agent-autonomy-kit
Stop waiting for prompts. Keep working.
共找到 41 个 Skills
Stop waiting for prompts. Keep working.
Build high-performing OpenClaw agents end-to-end. Use when you want to design a new agent (persona + operating rules) and generate the required OpenClaw workspace files (SOUL.md, IDENTITY.md, AGENTS.md, USER.md, HEARTBEAT.md, optional MEMORY.md + memory/YYYY-MM-DD.md). Also use to iterate on an existing agent’s behavior, guardrails, autonomy model, heartbeat plan, and skill roster.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Generate AI images with FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image
Perform structured HTTP/HTTPS requests (GET, POST, PUT, DELETE) with custom headers and JSON body support. Use for API testing, health checks, or interacting with REST services programmatically without relying on curl.
Write reliable Bash scripts with proper quoting, error handling, and parameter expansion.
Coding workflow with planning, implementation, verification, and testing for clean software development.
Write safe C++ avoiding memory leaks, dangling pointers, undefined behavior, and ownership confusion.
Web scraping using local Crawl4AI instance. Use for fetching full page content with JavaScript rendering. Better than Tavily for complex pages. Unlimited usage.
Build secure Django apps avoiding ORM pitfalls, N+1 queries, and common security traps.
OpenClaw自动化文件管理助手,用于批量文件操作、智能分类、重复文件清理、文件重命名、目录同步等任务。当用户需要整理文件、批量重命名、清理重复文件、同步目录或自动化文件工作流时使用此技能。
Essential Git commands and workflows for version control, branching, and collaboration.
Write reliable Go code avoiding goroutine leaks, interface traps, and common concurrency bugs.
Create, inspect, process, and optimize image files and visual assets with reliable format choice, resizing, compression, color-profile, metadata, and platform-export checks. Use when (1) the task is about images, screenshots, logos, product photos, or graphics; (2) resizing, converting, compressing, cropping, metadata, or export specs matter; (3) the asset must survive web, social, ecommerce, or print delivery without quality or format mistakes.
Image recognition and understanding tool. Uses a multimodal model (e.g. doubao-seed-2.0-pro, kimi-k2.5) to analyze image content and supports OCR text extraction and image description. Use this skill when a user sends a screenshot or image and needs the text extracted or the image content understood.
Write robust JavaScript with async patterns, type coercion handling, and modern ES2023+ features.
Convert documents and files to Markdown using markitdown. Use when converting PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), HTML, CSV, JSON, XML, images (with EXIF/OCR), audio (with transcription), ZIP archives, YouTube URLs, or EPubs to Markdown format for LLM processing or text analysis.
Write correct MySQL queries with proper character sets, indexing, transactions, and production patterns.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
View, extract, edit, and manipulate PDF files. Supports text extraction, text editing (overlay and replacement), merging, splitting, rotating pages, and getting PDF metadata. Use when working with PDF documents for reading content, adding/editing text, reorganizing pages, combining files, or extracting information.
Advanced expert in prompt engineering, custom instructions design, and prompt optimization for AI agents
AI prompt generator for image and text. AI绘画提示词、AI画图、Midjourney提示词、MJ提示词、Stable Diffusion提示词、SD提示词、DALL-E提示词、AI绘图、AI生图、AI画画、文生图提示词、text-to-image prompt、写作提示词、ChatGPT提示词、Claude提示词、prompt engineering、提示词工程、提示词优化、负面提示词、negative prompt、画风提示词、风格提示词、风格词库、工作流、提示词升级。Generate image prompts for Midjourney/SD/DALL-E and writing prompts for ChatGPT/Claude. Use when: (1) generating AI image/art prompts, (2) creating Midjourney/Stable Diffusion/DALL-E prompts, (3) translating Chinese descriptions to English prompts, (4) enhancing or optimizing existing prompts, (5) batch generating prompt variations, (6) creating writing prompts, (7) browsing style-specific keyword libraries, (8) getting complete negative prompt reference, (9) following complete image generation workflows, (10) upgrading simple descriptions to professional prompts, (11) any AI art or prompt engineering task. 适用场景:生成AI绘画提示词、Midjourney出图、SD出图、中文转英文提示词、优化提示词、批量生成提示词变体、风格词库查询、负面提示词参考、完整出图工作流、提示词升级优化。纯本地模板生成,不依赖外部API。 Triggers on: prompt generator, Image, Chinese, All.
Professional data visualization using Python (matplotlib, seaborn, plotly). Create publication-quality static charts, statistical visualizations, and interactive plots. Use when generating charts/graphs/plots from data, creating infographics with data components, or producing scientific/statistical visualizations. Supports PNG/SVG (static) and HTML (interactive) export.
FastAPI 快速构建 CRUD RESTful API。适用于快速创建 Python Web API、处理请求验证、自动生成文档等场景。
Python environment management skill. Automatically detect project type and existing environments, recommend based on popularity. Minimize interruptions, only ask when necessary.
Universal Ragflow API client for RAG operations. Create datasets, upload documents, run chat queries against knowledge bases. Self-hosted RAG platform integration.
高级 RAG 助手,具备 Agentic RAG 思考能力。能够自动化管理 RAGTOP 知识库,并在执行深度调研任务时,调用 RAGTOP 后端接口。使用场景包括:(1) 列出知识库和文档,(2) 执行语义检索和深度分析。
This skill should be used when the user wants to push code to Railway, says "railway up", "deploy", "deploy to railway", "ship", or "push". For initial setup or creating services, use new skill. For Docker images, use environment skill.
Write idiomatic Rust avoiding ownership pitfalls, lifetime confusion, and common borrow checker battles.
Structured extraction and cleanup for public, user-authorized web pages. Use when the user wants to collect, clean, summarize, or transform content from accessible pages into reusable text or data. Do not use to bypass logins, paywalls, captchas, robots restrictions, or access controls. Local-only output.
Automated security scanning and vulnerability detection for web applications, APIs, and infrastructure. Use when you need to scan targets for vulnerabilities, check SSL certificates, find open ports, detect misconfigurations, or perform security audits. Integrates with nmap, nuclei, and other security tools.
创建有效 Skills 的指南。当用户希望创建新技能(或更新现有技能)时使用,通过专业知识、工作流或工具集成扩展 AI 能力。
Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).
Write type-safe TypeScript with proper narrowing, inference patterns, and strict mode best practices.
TypeScript 内置工具类型详解。适用于需要转换类型、创建变体类型、选取/排除属性等场景。包含 Partial、Required、Pick、Omit、Record 等常用类型。
Deploy applications and manage projects with complete CLI reference. Commands for deployments, projects, domains, environment variables, and live documentation access.
Create AI videos with Sora 2, Veo 3, Seedance, Runway, and modern APIs using reliable prompt and rendering workflows.
Build Vue 3 applications with Composition API, proper reactivity patterns, and production-ready components.
This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses DuckDuckGo's search API to return results in clean, formatted output (text, markdown, or JSON). Use for research, fact-checking, finding recent information, or gathering web resources.
Send messages to various webhook-based bots (WeCom, DingTalk, Feishu, etc.).
Fetch and summarize YouTube video transcripts. Use when asked to summarize, transcribe, or extract content from YouTube videos. Handles transcript fetching via residential IP proxy to bypass YouTube's cloud IP blocks.