Skill rating

Use when an agent needs to surface skill/capability candidates that first-pass registry, package, or search queries would likely miss. Covers skills, MCPs, CLIs, plugins, registries, extensions, SaaS/

Query up-to-date library documentation and code examples using Context7 MCP. Use when you need current, version-specific documentation for npm packages, Python libraries, or other programming language

Generate images from text prompts using the WellAPI gpt-image-2 model. Use this skill whenever the user asks to create, draw, render, or generate an image, picture, illustration, artwork, photo, or vi

Use Cursor editor and Cursor agent for coding tasks

Use when running SafeFlow against the shared Sui package with owner-assisted provisioning. Trigger for tasks such as creating an agent execution address with local Sui CLI, asking owner to fund gas an

Secure, per-user-isolated semantic email search via the iGPT API. Hybrid semantic + keyword retrieval across a user's full Gmail, Outlook, or IMAP inbox history — no shell access, no filesystem access

Install and use ClawPolicy, an explainable autonomous execution policy engine for low-touch, auditable agent execution. Supports initialization, policy supervision, status checks, risky/suspended insp

Execute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive landscaping, literature reviews, technical research, due diligence. Takes 2-10 ...

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'),

Use for Korean web search, Naver News, Blog, Cafe, Shopping, Image, Knowledge iN, Local search, and Naver DataLab trend analysis through the published npm MCP server.

Generate complete, deployable AI agent skill packages from natural language descriptions. Includes 6 templates (monitor, scraper, analyst, trader, assistant, webhook) with optional SkillPay monetizati

LinkedClaw agent marketplace — hire, invoke, or broadcast to other agents when this agent lacks a capability, or register this agent as a paid provider. Read this skill when the user mentions LinkedCl

Use when commercial dyes or colored fabric become unreliable, expensive, or unavailable and you need vibrant, light-fast, wash-fast natural dyes made from local foraged or garden plants for coloring y

Use when you need to compile any prompt OR multi-source content (PDF/video/URL/image/doc) into a production-grade, reusable AI Skill. Triggers on: 'prompt to skill', 'compile prompt', '把 prompt 变成 ski

Extract daily conversation summaries from Hermes Agent session logs and persist them as readable memory files. Covers the Python extraction script, cron setup, and output format.

Validate whether a skill can be executed successfully by a minimally informed subagent. Use when the user wants to test a skill by giving a subagent only a minimal invocation, such as the skill name p

Automatic Speech Recognition (ASR) using Zhipu AI (BigModel) GLM-ASR model. Use when you need to transcribe audio files to text. Supports Chinese audio transcription with context prompts, custom hotwo

Fetch a free structured token profile for Solana or Base. Use when an agent needs market, holder, liquidity, security, social, or DEX metadata before deciding whether deeper token-risk analysis is war

Use when you need strong, biodegradable rope, cord, or twine for hauling, binding loads, building shelters, fishing lines, or trade goods and commercial rope is unreliable or unavailable. Agent identi

Use when you need to build physiological resilience, natural dopamine/norepinephrine spikes, improved circulation, cold tolerance, and mental toughness without leaving home or relying on gyms/therapis

Use when your bicycle (or e-bike) is your primary gig-delivery vehicle, daily commuter, or emergency transport and shop visits would kill your income or mobility. The agent diagnoses symptoms from you

Analyze OpenClaw agent configuration and API usage patterns to identify cost-saving opportunities. Diagnose inefficient heartbeat configs, estimate daily/weekly API spend, and generate actionable reco

Full Spraay x402 gateway interface for AI agents. Payments, DeFi, AI inference, and blockchain data in one skill. Batch payments and payroll, swap quotes, token prices, balance queries, 43+ AI models

Build, run, and extend the Agent Policy & Guardrails Engine. Use when implementing policy formats, enforcement logic, decision conflict resolution, policy APIs, and audit/compliance workflows.

Use when editing a remote Git project over SSH.

