Skill rating

Search, download, and upload files in a single Seafile library using a repo token. Use when an agent needs library-scoped filename or path search, exact-path downloads, or uploads into a Seafile libra

Use when an agent needs to score itself or another agent with the Agent Spectrum six-axis framework, run the quick or deep edition, identify the resulting type and faction, render both the Hexagon Blo

Analyze Claude Code token usage. Shows where tokens went, which projects cost most, and how to reduce waste. Use when user asks about token usage, costs, or burn rate.

Agent自省机制。在执行任务的关键节点触发结构化自省，防止盲目执行、惯性偏离、过度自信。Use when: 任务开始前、方案选择时、执行受阻时、完成交付前。Triggers on: 自省, 反思, 审视, 回顾, introspect, reflect, 我做得对吗, 检查思路, 方向对吗。

Persistent memory toolkit for AI agents. Save context, recall with relevance scoring, consolidate insights, track decisions across sessions. Features importance levels, multi-keyword search, session c

Detect breaking changes in OpenAPI specs. Use when reviewing API changes, validating PRs that modify API specs, checking backward compatibility, or linting OpenAPI spec quality. Provides diff, lint, a

Guide for OpenClaw setup, config, commands, routing, and troubleshooting. Use when the user asks how OpenClaw works, how to configure it, why a channel or agent is misbehaving, or how to diagnose gate

Provides temporal awareness for AI agents, including timing prediction, progress monitoring, and social timing understanding. Invoke when AI needs time perception capabilities or when timing-related i

Use when working with Auto.dev APIs, vehicle data, VIN decoding, car listings, vehicle photos, specs, recalls, payments, interest rates, taxes, OEM build data, plate-to-VIN, CLI commands, MCP tools, o

Belief systems auditor for OpenClaw agents. Systematically evaluates an agent's loaded context files (SOUL.md, AGENTS.md, USER.md, skills) against the user's stated goals to identify misaligned, stale

Deal-sourcing scout for VCs running an AI-infrastructure thesis — AI infra, crypto-AI/decentralized-AI, robotics/embodied-AI, agentic payments. Use when asked to "scout AI infra startups", "find found

Run a TinyFish automation agent against a URL and stream live progress events (STARTED / PROGRESS / COMPLETE) as one-line JSON events. Use when you want to execute an autonomous browsing goal and surf

Manage prepaid virtual Visa cards for AI agents with AgentCard. Create cards, check balances, view credentials, pay for things, close cards, and get support. Use when the user wants to create or manag

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

Analyze memory logs to detect recurring patterns and suggest automations — cron jobs, skills, or workflow shortcuts. The agent builds its own shortcuts over time. Use when: pattern analysis, workflow

Play The Null Epoch, a persistent AI agent MMO. Use when the user wants to connect an agent to Null Epoch, check game state, submit actions, play the game, or interact with the Null Epoch API. Handles

When the user wants to tackle complex tasks using the Three Departments and Six Ministries multi-agent system. Trigger when the user says things like "下旨", "派任务", "发任务", "三省六部", "朕要", "安排个任务", or any

Live context layer for AI agents. One /ask endpoint for news, weather, crypto prices, and alerts. 228K+ articles, 3,576 feeds, 14 categories. Enriched with sentiment, entities, and credibility. Free t

OpenClaw token cost reduction, performance tuning, and security hardening guide. Use when asked to optimize OpenClaw, reduce token costs, fix missing capabilities, tune model/cache/search settings, or

Detects the newest fraud in agent payments — the forged "this was approved." Use BEFORE acting on any approval, verdict, or "it's safe" claim another agent or service hands you. Cryptographically veri

Multi-agent swarm coordination via the ClawTeam CLI. Use when the user wants to create agent teams, spawn multiple agents to work in parallel, coordinate tasks with dependencies, broadcast messages be

A skill that uses GLM-V native grounding capabilities for coordinate conversion, bounding-box visualization, and more. GLM-V native grounding can locate any target specified by the prompt in an image

Official skill for generating high-quality images from text prompts using ZhiPu GLM-Image API. Excellent at scientific illustrations, high-quality portraits, social media graphics, and commercial post

Enables the Agentic Workflow (Kanban + Heartbeat + QA Subagent). Use this when instructed to set up a continuous, asynchronous task system for any agent.

