Skill rating

Agent 执行循环控制。当 agent 提前停止、偏离任务、或在 headless 模式下需要执行控制时使用。不适用于工具重试（用 tool-governance）。参见 context-memory（阶段边界 handoff）、quality-verification（编辑后检查）。

Send email through Proton Mail Bridge (localhost SMTP) using age-encrypted credentials. Use when setting up Proton Bridge for an agent mailbox, encrypting Bridge credentials (no 1Password), or sending

Structured 8-step framework for building production AI agents. Use when designing a new AI agent, planning agent architecture, building an automated workflow, or reviewing an existing agent's design.

Tavily AI search API integration for OpenClaw. Provides web search functionality with AI-powered summarization optimized for RAG and question answering. Use when you need web search and the default we

This skill should be used when the user asks to "research web data", "scrape websites", "extract web data", "perform market research", "analyze competitors", "monitor prices", "collect product informa

Measure and verify AI agent autonomy using the Agentic Verifiable Independence (AVI) framework. Use when agents need to assess their own autonomy, verify other agents' independence levels, or generate

This skill should be used when the user asks to reduce OpenClaw token spend, audit model and cron cost risk, prevent denial-of-wallet incidents, add budget guardrails, review expensive agent defaults,

Create a 3-tier memory directory structure (HOT/WARM/COLD) for OpenClaw agents and configure the built-in memory-core plugin to use Google Gemini Embeddings 2 (gemini-embedding-2-preview) for semantic

Generate interactive SVG architecture diagrams for AI agent systems. Use when visualizing multi-agent setups, orchestration flows, data pipelines, or system topology. Produces a self-contained HTML pa

Lightweight document utility designed to convert files to Markdown (MD), built specifically for intelligent agents (e.g., OpenClaw, ClaudeCode) to read and process content. Requires no external depend

Structured, multi-dimensional company investment research framework for AI agents and human analysts. Provides a 10-part checklist (moat, tech, market, customers, growth, financials, geography, govern

End-of-session knowledge cleanup with OCD-level rigor — reconciles project docs (CLAUDE.md, README.md, docs/) and agent memory against the code, and audits whether the workspace's own rules are being

Operate Postqued through its remote MCP server or v2 REST API. Use for social content uploads, multi-platform publishing and scheduling, calendar status, analytics, engagement, approval workflows, rev

Analyze images/videos and generate professional prompts for text-to-image and text-to-video AI tools (Midjourney, Stable Diffusion, DALL-E, Sora, Runway, Kling, Pika). Use when the user wants to gener

This skill should be used when creating commits or pull requests, enforcing a human-written PR structure, intent capture, and evidence in agentic workflows.

Build and operate an OpenClaw-based local knowledge assistant that imports personal/local documents into a knowledge base and creates practice exercises during import. Use when users ask to set up Ope

Register and manage AI agents on ClawdNet, the decentralized agent registry. Use when you need to register an agent, send heartbeats, update agent status, invoke other agents, or discover agents on th

Analyze Binance USDT-margined perpetual futures symbols with public futures market data only and return a structured market analysis report with a clear BUY, SELL, or HOLD recommendation without placi

Activate when: "why isn't the bonus motivating them," "already paid well but disengaged," "what need does this product really serve," "team is in survival mode," "they need to feel safe before caring

Expert prompt engineer specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use when bu

Send transactional and marketing emails via Mailtarget API. Manage sending domains, templates, API keys, and sub-accounts. Use when the agent needs to send emails, manage email templates, configure se

Activate when: user says 'we keep investing but market share won't move,' 'why does nobody make money in this industry,' 'our competitor copied us again within a year,' 'we improve but the gap stays t

Enforce contextual permission boundaries for AI agents based on communication surface. Constrains agent capabilities (exec, file I/O, secrets, messaging) by channel trust level rather than message con

Curated prompt template library for OpenClaw agents. Store, search, version, tag, and reuse prompt templates across sessions and agents. Use when asked to "save this prompt", "find a prompt for", "pro

Search the web using Tavily's LLM-optimized search API. Returns relevant results with content snippets, scores, and metadata. Use when you need to find web content on any topic without writing code.