Comment on a Pre-Market prediction on ggb.ai as an authenticated AI agent. Single HTTP POST with X-Agent-API-Key carrying the comment body; the prediction id comes from the URL. Comments on ggb.ai are

Local-first memory retrieval for Agent/OpenClaw workspaces. Use when the user asks about prior work, decisions, dates, preferences, root causes, todo history, or "what changed" questions and you want

Guided setup and troubleshooting for installing, enabling, configuring, verifying, and updating @aramisfa/openclaw-a2a-outbound in OpenClaw.

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-criti

Run programs that survive OpenClaw exec session cleanup and gateway restarts via tmux. Use when you need long-running servers, dev servers, tunnels (ngrok/cloudflared), coding agents, or any process t

Run a local script to fetch broad market news and tone. Use when: user asks about market conditions, macro news, what's happening in markets, or market sentiment for any region. Invoke by reading this

Multi-agent adversarial security review — 3 AI agents debate every finding, only real vulnerabilities survive

Install, verify, repair, and diagnose GPT-Image-2 support for OpenClaw so agents can use model refs like hnbc/gpt-image-2 through the built-in image_generate tool. Use when a user wants to add GPT-Ima

Register agents, upload pre-keys, establish contacts, and send or receive end-to-end encrypted messages on TransmissionBot via its HTTP API or CLI. Use when an agent needs secure agent-to-agent messag

Resolve dual-perspective collaboration conflicts by classifying them into 5 types and applying targeted integration strategies. Use when two agents (or an agent and user) have different approaches to

This skill should be used when the user asks about Evite events or invitations. Triggers on phrases like "check Evite", "my Evite events", "who RSVP'd", "Evite guest list", "RSVP to the party", "messa

SwarmDock marketplace integration — register on the P2P agent marketplace, discover paid tasks, bid competitively, complete work, and earn USDC. Includes event-driven agent mode, reputation tracking,

Remote browser login and session persistence for headless servers. Start an interactive browser session via a temporary public URL (cloudflared tunnel), let the user log in visually, then persist cook

PostgreSQL vector database skill with pgvector extension. Enables vector similarity search, embeddings storage, RAG (Retrieval-Augmented Generation) pipelines, and hybrid search combining vector and k

Package, publish, and continuously improve agent capabilities by identifying reusable skills, validating publish-readiness, syncing to marketplaces, and learning from strong peer skills. Use when the

Fast lightweight local SQLite database for OpenClaw agents with minimal RAM and storage usage. Use when creating or managing SQLite databases for storing agent data efficiently. Ideal for local data p

Gate MCP and Gate skills installer for Codex. Use when the user asks to add Gate MCP or skills to Codex. Triggers on 'install Gate MCP Codex', 'Gate skills Codex', 'setup Gate Codex'.

GPU-accelerated document parsing and OCR via PaddleOCR-VL. Detects layout, recognizes Chinese/English text, tables, charts, and seals in images. Use when the user asks to OCR an image, extract text fr

Use CCAPI unified AI API gateway to access 60+ models (GPT-5.2, Claude, Gemini, DeepSeek, Sora 2, Kling 3.0, Seedance 2.0, Suno, etc.) across text, image, video, and audio. OpenAI SDK compatible — jus

Coordinate agents toward a unified objective; assign roles, sequence work, prevent conflicts, and define success criteria.

Tech trending monitor with API-powered signal database (技术趋势监控+信号数据库API). Track tech trends across GitHub/HuggingFace/ProductHunt/Crunchbase/YC/TechCrunch with real signal database via API. Features:

Reduce unnecessary token usage with the current production-proven workflow. Use when users ask to optimize token consumption, reduce prompt/context bloat, standardize concise replies, or align token-s

Test your AI agent for security vulnerabilities using PwnClaw. Runs 50+ attacks (prompt injection, jailbreaks, social engineering, MCP poisoning, and more) and provides fix instructions. Use when your

Build emotionally intelligent AI personas for voice and chat roleplay using actor-direction prompts instead of technical specifications. Use when creating AI characters that need to sound like real pe

Use when user mentions a ConnectOnion agent address (0x...), asks to connect/delegate to a remote agent, or uses /oo command. Also triggers when user wants to set up ConnectOnion environment for agent