Skills your agents can run

Creative exploration during quiet hours. Turns idle heartbeat time into freeform thinking — hypotheticals, future scenarios, reflections, unexpected connections. Use when you want your agent to do something meaningful during low-activity periods instead of just returning HEARTBEAT_OK. Outputs written to files for human review later (like remembering dreams in the morning).

Generate and read XMind (.xmind) files via the published xmind-generator-mcp MCP server (npm), with a chat-first UX.

Life OS and project analysis. USE WHEN TELOS, life goals, projects, dependencies, books, movies. SkillSearch('telos') for docs.

Alpha research recorder - serves as the data persistence layer for the research workflow. Core features: 1. Reference the corresponding template file based on record type (session_meta/round/final_summary) 2. Accept structured data and validate required fields 3. Create/update YAML or Markdown log files Usage: - Specify record_type and session_id when invoking - Inspect template files to see the full field structure: templates/{record_type}.template - Merge the provided data into the template to produce the final file

Export all memories for the current user as a file. The file is sent directly via private message (DM) to the user, regardless of where the request was made. Use ONLY when the user explicitly requests to export their memories, and ONLY after confirming with the user.

Bidirectional sync with reMarkable tablet via Cloud API (rmapi). Fetch handwritten notes/sketches, process with AI, and push content back. Use for sketch enhancement, journal extraction, or sending documents/images to the tablet.

Tencent IMA OpenAPI skill for notes and knowledge base management. Use when the user mentions knowledge base, notes, memos, file uploads, web page collection, or knowledge search. Supports notes CRUD operations, knowledge-base file uploads, adding web links, and content search.

Manage Confluence pages via Atlassian MCP — search, create, update, and comment with proper Markdown formatting. Auto-detects workspace configuration. Use when user says "update Confluence", "create a Confluence page", "find that page in Confluence", "search Confluence", or "add a comment on Confluence". Do NOT use for Jira operations (use jira-assistant).

Use the Obsidian CLI to read, create, search, and manage vault content, or to develop and debug Obsidian plugins and themes from the command line.

Work like Manus: Use persistent Markdown files as your "working memory on disk."

Build and maintain a personal knowledge base using Karpathy's llm-wiki methodology across Claude Code, Codex, and OpenClaw agents.

Create and maintain comprehensive collection records including cataloging, photography, condition documentation, and database management following AAM/ICOM standards

Confluence tools: add_confluence_comment, create_confluence_page, get_confluence_page, search_confluence_pages, update_confluence_page

Exports OneNote notebooks to Obsidian-compatible Markdown with inline images via Playwright browser automation. Uses CDP to reuse an authenticated browser session (no API keys or app registrations needed). Use when the user asks to "export OneNote", "convert OneNote to markdown", "OneNote to Obsidian", or "onenote-to-markdown".

Development patterns for Obsidian. Load when implementing features or following coding conventions.

Generate Excalidraw diagrams and save them to the Obsidian vault. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Saves as .excalidraw.md in the correct Obsidian vault folder with an embedding MD file.

```markdown

思源笔记 (SiYuan Note) 联动。支持管理笔记本、文档、块，支持 SQL 查询内容。当需要从思源笔记中读取、写入或搜索内容时使用。

Triggered when the user wants:

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.