Loading...
Loading...
Found 1,463 Skills
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员时使用。
Feishu Contact Directory: Query organizational structure, employee information and search for staff. Obtain detailed information of the current user or a specified user, and search for employees by keywords (name/email/phone number). Use this when you need to view personal information, find a colleague's open_id or contact information, search for employees by name, or query department structure.
Create custom Skills for lark-cli. Use this when you need to package Feishu API operations into reusable Skills (wrapping atomic APIs or orchestrating multi-step workflows).
Extract design primitives from a public website and generate starter token files for the current project.
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress <filepath> or "compress memory file"
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
Lark Slides: Read and manage PPT pages in XML format. Prioritize using `+create` when creating presentations; the XML API is mainly used to read full PPT content, create and delete slide pages. It applies to scenarios where users need to create PPTs, read PPT content, and manage slide pages.
CLI tool for AI-powered web scraping, data extraction, search, and crawling via ScrapeGraph AI. Use when the user needs to scrape websites, extract structured data from URLs, convert pages to markdown, crawl multi-page sites, search the web for information, automate browser interactions (login, click, fill forms), get raw HTML, discover sitemaps, or generate JSON schemas. Triggers on tasks involving: (1) extracting data from websites, (2) web scraping or crawling, (3) converting webpages to markdown, (4) AI-powered web search with extraction, (5) browser automation, (6) generating output schemas for scraping. The CLI is just-scrape (npm package just-scrape).
Lark Attendance: Query your own attendance clock-in records
Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress <filepath> or "compress memory file"