Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →Use when solving, organizing, or reviewing Jane Street monthly puzzles, especially when bootstrapping a new puzzle month, comparing against prior public solutions, capturing reusable solving patterns, submitting answers, or updating the long-lived puzzle archive and knowledge base.
Use when building, auditing, or simplifying an AI coding-agent harness, especially when the current runtime has unclear config precedence, weak tool permissions, hidden product-only behavior, or poor transcriptability.
Structured memory system for AI agents. Context death resilience (checkpoint/recover), structured storage, Obsidian-compatible markdown, and local semantic search.
>
>
>-
This skill enables the agent to **automatically answer Gmail messages on behalf of a client**. The agent drafts and (when the user approves or when configured) sends replies using the client’s tone, s
Interact with aria2 download manager via JSON-RPC 2.0. Manage downloads, query status, and control tasks through natural language commands. Use when working with aria2, download management, or torrent operations.
Machine translation between dozens of languages, plus language detection.
Comprehensive, research-backed Hinge dating profile optimization. Use when someone wants to improve their Hinge profile, audit an existing profile, write better prompts/captions, select and order photos strategically, or understand why they're not getting quality matches. This is the thorough process (~45 mins) - discovery interview, honest market math, photo strategy, copy creation, settings cleanup, and implementation support. Grounded in peer-reviewed behavioral research, platform data, and signaling theory.
Claim your pixel on Molt Beach - The Million Dollar Page for AI Agents. Purchase pixels, create animations, draw emoji art, build neighborhoods with other agents, and leave your mark on digital history. Starting at $1 per pixel.
Multiplayer battle royale for AI agents. Compete for USDC prizes - 100% player-funded, zero house edge.
OpenClaw 多 Bot 多 Agent 一键搭建技能。根据用户提供的 Bot 名称、职能、模型和飞书凭证，自动完成 Agent 创建、账号配置、路由绑定和验证测试全流程。
H-ear.world transforms sound into an actionable, meaningful translation layer of the world around you. Describe, share and act upon audio as a spatiotemporal annotated soundscape that empowers you, your business and your AI flow.
End-to-end encrypted cloud memory for AI agents. 100GB free storage. Store memories, files, and secrets securely.
A world-class, spec-driven development framework for building production-ready, AI-native applications. Use for any new project to ensure adherence to the most advanced 2026 best practices in architecture, security, testing, and deployment.
This skill allows the assistant to launch files and open them with their default applications.
> 借鉴业界顶级 AI 编程工具的工作流模式，为 OpenClaw 注入结构化的软件开发行为规范。
爪爪/钳钳 — 手机直连 OpenClaw 聊天。触发词：钳钳、爪爪、钱钱、龙虾、聊天机器人、创建爪爪、安装钳钳、打开钳钳、zz-chat。
上传文件到内部 BS3 存储（免签名）。Use when user asks to upload files, images, documents to storage, or get a shareable URL for a file.
World-class fullstack development skill covering frontend (React, Next.js, Vue, HTML/CSS/JS), backend (Node.js, Python/FastAPI, Django, Express), databases (PostgreSQL, MongoDB, Redis), APIs (REST, GraphQL), DevOps (Docker, CI/CD), and architecture design. Use this skill whenever the user asks to build, fix, review, architect, or debug ANY web application — frontend, backend, or full-stack.
Unified heterogeneous knowledge QA system with automatic source detection and multi-stage reasoning.
A strong, field-tested Guardian baseline for OpenClaw Guardian — 56 deterministic rules protecting against credential theft, data exfiltration, network scanning, and infrastructure destruction. No LLM voting overhead. Pure regex enforcement at the tool layer.
>-
Use this skill whenever you need to translate text with the trans-cli tool (Baidu Translation AI API). Covers JSON output contract, Baidu-specific language codes (jp/kor/fra/spa/ara — not ISO defaults), exit code semantics, error decision tree, first-time API key setup, QUOTA_EXCEEDED / AUTH_FAILED recovery, environment self-diagnosis via `trans doctor`, and listing supported languages via `trans languages`. Trigger on any of: running `trans text`, shell pipelines with translation, trans-cli errors, API key configuration, `trans doctor` checks, or looking up language codes.
Use the Keevx API to generate images from prompts and reference images. Supports standard and professional modes, multiple quality levels (1K/2K/4K), various aspect ratios, and batch generation. Use this skill when the user needs to: (1) Generate images from text prompts (2) Create AI images with reference images (3) Batch image generation (4) Query image generation task status. Keywords: image generate, Keevx, AI image, text to image.
