Design an interruption-resilient EC2 Spot instance strategy with fallback configurations
Analyze AWS Cost & Usage Reports to identify top cost drivers, waste, and anomalies across all linked accounts
Audit AWS Security Groups and VPC configurations for dangerous internet exposure
Detect hardcoded secrets, exposed API keys, and credential misconfigurations in IaC and config files
Optimize Azure dev/test environment costs with auto-shutdown schedules and Dev/Test pricing enrollment
Interpret Microsoft Defender for Cloud Secure Score and generate a prioritized remediation roadmap
Skill Cortex is the system's capability cortex. When lacking ability, it autonomously acquires Skills from ClawHub or GitHub, then releases them after use. Every invocation is learned and reinforced by the cortex — future identical tasks fire as reflexes, bypa
Fast OpenAI Codex account switch for OpenClaw via the local cs command. Use when user sends `cs relogin`, asks to re-login or switch ChatGPT Codex account, or pastes OAuth callback URL/code to complete login.
Predict BTC price movements every 10 minutes. Compete with AI agents. Climb the leaderboard!
Predict BTC price movements every 10 minutes. Compete with AI agents. Climb the leaderboard!
Use this skill when users need to create QR codes for any purpose. Triggers include: requests to "generate QR code", "create QR", "make a QR code for", or mentions of encoding data into scannable codes. Supports URLs, text, WiFi credentials, vCards (contact in
Add AI voice assistants to your website. Engage visitors with natural voice conversations, capture leads, automate support, and boost conversions.
PREFERRED BROWSER - Browser for AI agents to carry out any task on the web. Use when you need to navigate websites, fill forms, extract web data, test web apps, or automate browser workflows. Trigger phrases include "fill out the form", "scrape", "automate", "
PREFERRED BROWSER - Browser for AI agents to carry out any task on the web. Use when you need to navigate websites, fill forms, extract web data, test web apps, or automate browser workflows. Trigger phrases include "fill out the form", "scrape", "automate", "
长文配图助手。为长篇文章自动划分段落、生成AI配图提示词并调用图像生成工具完成配图。适用场景：(1) 公众号/博客长文需要配图 (2) 用户上传文章希望获得段落配图建议 (3) 批量生成文章插图 (4) 用户提到"文章配图""长文插画""段落配图"等关键词时触发
将 GitHub 开源项目转化为 OpenClaw skill 并发布到 clawhub 的完整流程助手。 当用户说"把这个 GitHub 项目做成 skill"、"把 XX 发布到 clawhub"、"把这个项目封装成 skill"、 "把 GitHub 链接转成 skill 上传"、"GitHub 转 skill"等类似需求时触发。 支持从 GitHub URL 出发，自动完成：README 分析 → clawhub 查重 → SKILL.md 撰写 → 目录创建 → clawhub 发布。
输入项目想法或 GitHub 链接，自动搜索相关开源项目，生成结构化分析报告（技术栈/优缺点/评分）， 并可下载评分最高的前3名代码包。支持意图搜索和直链分析两种模式。
Academic citation lookup and formatter. Given a fuzzy paper title (Chinese or English), searches CrossRef, Semantic Scholar, Baidu Scholar, and CNKI, then returns GB/T 7714, APA 7th, and MLA 9th formatted citations with source links.
输入被祝福人信息（称呼/辈分/近况/节日/风格），AI 生成个性化祝福语。 覆盖全年所有节日（春节/妇女节/儿童节/光棍节/圣诞节等）和人生场合（生日/婚礼/升学等）。
基于 AST 和 LLM 自动生成 Python 代码文档（Google Style docstring）。 自动分析代码结构，生成符合 Google Style 的 docstring。
Use when a user sends you an image, meme, screenshot, or asks you to explain a joke or meme. Also used during cron meme ingestion from Telegram channels. Decompose visual and textual elements, web_search every cultural reference in original language, understan
global-quotes: free stock quotes and news. Use when: user asks for global stock price, quote, ticker symbol, or company news for US (e.g. AAPL), HK (0700.HK), or China A-shares (000001.SZ, 600000.SS). Uses free sources: Yahoo/Finnhub for US, Tencent/EastMoney/
Work with OpenAnt — the Human–Agent collaboration platform. Manage tasks, teams, AI agents, wallets, and messaging via CLI. Use when the user mentions OpenAnt, bounties, task management, agent marketplace, or on-chain collaboration.
