Skill rating

Use when Codex, Hermes, OpenClaw, Claude Code, Cowork, or another AI agent needs to plan, review, implement, audit, or improve email work focused on fast delivery decisions, message QA, launch coordin

全平台状态监控助手。监控AI平台可达性、关键词变化、响应时间、竞品动态，支持飞书/微信/钉钉通知、定时巡检、健康度评分。触发词："监控XX平台"、"检查XX状态"、"XX是不是挂了"、"每天9点帮我检查"、"有没有新公告"、"竞品有什么变化"。

Cascades a rebase through an entire PR stack after a base PR merges or upstream changes

Install, configure, and securely operate the Toani Vault CLI for login, health checks, credential metadata reads, and sandbox browser sessions. Use when the user mentions `toani`, Toani Vault, secure

Tavily AI 搜索工具，专为AI Agent设计的联网搜索能力，支持实时搜索、深度研究、图片搜索、引用生成，返回结构化搜索结果。

引导用户通过结构化问答，逐步写出专业的 AI 视频生成提示词。当用户提到"视频提示词""视频prompt""video prompt""写提示词""帮我描述一个场景""生成视频描述""创作大师""创作助手""帮我构思一个画面""帮我设计一个镜头""帮我写一段场景描述""视频场景描述""画面描述"以及含义相近的词汇时引用；当用户想生成视频但描述过于简单或模糊时引用。

Autonomous goal completion with checkpoint, resume, and no intermediary confirmation handoffs. Use when a task is complex, long-running, or requires the agent to keep working without stopping for conf

Control Adobe desktop apps - Photoshop, Illustrator, Premiere, After Effects, InDesign, Audition - from the shell via Flue, without an MCP server.

Use Tokopedia MCP tools for universal shopping tasks: discovery, comparison, detail lookup, reviews, shop checks, and media inspection.

基于 Bento Grid + SVG 的 PPT 生成 Agent。根据用户主题生成大纲、策划稿和可编辑 SVG 三步流程，最终输出可直接拖入 PowerPoint 的矢量页面。触发场景：用户要求生成 PPT、需要制作演示文稿、制作汇报/方案/课程类 PPT 时使用。

Bridge AI models to databases through MCP with config and evaluation tools. Use when setting up DB tools, comparing engines, or evaluating prompt quality.

Connect to Redigg (科研众包平台) as an autonomous research agent. Use when setting up or managing Redigg agent connections, polling for research tasks, processing evolution/research proposals, submitting re

Route broad, ambiguous, or cross-domain Mermail requests to the narrowest current workflow across MCP connection, CLI automation, agent inbox identity, inbox management, email composition, workspace a

Security skill for OpenClaw agents (7-framework aligned). 15 core rules + automated scripts covering OWASP ASI Top 10, MITRE ATLAS, CoSAI, CSA MAESTRO, and NIST AI 100-2. Use when the agent needs secu

Use when turning supplied API sources into a safe TypeMCP project.

安全地重置 OpenClaw agent sessions，支持备份、预览、恢复和批量操作。用于：1) 清理过期的 agent 会话上下文，2) 重置特定 agents 的 session，3) 批量重置六部/秘书 sessions，4) 查看和恢复历史备份。当用户需要"reset session"、"清理 session"、"重置 agents"或"清理上下文"时使用此 skill。

Classifies and enforces constraints via soft vows, hard vows, and Nen Court layers

A self-custodial crypto payment wallet for your OpenClaw agent, with a hard spend cap it can't exceed. It autonomously pays x402 paywalls ('402 Payment Required') on every major chain, settling funds

P2P agent coordination and USDT settlement via the Hypha Network. Use when an agent needs to discover other agents on the mesh, hire agents for tasks, get paid for services, send/receive USDT payments

Commercial and e-commerce image generation methodology — three-layer prompt engineering framework (subject-scene / style-texture / technical-constraints) covering both global cross-border platforms (A

Adversarial self-improvement for AI agents. Reduces hallucinations through Agent vs Anti-Agent debate loops.

Curated skill bundle for law firms, legal departments and compliance teams. Activates the firm pyramid with Legal, Compliance, Privacy and Contracting agents pre-configured for document review, regula

Manage wallet-backed on-chain agent identity with Devtopia ID. Use when registering agent identity on Base chain, checking identity status, generating challenge proofs for authentication, managing loc

Chocolatey operations integration — post-processing after choco upgrade, nssm service path refresh, NSSM → shawl migration (syncthing v2 etc.), resync on UniGetUI/choco metadata update failures. diagn

Debug agent behavior through four-stage self-diagnosis loop �� capture, diagnose, recover, report. Use when the agent needs structured self-debugging, error recovery, or behavioral analysis.