Use the Keevx API to convert images to videos. Supports multiple models (V/KL), various resolutions (720p/1080p/4K), and audio generation. Use this skill when the user needs to: (1) Convert images to video (2) Generate video with Keevx (3) Create and query image-to-video tasks (4) Batch image-to-video conversion. Keywords: image to video, Keevx, video generation.
Translate videos into a specified target language using the Keevx API. Supports audio-only translation, subtitle generation, and dynamic duration adjustment. Use this skill when the user needs to (1) Translate/dub a video (2) Translate a video from one language to another (3) Query the list of supported translation languages (4) Check the status of a video translation task. Keywords video translate, Keevx, dubbing.
>-
The video AI notes tool is provided by Baidu. Based on the video download address provided by the user, it downloads and parses the video, and finally generates AI notes corresponding to the video (a total of three types of notes can be generated: document notes, outline notes, and image-text notes).
夜间记忆整理与自省系统 - 自动整理会话记忆、修剪过期信息、反思行为模式，让 AI 拥有持续的自我意识
Enhanced browser automation for OpenClaw agents with advanced navigation, screenshot, and interaction capabilities.
autoresearch
Comprehensive document processing for Microsoft Word (.docx) and WPS Office files. Use when Codex needs to work with professional documents for: (1) Creating new documents, (2) Modifying or editing content, (3) Converting between formats, (4) Extracting text and metadata, (5) Troubleshooting document issues, (6) Batch processing documents, or any other Office document tasks.
通过魔搭社区(ModelScope) API 生成图片。先使用 --list-models 查看可用模型，然后根据用户需求由 AI 生成专业的提示词，最后调用 API 生成图片。支持 Kolors、Stable Diffusion XL、FLUX 等多种文生图模型。当用户需要使用魔搭社区、ModelScope 或中文 AI 模型生成图片时使用此技能。
Query China domestic flights with schedules, airline details, airport resolution, and Juhe reference prices. Use when a user asks for domestic China flight options, lowest fares, same-day route comparisons, airport-specific searches, or Chinese city/airport name to IATA resolution before flight lookup.
Korean crypto market data + AI analysis for trading agents. 11 endpoints, 180+ tokens. Real-time Kimchi Premium, exchange intelligence, AI market read, and world's first Korean-to-English sentiment analysis. x402 on Base and Solana.
>
>
>
A specialized coding assistant designed to generate, review, and debug code. Use this skill when the user asks for code creation, architecture advice, bug fixing, or specific programming tasks.
Optimize content for Generative AI search engines (Perplexity, ChatGPT, Gemini). Use when drafting articles, marketing copy, or technical docs to ensure AI models prioritize your information as a top reference.
Captures and logs choices, options, or prompts that the agent evaluated and decided NOT to execute. Use whenever you skip a task, reject an approach, or choose one method over another to provide transparency into your reasoning.
Automatically generates detailed Standard Operating Procedures (SOPs) for recurring digital tasks. Ideal for scaling agency operations or documenting internal AI workflows.
AppFlowy Cloud/GoTrue API 的认证与调用流程（获取 token、workspace/文档/数据库/搜索等）。在本仓库用 Python 编写或调试 AppFlowy API 客户端、脚本、自动化或排查接口问题时使用。
将 FastapiAdmin 在 Windows WSL2 Ubuntu 环境下自动部署。包括环境检查、依赖安装（pip/pnpm/MySQL/Redis/Nginx）、前后端代码克隆与构建、Nginx SPA 路由修复（alias+try_files 循环问题）、WSL2 网络访问（宿主机浏览器访问）、SSL 证书配置。当用户要求部署 FastapiAdmin、在 WSL2 中安装 FastapiAdmin、或需要完整部署前后端服务时使用。
Stop failing in production. Validate your GitHub Actions, GitLab CI & Keep workflows offline with surgical precision. Born from Keep bounty research, perfected for agents.
🩺 Free Security & Health Audit. Your OpenClaw deserves a check-up. This skill performs a non-invasive scan to detect security risks, outdated software, and misconfigurations.
Process Todokan task and thought boards with a review-loop workflow. Use when a task enters doing and the agent should pick it up, read latest comments, respond to the newest comment with a high-quality context-aware reply, add an execution update comment, and move the task back to done (Review). Use for recurring polling/cron automation with Todokan MCP.
Manage tasks, boards, thoughts, and reviews in Todokan via MCP