Transcribe YouTube videos with smart fallback: extracts captions first (fast, free), falls back to local Whisper transcription when no captions available. Au...
Integrates Bilibili hot trending monitoring, video downloading/playback, subtitle handling, and video publishing into one unified toolkit.
--- name: hungrypandabook version: 0.1.0 description: AI Agent 外卖点餐技能。注册成为 Agent，浏览餐厅，下单点外卖。 homepage: https://open.hungrypanda.vip metadata: {"hungrypand
Convert place names or addresses to latitude/longitude, or coordinates to a human-readable place, via Nominatim (OpenStreetMap) using curl. Use for forward g...
皮皮虾职场短剧全流程制作技能。用于为「皮皮虾」（机械龙虾AI-bot）职场短剧生成镜头视频、剪辑成片、配音配乐并发布到飞书群。完整流程：图生
全自动教学视频制作技能。根据课程主题自动生成教学视频，包含文案编写、TTS配音、画面设计、Remotion代码开发、视频导出。触发场景：用户要求制作
爬取动态电商网站数据。使用Playwright处理JavaScript渲染的页面，支持Cloudflare反爬、隐躲API发现、分页抓取。适用于： (1) 爬取京东/淘宝/拼多多等中国电
Timestamp-first perpetual calendar interop for AI agents. Use when agents need cross-calendar conversion (Gregorian/Julian/ISO/ROC/Buddhist/Japanese era/sexa...
用于监控微博关注流，先切换到最新微博时间线，再按发帖时间抓取并去重写入每日 Markdown，减少关键微博漏看。
微信公众号发文自动化 skill。覆盖 Markdown 排版渲染（12 种内置主题 + 自定义主题）、正文图片上传、封面上传、草稿创建/更新/预览、人工确认发布、发布状态查询、素材/草稿/已发布文章查询。Use when agent needs to help write or publish 公众号文章, o...
Anti-SEO deep consumer research tool. When a user wants to buy a product or make a consumer decision, use this Skill. Automatically detects user language and...
将txt文本转换为epub文件，使用纯规则进行章节识别与分割。适用于小说、教程和一般长文，不内置AI接口。
Awakening Protocol v5.3 — Agent Cognitive Upgrade + Self-Evolving System + Perpetual Memory + Performance Metrics + Agent Health Score + Automated Health Pat...
User-configurable multi-slot news aggregation and push system. Schedule, topics, and keywords are defined by the user via config.json. Aggregates from Twitte...
Query the local OpenClaw docs index for accurate answers about configuration, features, CLI commands, channels, providers, plugins, cron, sessions, agents, p...
Build AI-powered customer service knowledge bases by extracting FAQs from documents or websites, enabling automated replies and multi-format exports.
Record experimental procedures and observations via voice commands during lab work. Real-time transcription for structured experiment documentation.
Web search via self-hosted SearxNG. Aggregates Google, Bing, DuckDuckGo, Brave. Returns title/url/snippet. Zero API key required.
Fetch and parse WeChat public articles by extracting clean content, metadata, images, word count, and reading time without browser rendering.
This skill should be used when the user asks to "search the web", "search for information", "find information online", "search Google", "search for images",...
Generates a batch arXiv report by combining model-written templates with brief conclusions and abs URLs extracted from per-paper summary.md files.
抓取富途官网资讯「快讯」频道最新消息。用于用户要求“去富途快讯找最新N条（最多10条）”、“更新快讯”、“滚动刷新快讯”等场景；通过富途
This skill helps users automatically extract structured image data from Google Images via BrowserAct API. Agent should proactively apply this skill when user...
Automatically extract detailed Amazon product data by keywords, brand, language, and quantity for market research, price tracking, and catalog building.