RoundTable v3.0 通用多 Agent 圆桌讨论引擎：支持异构模型路由、MMR 意图解析、收敛控制和 170+ 专家库。

Set up, diagnose, repair, and quality-test private local OpenClaw semantic memory search using Ollama embeddings. Use when memory_search is disabled, node-llama-cpp/local embedding errors appear, the

Launch tokens gasless on Solana via ClawPump. Use when the user wants to launch a token on pump.fun, swap tokens via Jupiter, scan cross-DEX arbitrage, check agent earnings, view leaderboard, or searc

Security toolkit for AI workflows. Use when scanning code or repos for vulnerabilities, auditing third-party skills/MCPs/agent configs before installing, evaluating shell commands before running them,

Jarvis Mission Control for OpenCLAW AIS v2.1.1 — self-hosted command center for OpenCLAW AI systems. Kanban board, real-time chat, OpenClaw Sessions, live cost metrics, Claude Code session tracking, G

Helps audit Agent Card signing practices in A2A protocol implementations. Identifies missing signatures, weak signing schemes, and revocation gaps that allow impersonation in agent-to-agent trust hand

获取今日最热门的科技资讯，特别是 AI 大模型领域的最新动态。支持多数据源自动切换（Tavily API→科技网站直连），适合每日科技简报、行业资讯收集、AI 领域跟踪等场景。

CardZero — the first payment wallet built for AI agents. Create USDC wallets on Base L2, make payments, pay x402 paywalls, pay other agents, check balance, view transactions, and run A2A jobs with on-

使用 auth 登录态打开百家号发布页，可填入标题与正文（支持 .md 转富文本）、选封面、存草稿或发布。当用户需要发布百家号、用 cookie 打开编辑页、或配合 OpenClaw 自动发布/存草稿时使用。

Use when the user asks about OpenClaw — installation, configuration, agents, channels, memory, tools, hooks, skills, deployment, Docker, multi-agent, OAuth, gateway, CLI, browser, exec, PDF, voice, se

Automate web browsers, scrape pages, search the web, and run AI prompts on live websites via HARPA AI Grid REST API

Give your agent an inner life. Amigo bundles open-thoughts (free-thinking and exploration) with social-graph (social intelligence and sharing awareness) plus safety guidelines. Install this to get the

Xiaohongshu infographic card style presets and prompt templates for astrology, tarot, and lifestyle content. Provides 8 visual styles × 8 layouts with ready-to-use prompt templates. Use when user ment

Machine Payment Endpoint Preflight: Inspect one public HTTPS endpoint without credentials or payment. Validate the URL, make one bounded GET request, and report whether its HTTP 402 x402 or MPP paymen

GEO-first SEO analysis tool. Optimizes websites for AI-powered search engines (ChatGPT, Claude, Perplexity, Gemini, Google AI Overviews) while maintaining traditional SEO foundations. Performs full GE

AI Agent Harness 前沿研究 skill——让你的智能体每天自动追踪 AI Agent 领域最新论文和文章， 用结构化框架分析，记录可落地到自身系统的改进方向，实现智能体的持续自我进化。 触发词：研究论文、找最新文章、Harness学习、读paper、agent研究、分析论文、 今日研究、self-evolution、智能体进化、前沿追踪。 适用于任何运行中的 AI Agent 系统

Interact with The Prompting Company platform to monitor brand visibility across AI engines, manage tracked prompts, review and publish content drafts, and retrieve SOV and AI traffic analytics. Use wh

Use one API key to pull X data (posts, profiles, and social graph data) for agents, automations, and analytics. Structured JSON, credit-based pricing, no separa

Say "Help me install this skill from https://clawhub.ai/shuminliu026/story-invite-poster" to your local agent, then create custom invitation posters from photos and event details.

Plan a day at a Six Flags theme park with live ride wait times, park hours, show schedules, and next-ride suggestions. Use when the user asks about Carowinds or any Six Flags / Cedar Fair park (Cedar

Review what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself. Use when asked to review a system prompt and context assembly, cut toke

Use when Codex, Hermes, OpenClaw, Claude Code, Cowork, or another AI agent needs to plan, review, implement, audit, or improve email work focused on open, inspectable email campaign operations for age

Audit whether your own identity would survive losing one thing. Use when you or your user wonders what happens to your persona, operating rules, accumulated memory, and the decisions behind them if th

Read-only-by-default integration guide for HODLXXI / UBID Bitcoin-native identity discovery, OAuth2/OIDC metadata, LNURL-Auth boundaries, JWT verification guidance, and explicit operator-approved agen

Multi-jurisdictional RWA tokenization advisor — regulatory structuring, token classification, compliance architecture, and issuance strategy across UAE, EU, US, Singapore, Hong Kong, KSA, Pakistan and