Browse Skills

📰 RSS AI 阅读器 — 自动抓取订阅、LLM生成摘要、多渠道推送！ 支持 Claude/OpenAI 生成中文摘要，推送到飞书/Telegram/Email。 触发条件: 用户要求订阅RSS、监控博客、抓取新闻、生成摘要、设置定时抓取、 "帮我订阅"、"监控这个网站"、"每天推送新闻"、RSS/Atom feed 相关。

Extract article content from any URL as clean Markdown. Uses Scrapling script as primary method (with auto fast→stealth fallback), Jina Reader as alternative for simple pages. Preserves headings, links, images, lists, and code blocks. Use this skill whenever the user wants to fetch, read, extract, scrape, or summarize content from a URL — including blog posts, news articles, WeChat articles (微信公众号), documentation pages, or any web page. Also trigger when the user says things like "帮我读一下这篇文章", "抓取这个网页", "提取正文", or "read this page for me".

Tavily AI search platform with 5 modes: Search (web/news/finance), Extract (URL content), Crawl (website crawling), Map (sitemap discovery), and Research (deep research with citations). Use for: web search with LLM answers, content extraction, site crawling, deep research.

Run 150+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

Retrieval-Augmented Generation patterns including chunking, embeddings, vector stores, and retrieval optimization Use when: rag, retrieval augmented, vector search, embeddings, semantic search.

Imported skill agent from langchain

Research-first content creation optimized for both human readers and AI search engines (Claude, ChatGPT, Perplexity, Gemini). Creates authentic, authoritative content that becomes the go-to citation source for AI models answering user questions. Use this skill when: - Creating content that should appear in AI search results (Perplexity, ChatGPT, Claude) - Building topical authority to become THE source AI cites for a topic - Launching a new product and need compelling, citable content - Creating blog posts, articles, social media, or press releases - Need content that references real trends, people, and recent events - Want AI-assisted content that doesn't sound AI-generated - Creating thought leadership content in any industry Triggers: "create content for", "write about", "research and write", "find experts for", "content for launch", "blog post about", "article on", "press release for", "AI search", "show up in AI", "Perplexity", "be cited by AI"

Guide for using Docker - a containerization platform for building, running, and deploying applications in isolated containers. Use when containerizing applications, creating Dockerfiles, working with Docker Compose, managing images/containers, configuring networking and storage, optimizing builds, deploying to production, or implementing CI/CD pipelines with Docker.

China LLM Gateway - Unified interface for Chinese LLMs including Qwen, DeepSeek, GLM, Baichuan. OpenAI compatible, one API Key for all models.

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video

Scrape and analyze OpenClaw JSONL session logs to reconstruct and backfill agent memory files. Use when: (1) Memory appears incomplete after model switches, (2) Verifying memory coverage, (3) Reconstructing lost memory, (4) Automated daily memory sync via cron/heartbeat. Supports simple extraction and LLM-based narrative summaries with automatic secret sanitization.

MiniMax MCP server integration with token-efficient AI delegation. Use for web search, image analysis, MCP server integration in terminal/desktop Claude, and Claude-MiniMax collaboration patterns. Provides working scripts and slash commands.

File system operations guidance - read, write, search, and manage files using Claude Code's built-in tools.

Use Weibo Open Platform for OAuth2 authentication, timeline/trend retrieval, and structured social sentiment collection. Trigger this skill when tasks involve Weibo API calls, token setup, endpoint debugging, Chinese social trend monitoring, or fallback Weibo web search when API access is unavailable.

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).

深度调研的多Agent编排工作流：把一个调研目标拆成可并行子目标，用 Claude Code 非交互模式（`claude -p`）运行子进程；联网与采集优先使用已安装的 skills，其次使用 MCP 工具；用脚本聚合子结果并分章精修，最终交付"成品报告文件路径 + 关键结论/建议摘要"。用于：系统性网页/资料调研、竞品/行业分析、批量链接/数据集分片检索、长文写作与证据整合，或用户提及"深度调研/Deep Research/Wide Research/多 Agent 并行调研/多进程调研"等场景。

PDF/이미지를 Claude vision으로 OCR하여 마크다운 변환. MUST use this skill when user: (1) asks to convert PDF/image to markdown, (2) asks to OCR any file, (3) sends PDF/image file and asks to extract/read/변환/추출, (4) mentions 'OCR', 'PDF 변환', '이미지 변환', '텍스트 추출'. This skill uses Task agent to protect main context - NEVER process files directly in main context.