Skills your agents can run

Read and extract content from Feishu (Lark) documents using the official Feishu Open API

Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.

深度解析 AI 论文，生成可直接发布的专业阅读笔记

Continuous learning system that extracts reusable knowledge from work sessions. Triggers: (1) /learn command to review session learnings, (2) "save this as a skill" or "extract a skill from this", (3) "what did we learn?", (4) After any task involving non-obvious debugging, workarounds, or trial-and-error discovery. Creates new Claude Code skills when valuable, reusable knowledge is identified.

Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.

This skill provides a simple interface to the Memos API (https://usememos.com/docs/api). It lets you create, read, delete, and list memos from OpenClaw.

Generate clear documentation for each task including technical descriptions, architecture diagrams, and usage guides. Use when documenting completed features, creating README files, writing API documentation, generating architecture diagrams, or maintaining project documentation. Ensures knowledge is preserved and accessible.

BookStack Wiki & Documentation API integration. Manage your knowledge base programmatically: create, read, update, and delete books, chapters, pages, and shelves. Full-text search across all content. Use when you need to: (1) Create or edit wiki pages and documentation, (2) Organize content in books and chapters, (3) Search your knowledge base, (4) Automate documentation workflows, (5) Sync content between systems. Supports both HTML and Markdown content.

Management, ingestion, synchronization, and search of knowledge bases across multiple storage layers (local files, MCP memory, vector stores, Git repositories). Used when a user wants to store, organize, synchronize, deduplicate, and search across the entire knowledge system.

中文写作技能指南，用于生成高质量的周刊、博客及科技资讯类文章。

Use when user asks YouTube video extraction, get, fetch, transcripts, subtitles, or captions. Writes video details and transcription into structured markdown file.

Capture conversations and decisions into structured Notion pages; use when turning chats/notes into wiki entries, how-tos, decisions, or FAQs with proper linking.

Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.

Feishu (Lark) Cloud Documents: create and edit Feishu documents. Create documents from Markdown, retrieve document content, update documents (append/overwrite/replace/insert/delete), upload and download images and files contained in documents, and search documents in cloud space. Use this when a user needs to create or edit Feishu documents, read document content, insert images into a document, or search documents in cloud space. If the user intends to locate cloud-space objects such as spreadsheets or reports by name or keyword first, prefer using this skill's docs +search for resource discovery.

Create, read, and manage OneNote notebooks, sections, and pages via Microsoft Graph API. Use when someone asks to "create OneNote pages", "read OneNote notes", "automate OneNote", "save to OneNote", "extract OneNote content", "organize OneNote notebooks", or "OneNote API". Covers notebooks, sections, pages (create with HTML), content extraction, and search.

Transforms raw meeting transcripts into high-fidelity, structured meeting minutes with iterative review for completeness. Use this skill when (1) a meeting transcript is provided and meeting minutes, notes, or summaries are requested, (2) multiple versions of meeting minutes need to be merged without losing content, (3) existing minutes need to be reviewed against the original transcript for missing items, or (4) the transcript uses anonymized speakers like 「Speaker 1/2/3」 that require identification. Features include: speaker identification via feature analysis (word count, speaking style, topic focus) with context.md team-directory mapping, intelligent file naming from content, integration with transcript-fixer for preprocessing, evidence-based recording with speaker-attributed quotes, Mermaid diagrams for architecture discussions, multi-turn parallel generation to avoid content loss, and iterative human-in-the-loop refinement.

Implements a Manus-style, file-based planning workflow for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring more than 5 tool calls. Now includes automatic session recovery after /clear.

Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.

Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.

Store and retrieve memories using the SuperMemory API. Add content, search memories, and chat with your knowledge base.