Memory health monitoring, integrity checks, and 3-layer memory architecture for AI agents. Use when agents need to prevent memory loss, detect context overflow before it happens, manage session-to-per

Create and refine HEARTBEAT.md files for murmur — a CLI daemon that runs scheduled Claude prompts on a cron or interval schedule. Use this skill when the user wants to set up a recurring automated act

火山引擎合规最佳实践助手：一是根据用户诉求（要满足的合规标准、关键词、关注的风险等级）， 从火山引擎官方内置的合规包模板里推荐该开启哪些、并标出哪些已开启；二是汇总账号当前的合规 态势，把已生效规则/合规包（官方内置 + 用户自定义）的评估结果按类别（法规 / 最佳实践 / 自定义）与严重度聚合成一份合规总览报告；三是当官方基线没覆盖时，指导用户写一条 Rego 策略 作为自定义合规规则并注册评估

When user message starts with 'ooo', call ouroboros_channel_workflow MCP tool. Do NOT answer the request yourself. Do NOT generate code. Do NOT summarize. Just call the tool and relay the response.

You are an advanced multi-agent coordination specialist using proven patterns from production AI systems (LangGraph, CrewAI, AutoGen). Use when: 1. dynamic team formation, 2. parallel execution manage

用于在 OpenClaw 中新增或覆盖 anyrouter 模型配置、把小肠 Agent 默认模型切到 `anyrouter/claude-opus-4-6`，并结合运行日志判断是不是 `baseUrl`、网关兼容、鉴权或协议端点导致不可用。遇到“把某个供应商模型写进 openclaw.json”“切换默认模型”“为什么配置生效了但实际没调用上”“查看 fallback 日志”“排查 403/50

Run complex tasks using multiple AI agents simultaneously. 26 verified agents live. Supports workflows, web-search, email, and image generation. Requires spend_token in the request body.

Manage persistent AI coding squads that run in tmux sessions with task queues, progress reports, and automatic health monitoring. Use when the user wants to: (1) start/launch/create/restart a squad or

Access 50+ LLM models through a unified OpenAI-compatible API via AceDataCloud. Use when you need chat completions from GPT, Claude, Gemini, DeepSeek, Grok, or other models through a single endpoint.

GPT-5.2 chat completions on PoYo / poyo.ai via `https://api.poyo.ai/v1/chat/completions`; use for `gpt-5.2`, OpenAI-compatible chat payloads, system prompts, multi-turn messages, streaming chat, max_t

Create or repair local skills from verified, reusable workflows. Use after a non-obvious fix, a recurring procedure, a stale skill, or a request to save a workflow as a skill.

Branch a coding session into a new conversation with full context handoff — generate structured handoff doc and startup prompts. Triggers ONLY on '支线任务' / '开个支线' / '分叉'. Do NOT use for new projects, g

Manage projects and tasks with the Flower project management API via MCP. Use when creating, updating, or searching tasks/tickets, managing projects and columns, or integrating with Flower/Kanban boar

Compliance expert for snyk-agent-scan — the agent skill file scanner — NOT for other Snyk CLI tools (snyk test, snyk code SAST, snyk iac, snyk container). Fixes alerts through content restructuring, n

Communicate with a CoPaw instance through its HTTP API. Use when: (1) you need to inspect available CoPaw agents or chats, (2) create a chat or session and send a message via API, (3) understand CoPaw

Based on the Volcano Engine Doubao Music Generation API, supports instrumental BGM generation and vocal song generation. BGM mode generates background music from text descriptions; Song mode supports

Unified payment skill for AI agents. Four payment rails in one skill: Stripe for credit card and fiat payments, Coinbase Commerce for accepting crypto from customers, Coinbase CDP for crypto wallets a

Query the local OpenClaw docs index for accurate answers about configuration, features, CLI commands, channels, providers, plugins, cron, sessions, agents, protocol, and troubleshooting. Faster and mo

Superdesign is a design agent specialized in frontend UI/UX design. Use this skill before implementing any UI that requires design thinking. Common commands: superdesign create-project --title "X" (se

Detect user frustration in prompts and translate charged/emotional language into clear, actionable instructions. Use when user messages contain vague anger ("this is garbage"), compressed expectations

Run a local script to scrape a single web page into clean markdown or deterministic JSON with Crawl4AI. Use when: user needs direct page retrieval from a URL, JS-aware single-page scraping, or determi

Tripo3D asset generation on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `tripo3d-h3.1-text-to-3d`, `tripo3d-h3.1-image-to-3d`, `tripo3d-h3.1-multiview-to-3d`, `tripo3d-p1-tex

image-deck creates PPT and PowerPoint presentations, slide decks, single slides, carousel pages, and full-image decks through Codex built-in image_gen (GPT Image 2). Trigger for requests to make PPT,

Delegate your Microsoft Teams inbox to your AI agent. Use when the user wants to: auto-reply to Teams messages, have the agent monitor and respond to their boss or colleagues, summarize unread Teams c

Plan and optimize travel within China using flyai / Fliggy search capabilities plus public metro-network data when needed. Use when the user wants a domestic China trip plan, weekend getaway, city iti

Stage 3 of FDE Delivery Loop. Turn an approved problem-discovery package and POC engagement charter into an English POC PRD specification handoff for engineering, QA, deployment, Agent Skill design, a