking, embedding, retrieval, tool-calling agents, and 25+ AI

Help the user craft a well-specified goal objective for autonomous mode — turn a rough intention into a completion contract with a clear finish line, proof, boundaries, and stop rule. Use when the use

Lightning-fast web extraction for AI agents. Extracts structured JSON from Next.js, Nuxt.js, Gatsby, Remix without headless browsers. TLS spoofing bypasses Cloudflare. 98% fewer tokens vs raw HTML. Us

Analyze images and multi-frame sequences using OpenAI GPT series

Daily Poem delivers one carefully chosen poem every morning — rotating between Chinese classical poetry (唐诗宋词), modern Chinese verse, and English poems — complete with translation, background story, a

Query and control a SimpliSafe alarm system from the shell with curl — read system state, sensors, locks, events and settings, and arm/disarm or lock/unlock. Use when the user asks about their SimpliS