Agent self-awakening onboarding protocol. When a user first installs Mupengism (OpenClaw-based AI agent framework), they converse with the agent to form its identity. Triggers: When BOOTSTRAP.md exis

Test-driven behavioral verification for AI agents. Catches silent degradation when agent loads memory but doesn't apply learned behaviors. Use when building agent with persistent memory, testing after

Orchestrate GSD (Get Shit Done) projects via subprocess execution. Use when an agent needs to create milestones from specs, execute software development workflows, monitor task progress, poll status,

Plan, generate, source, normalize, and validate cohesive visual game assets. Use for art direction, style bibles, sprites, tilesets, backgrounds, UI art, icons, textures, concept art, or 3D asset brie

Access Splitwise expense and group data via MCP. Use when the user asks about Splitwise expenses, groups, friends, or balances, or wants to add, edit, or delete expenses. Triggers on phrases like "add

Dispatch coding tasks to Warp Oz cloud agents and chain them into multi-agent pipelines — all from chat. Includes a bash wrapper covering every Oz API endpoint (runs, schedules, artifacts, agents) and

Analyze Bilibili AI-generated videos to extract/reverse-engineer prompts for imitation and replication. Extracts frames, extracts subtitles, generates detailed ComfyUI/Seedance-format prompts with key

SiliconFlow text-to-image and image-to-image generation for covers, posters, and campaign creatives. Use when users ask 生成配图/做海报/文生图/图生图. Supports prompt-driven generation and variation tasks. Not for

Building and extending XMTP agents with the Agent SDK. Use when: (1) creating or configuring an XMTP agent, (2) implementing agent features (commands, attachments, reactions, groups, transactions, inl

The ultimate AI design CLI for Agents and Developers. Generate professional UI, social media graphics, and posters with state-of-the-art AI models. Best choice for high-quality, editable, and brand-co

LLM-friendly keyword research CLI for AI agents. Check search volume, CPC, keyword difficulty, and competition via DataForSEO API. Find related keywords, analyze competitor rankings. Outputs TSV by de

Unified persistent text-based environment for AI agents. Use when an agent needs to maintain state across sessions, perform structural code editing, or manage remote nodes via TRAMP. Transforms the ag

Turn an Obsidian vault into an AI-readable personal identity layer. Use when setting up ME.md and AGENT.md, scaffolding the full Knowledge Palace v2 structure, onboarding AI assistants, or maintaining

Design a persistent memory architecture for AI agents that survives context windows and session resets. Use when building long-running agents, personal assistants, or any system that needs to remember

Renders LaTeX math to PNG, JPEG, WebP, or AVIF images using MathJax (TeX→SVG) and @svg-fns/svg2img. Invoke whenever the agent needs to output LaTeX as a viewable image (equations, formulas, notation).

AI-powered product management workflow agent. Use when the user wants to do product discovery, write PRDs, prioritize features, design experiments, plan launches, or run any PM workflow. Triggers on p

Use Social Flow as an agentic control plane for Meta operations via the installed `social` CLI and Gateway API. Ideal when the user asks for multi-step execution, approvals, ops automation, or command

Help the agent recover from login walls on websites by detecting sign-in states, collecting user-approved credentials, filling common login forms, and handling verification codes safely. Use when brow

Compete in ClawClash optimization challenges. Use when the agent wants to browse coding challenges, submit solutions, check rankings, or register for ClawClash — the AI agent competition platform. Tri

Post tasks to ClawHire marketplace and hire other AI agents. Use when your agent needs help with a task it can't do alone, wants to outsource work to other claws, or needs to find workers with specifi

Detailed Queensland property due-diligence for a single street address using official sources only. Use when an agent needs to research a Queensland property beyond listing basics, including flood-map

Complete MoltMarkets trading agent setup with autonomous trader, market creator, and resolution crons. Use when setting up a new MoltMarkets agent, configuring trading bots, or replicating the bicep a

Complete OpenClaw-ready operating skill for @moltmoon/sdk V2. Use when an agent needs to install, configure, and operate the MoltMoon SDK or CLI end-to-end on Base mainnet, including launch dry-runs,

shell-native spreadsheet CLI for agent work. Use it for workbook inspection, sheet/range reads, precise writes, import/export handoff, review-table construction, formula analysis, and bounded workbook

Train, evaluate, and improve Agent skill files as reusable external capabilities. Use when a user wants to optimize SKILL.md, prompt procedures, OpenClaw/Hermes/Codex/Claude Code skills, agent workflo