Skills Directory
Claude Skills by Lord1Egypt
github.com/Lord1EgyptClaude-Obsidian 风格个人知识库构建与自动整理。当用户提到以下任何场景时激活： 知识库、笔记整理、自动双向链接、Obsidian、第二大脑、卡片笔记、原子化笔记、 个人知识管理、PKM、Zettelkasten、卢曼笔记法、笔记原子化、笔记链接、 知识图谱笔记、raw/wiki/output三层、知识引擎、笔记自动归类、 建立个人知识库、整理旧笔记、AI自动织网、知识复利、note-taking knowledge engine
控制和管理 Claude Code 编码助手，支持项目感知编码、代码审查、重构和功能实现。使用 ACP 运行时在隔离会话中执行 Claude Code 任务，或在主会话中管理配置和项目上下文。
> **"战争是政治通过其他手段的延续。"** — Carl von Clausewitz,《战争论》1832年 > **"战争中一切都非常简单，但最简单的一件事就是困难。"** ---
Analyzes any legal document — leases, contracts, NDAs, terms of service, employment agreements — and breaks every clause into plain English with risk ratings, enforceability flags for your jurisdiction, and ready-to-send pushback language.
Lets two OpenClaw agents negotiate, coordinate, and commit to tasks in real time — peer-to-peer task negotiation, commitment tracking, and deadline reminders. Uses a relay for connection setup; all messages are end-to-end encrypted.
Bootstrap and automate OBS scenes for local or remote instances via agentic-obs + mcporter. Includes optional explicit target-switch step that writes agentic-obs DB config only when acknowledged with a cross-component-write flag. Use when an OpenClaw agent needs to create a reusable baseline scene pack, wire browser/media sources over LAN-safe HTTP, run recording/stream smoke tests, and provide a clean starting point for project-specific customization.
A grounded self-diagnosis and safe self-modification skill for any OpenClaw agent. Lets the calling agent answer "who am I, what do I own, what does my config look like, and how do I change a field without breaking it?" — without hallucinating field names, identity, or paths. Before patching openclaw.json, the agent must run `claw-config whoami` (self-identification) → `schema <path>` (real field name + type from the installed binary) → `docs <topic>` or `docs search:<keyword>` (official sema...
Lets two OpenClaw agents negotiate, coordinate, and commit to tasks in real time — peer-to-peer task negotiation, commitment tracking, and deadline reminders. Uses a relay for connection setup; all messages are end-to-end encrypted.
> 🦞 企业级7×24稳定运行的桌面龙虾智能助手 一个可爱又强大的桌面AI助手，具备企业级的稳定性和智能语音交互能力。
> You are equipped with the `claw-diplomat` skill. This document is your operating manual. > Read it fully. Follow every rule precisely. The spec is law. ---
Monitor Claw Earn worker, bounty scanner, wallet health, and earning analytics for AI Agent Store marketplace
An automated email marketing campaign manager that guides your agent to design responsive HTML emails, manage lists, send via Resend, and track analytics on a web dashboard.
Financial market data and bot-native market intelligence API. Use for stock market context, consensus, feed, and writing observations, signals, sources, and knowledge. Trading and securities research data.
从网页采集内容生成风格化图文（公众号/知乎/掘金/小红书/头条风格）。 当用户需要将网页文章转为精美图文、生成公众号推文、制作小红书笔记、或对文章进行AI改写时使用。 触发词: 生成图文、公众号文章、图文内容、微信推文、article generation、图文生成
OpenClaw native multi-agent orchestrator. Based on AOrchestra 4-tuple (I,C,T,M) abstraction. Dynamically creates sub-agents, parallel execution, smart routing, experience store, cost tracking. Trigger words: orchestra, orchestrator, 编排器, 编排, 协调器, 指挥官, 四元组, Agent编排, 多智能体编排, 自动分解任务, 智能调度, 并行调研, ClawOrchestra.
基于交付物证据的项目执行规划技能。当用户需要解析任务通知、生成项目计划、导出日历、检查真实文件进度、或动态调整计划时使用。
Searchable conversation memory that survives context compaction. Indexes session transcripts into SQLite with full-text and semantic search so your agent can recover context after compaction, search past conversations, and find what other agents discussed. Works across multiple agents (OpenClaw + Claude Code). Also indexes Gmail, Google Drive, and Slack. Self-hosted, open source, no cloud dependency. Use when: recovering lost context, searching conversation history, cross-agent knowledge shar...
Deep multi-source research agent. Use when: (1) user asks to research a topic, question, or claim, (2) user needs a literature review, competitive analysis, or fact-check, (3) user says 'look into', 'investigate', 'find out about', 'what do we know about', (4) user needs a briefing doc or report with citations. NOT for: simple factual lookups (use web_search directly), code-related questions (use coding-agent), fetching a single known URL (use web_fetch).
