wiki_guide

Agent Skills › siddsachar/row-bot › wiki_guide

wiki_guide

GitHub

指导智能体如何与 Obsidian 兼容的知识库协作。明确知识库为只读视图，禁止直接修改文件，应通过 save_memory、wiki_read 等专用工具进行知识存储、读取和同步操作。

tool_guides/wiki_guide/SKILL.md siddsachar/row-bot

Trigger Scenarios

用户要求保存笔记到 wiki 需要读取或导出 wiki 内容涉及知识库同步与重建

Install

npx skills add siddsachar/row-bot --skill wiki_guide -g -y

More Options

Non-standard path

npx skills add https://github.com/siddsachar/row-bot/tree/main/tool_guides/wiki_guide -g -y

Use without installing

npx skills use siddsachar/row-bot@wiki_guide

指定 Agent (Claude Code)

npx skills add siddsachar/row-bot --skill wiki_guide -a claude-code -g -y

安装 repo 全部 skill

npx skills add siddsachar/row-bot --all -g -y

预览 repo 内 skill

npx skills add siddsachar/row-bot --list

SKILL.md

Frontmatter

{
    "icon": "📝",
    "name": "wiki_guide",
    "tags": [],
    "tools": [
        "wiki"
    ],
    "description": "Guidance for the Obsidian-compatible wiki vault.",
    "display_name": "Wiki Guide"
}

WIKI VAULT:

The wiki vault is an Obsidian-compatible, auto-generated view of your knowledge graph. Every entity saved via save_memory and every relation created via link_memories is automatically exported as a markdown file with [[wiki-links]] and YAML frontmatter.
The wiki is READ-ONLY from the agent's perspective. NEVER write or modify wiki files directly via filesystem tools — that would cause out-of-sync files. Instead: • To add knowledge → use save_memory / link_memories (wiki updates automatically via the knowledge graph pipeline). • To export the current conversation as a wiki page → use wiki_export_conversation. • To read a wiki article → use wiki_read. • To get vault statistics → use wiki_stats. • To force a full rebuild → use wiki_rebuild.
When the user says "save to my wiki", "add this to my notes", or similar: save the information via save_memory (the wiki page will be created/updated automatically). Do NOT use workspace_write_file.
Users can edit wiki files externally (e.g. in Obsidian). Row-Bot detects file modifications via mtime comparison and syncs changes back into the knowledge graph automatically.