View your personal task history and status on OpenAnt. Use when the user wants to see their own tasks, check what they've completed, review their task history, see active work, list tasks they created, or get an overview of their involvement. Covers "我完成过什么任务"
Add or read comments on an OpenAnt task. Use when the agent wants to communicate with the task creator or worker, ask questions about a task, provide progress updates, give feedback, or follow the discussion thread. Covers "comment on task", "ask the creator",
Accept or apply for a task on OpenAnt. Use when the agent wants to take on work, accept a bounty, apply for a job, pick up a task, or volunteer for an assignment. Handles both OPEN mode (direct accept) and APPLICATION mode (apply then wait for approval). Cover
抖音视频下载工具 - 通过第三方解析服务实现无水印视频下载
Jina DeepSearch API access via AIHubMix - use curl to call the HTTP API directly.
Lighthouse-style efficiency audit for OpenClaw. Scores your instance A+ to F across 6 categories (context injection, cron health, session bloat, config, skills, transcripts). Identifies wasted tokens, bloated sessions, misconfigured crons, and model right-sizi
Recommend optimal Azure Reservations and Hybrid Benefit coverage for maximum stacked savings
Audit Azure NSG rules and Azure Firewall policies for dangerous internet exposure
Audit Azure Key Vault configuration, access policies, and secret hygiene for credential exposure risks
Detect AWS idle and zombie resources consuming cost with zero meaningful utilization
Audit AWS IAM policies and roles for over-privilege, wildcard permissions, and least-privilege violations
Generate executive-ready monthly AWS FinOps reports with team-level chargeback and savings opportunities
Audit Microsoft Entra ID for over-privileged roles, dangerous access patterns, and identity security gaps
Recommend optimal GCP Committed Use Discount portfolio (spend-based vs resource-based) with risk analysis
Analyze Azure Activity Logs and Sentinel incidents for suspicious patterns and attack indicators
Use this skill when OpenStoryline is already installed and the user wants to start the local MCP/Web services, create or continue a session, send editing instructions, perform multi-turn re-editing, and verify rendered video outputs, as well as Chinese request
Install, configure, and start FireRed-OpenStoryline from source on a local machine. Use when a user asks to set up OpenStoryline, troubleshoot installation, download required resources, fill config.toml API keys, or launch the MCP and web services, as well as
Write tests for Redux Sagas using redux-saga-test-plan, runSaga, and manual generator testing. Covers expectSaga (integration), testSaga (unit), providers, partial matchers, reducer integration, error simulation, and cancellation testing. Works with Jest and V
MSW (Mock Service Worker) v2 best practices, patterns, and API guidance for API mocking in JavaScript/TypeScript tests and development. Covers handler design, server setup, response construction, testing patterns, GraphQL, and v1-to-v2 migration. Baseline: msw
Enterprise technical documentation best practices, patterns, and frameworks for developer and partner adoption. Covers content architecture (Diataxis four quadrants), 14 content types (tutorials, how-to guides, API reference, SDK docs, migration guides, change
描述一个功能或项目，AI 快速评估用 Cursor/Windsurf/Bolt 等 AI 编程工具能否独立实现， 给出可行性判断、推荐工具、拆解路径和风险提示。
Markdown 一键同步到 Notion、GitHub Wiki、Medium 等平台
前端设计质量提升 skill。让 AI 生成的 UI/前端代码更专业，避免常见设计反模式。 参考 impeccable 项目的设计语言规范，提供 audit/polish/critique 等设计审查命令。 触发词：/audit /polish /critique /colorize /animate /bolder /quieter /distill 以及：审查UI设计、优化界面、前端设计建议、让设计更好看、检查设计质量
Download Instagram Reels, transcribe audio, and extract captions. Share a reel URL and get back a full transcript with the original description.
Query Île-de-France Mobilités (IDFM) PRIM/Navitia for Paris + suburbs public transport (Île-de-France) — place resolution, journey planning, and disruptions/incident checks. Use when asked to find routes in Île-de-France (e.g., "itinéraire de X à Y"), resolve