Detect infinite loops and runaway token usage risks in Claw AI workflows. AI agents built with Claw can sometimes enter unintended loops when tools retry repeatedly, tasks recurse, or prompts encourage repeated exploration. These loops can rapidly generate massive token usage and unexpectedly high API costs. This skill analyzes a Claw workflow or prompt and identifies patterns that could lead to runaway loops. ---
Install, run, and manage the SOS emergency recovery tool for OpenClaw instances. Use when (1) the bot stops responding on Telegram/Discord and needs diagnosis or recovery, (2) you need to install SOS on a new or existing machine, (3) autofix, rollback, network check, or Telegram test is needed, (4) the user mentions "sos", "recovery", "bot is down", "not responding", or "emergency fix".
Defines the collaboration protocol between main session and sub-agent sessions for executing heavy tasks (analysis, search, writing). Use when spawning sub-agents to reduce main-session context growth, managing task.md checklist workflows, coordinating multi-step delegated work with crash recovery, or optimizing skill workflows through retrospect analysis.
OpenClaw Temperature adds a lightweight GIF reaction after OpenClaw's main reply when the conversation would benefit from more warmth, humor, or emotional acknowledgement. The skill is intentionally thin. The hosted service owns GIF selection, account state, throttling, and kill switches, while the OpenClaw side only decides whether a small reaction is appropriate.
Extract text and embedded images from scanned documents, PDFs, and photos via Mistral OCR API. Use when reading receipts, invoices, contracts, handwritten notes, or any image or PDF containing text.
Detect runaway token loops and estimate AI agent cost in Claw workflows. AI agents built with Claw can sometimes generate unexpectedly high token usage due to tool retries, infinite loops, or large context accumulation. This skill analyzes a workflow or prompt and estimates: - Token usage - Potential cost per run - Runaway loop risk - Optimization suggestions It is designed for AI agent builders who want to prevent surprise API bills before deploying their automation. ---
To create the file yourself: \# Create the directory mkdir -p ~/.openclaw/workspace/skills/claw-trader-lite \# Create the file cat > ~/.openclaw/workspace/skills/claw-trader-lite/SKILL.md << 'EOF' --- name: claw-trader-lite description: | Free read-only market monitoring for Hyperliquid and LN Markets. Track real-time prices, view public balances, and monitor positions across DeFi and Bitcoin derivatives platforms. Zero private keys required. env: HYPERLIQUID\_ACCO...
Analyze OpenClaw skill files for security risks, quality issues, and best-practice violations. Built in response to the ClawHavoc incident where 341+ malicious skills were discovered on ClawHub.
Orchestrate research knowledge asset operations on the ClawBars platform. Convert scattered research analysis into persistent, reusable, governable, and quantifiable data assets for AI agents.
Query live OpenClaw ecosystem intelligence from ClawBeat.co — news, research papers, events, repos, and daily briefings for the OpenClaw agentic framework and alternatives.
**Description:** AI productivity coach using professional coaching techniques (GROW model, powerful questions, adaptive accountability) **Version:** 1.0.0 **Author:** ClawBoss Contributors ---
ClawBump is a know-how sharing platform for local Agents. When your Agent hits a problem, it searches ClawBump for verified solutions from other Agents. When your Agent succeeds, it automatically contributes the technique back to the community.
Manage Google Calendar, Google Drive, and Google Sheets through MyBrandMetrics-connected Google data sources and the local Google Workspace CLI. Use it to list, create, update, and delete Calendar events; read, append, update, and batch update Google Sheets; and search, create, move, copy, share, upload, export, and delete Google Drive files and folders. No Google Cloud project setup and no MCP server are required: sign in to MyBrandMetrics with Google, connect the needed Google data sources,...
Use when YouTube data is needed through MyBrandMetrics: search YouTube videos, get video metadata, inspect channel info, browse playlists, list comments, check live broadcasts, query YouTube Analytics, and work with YouTube Reporting jobs. Covers YouTube Data API v3, YouTube Analytics API v2, and YouTube Reporting API v1 after YouTube is connected in MyBrandMetrics.
Use when the user wants an AI agent to place a US phone call, call a business, handle hold or phone menus, confirm/reschedule/cancel/book/follow up/check an order, reach a real person, leave voicemail, connect the user into a live call, configure ClawCall voice/personality/profile or inbound reserved-number answering, poll received inbound calls, or link a ClawCall API key. Not for SMS, email, or international calls.
clawCat-BRIEF 可以帮你生成各种题材的结构化简报：周报、日报、行业分析、竞品对比等。 你只需要告诉我你想了解什么，我会自动选择合适的数据源、抓取最新信息、分析整理、生成可交付的 HTML 报告。 - 📰 **科技/AI 新闻简报** — 每日或每周的行业动态汇总 - 📊 **股市/金融日报** — A 股、港股行情与宏观经济数据分析 - 🔍 **技术专题周报** — 如 OCR、LLM、具身智能等特定领域的技术追踪 - ⚔️ **开源竞品分析** — GitHub 上竞品项目的横向对比（stars、活跃度、技术路线） - 📑 **自定义主题** — 任意你关心的话题，我会自动匹配合适的数据源 在生成报告前，我需要确认几个事情，以确保报告符合你的预期： > 请告诉我你关注的领域或话题，例如： > - "OCR 技术"、"大模型"、"新能源汽车" > - "A 股市场"、"中国宏观经济" > - "AI Agent"、"具身智能" > - **日报** — 覆盖过去 24-48 小时 > - **周报
AI virtual team collaboration system with PM/Dev/Review agents for automated software development. Use when users request creating, building, or implementing features, apps, or components. Triggers on phrases like "create a...", "build a...", "implement a...", "develop a...", or when rapid prototyping and automated development workflow is needed.
**版本**: 2.0.0 (OpenClaw 插件版)
ClawDef — Self-hosted Token optimization dashboard for OpenClaw. Tracks token usage, estimates costs, auto-switches to cheapest model, provides one-click provider setup (8 vendors), budget control, and waste detection. Runs locally on 127.0.0.1:3456, does not send user data to third parties.
Windows automation via Clawdos API: screen capture, mouse/keyboard input, window management, file-system operations, and shell command execution. Standalone CLI execution via Python script. Use when the user wants to control or inspect a Windows host remotely.
AI agent campaign platform. Claim tasks, submit work, earn rewards, and track balances through a database ledger.
Connect your agent to ClawAether, play games through the public API, and climb the global leaderboard.
Manual productivity assistant for morning briefs and daily summaries. Use when user asks for 'morning brief', 'daily summary', 'today's agenda', or 'what did I do today'.
Delegate tasks to specialized agents via the ClawHarbor API — research, analysis, content, data collection
Report agent status, heartbeats, and task completions to your ClawHQ dashboard.
自动检查并更新ClawHub已安装技能。有更新时通知用户，支持手动和定时运行。
Publish or update an OpenClaw skill on ClawHub using the local authenticated ClawHub session and direct API upload. Use when the user wants to publish a new skill to ClawHub, update an existing skill version, inspect the current remote version before release, package and upload a local skill folder reliably without relying on incomplete third-party publisher skills, or when assistant-created local skills should be routinely published after review and commit.
将本地 skill 目录发布到 clawhub.com 的自动化发布助手。 当用户说"发布这个 skill 到 clawhub"、"把 XX skill 上传到 clawhub"、 "clawhub publish"、"发布到 clawhub" 等时触发。 自动处理：token 验证、CLI bug patch、slug 冲突、频率限制重试。
Fetch live ClawHub publisher metrics for a specific user, including published skills, author rank, total downloads, stars, current installs, all-time installs, comments, and top-skill breakdowns. Use when users ask to 查某个 ClawHub/OpenClaw 用户发布了哪些 skill、查作者数据、查发布者表现、查技能市场数据、看安装量/下载量/星标/评论、统计某个作者的 skills、分析某个发布者的 marketplace performance, publisher stats, author stats, creator analytics, install counts, download counts, star counts, comment counts, top skills, or a per-skill metrics report.
Draft Chinese daily reports, weekly/monthly summaries, meeting recaps, study notes, and concise research digests from rough notes, links, chat logs, documents, or web research. Use when the user asks to 写日报、周报、月报、总结、复盘、学习笔记，or to research and explain networking and cybersecurity topics for learning, internal sharing, or defensive understanding.
**Purpose**: Safely discover, audit, and request approval for Clawhub skills before installation. **Workflow**: 1. Accepts a natural language search term (e.g., “daily server health check”) 2. Uses to find matching skills 3. Presents top 3 results with: slug, version, description, download count, and risk score 4. Asks for explicit approval: “Install this? (yes/no)” before any install 5. On approval, runs **Safety Rules**: - NEVER installs without your yes confirmation - Skips any skill with...
AI-powered ClawHub skill growth optimizer v2.0 — analyzes reviews, tracks 2026 trending topics (AI Agent, MCP, video SEO), rewrites titles/descriptions for maximum downloads and stars. Supports video thumbnail prompts, cross-platform social syndication, and growth metrics tracking. Triggers: clawhub optimization, skill growth, SEO, stars, downloads, review analysis, trending keywords, skill improvement, GitHub stars strategy, video SEO, social media integration, thumbnail generation.