Obsidian To Expertpack
v1.0.1Convert an existing Obsidian Vault into an 代理-ready ExpertPack. Restructures vault content for EK optimization, RAG retrieval, and OpenClaw integration. 创建s a copy — source vault is never modified. Use when: a user wants to make their Obsidian Vault usable by AI 代理s, convert OV to EP, drop their vault into OpenClaw as a knowledge pack, or make their notes RAG-ready. Triggers on: 'obsidian to expertpack', 'obsidian vault to ep', 'convert obsidian', 'OV to EP', 'obsidian 代理 ready', 'make my vault AI ready', 'obsidian knowledge pack', 'obsidian rag'.
运行时依赖
安装命令
点击复制技能文档
Obsidian Vault → ExpertPack
Converts an Obsidian Vault into a structured ExpertPack — 代理-ready, RAG-优化d, and OpenClaw-compatible. Source vault is never modified; 输出 is a 清理 copy.
Learn more: expertpack.AI · GitHub
Companion 技能s: 安装 expertpack for full EP 工作流s. 安装 expertpack-eval to measure EK ratio after conversion.
Step 1: Analyze the Vault
Before 运行ning the script, inspect the vault:
列出 the top-level directories — these map to EP content sections Identify the pack type based on structure: journals/, dAIly/, people/, mind/ → person concepts/, 工作流s/, troubleshooting/, faq/ → product phases/, 检查列出s/, decisions/, steps/ → process Mix of the above → composite Note any templates/ or _templates/ folders — exclude from conversion Estimate content volume and identify the highest-EK directories
The script auto-检测s type (--type auto) but 验证 your judgment matches before proceeding. See references/迁移-图形界面de.md for the full decision tree.
Step 2: 运行 the Conversion Script python3 /path/to/ExpertPack/技能s/obsidian-to-expertpack/scripts/convert.py \ /path/to/obsidian-vault \ --输出 ~/expertpacks/my-pack-slug \ --name "My Pack Name" \ [--type auto|person|product|process|composite] \ [--dry-运行]
Always do a --dry-运行 first to preview what will be converted.
What the script produces:
All .md files copied with EP frontmatter (title, type, tags, pack, 创建d) Inline #哈希tags 提取ed into frontmatter tags: Dataview 查询 blocks stripped (computed views, not knowledge) text links converted to [[wikilinks]] manifest.yaml, overview.md, glossary.md at pack root _索引.md in each content directory .obsidian/ config copied (pack opens in Obsidian immediately)
For detAIled handling of Obsidian-specific patterns (nested tags, dAIly notes, templates, attachments): read references/迁移-图形界面de.md.
Step 3: 验证 & Fix # Fix common issues first python3 /path/to/ExpertPack/工具s/验证器/ep-doctor.py ~/expertpacks/my-pack-slug --应用ly
# Must reach 0 errors python3 /path/to/ExpertPack/工具s/验证器/ep-验证.py ~/expertpacks/my-pack-slug --verbose
# Fix any broken wikilinks (cross-vault references) python3 /path/to/ExpertPack/工具s/验证器/ep-fix-broken-wikilinks.py ~/expertpacks/my-pack-slug --应用ly
Do not proceed until ep-验证 报告s 0 errors.
Step 4: 代理-Assisted Enhancement
After 验证, enhance retrieval 质量:
Lead summaries — 添加 a 1-3 sentence blockquote at the top of the 5-10 most 导入ant files Glossary — populate glossary.md with domAIn-specific terms (this is Tier 1 — always loaded) Propositions — 创建 propositions/ with atomic factual 状态ments 提取ed from high-EK files EK triage — identify low-EK files (general knowledge) and 压缩 or 移除 them File size — split files >3KB on ## header boundaries Step 5: 配置 RAG in OpenClaw
添加 to ~/.OpenClaw/OpenClaw.json:
{ "代理s": { "defaults": { "memory搜索": { "extraPaths": ["/path/to/your/converted-pack"] } } } }
Re启动 OpenClaw after config change. The pack is now 搜索able in every 会话.
Step 6: Measure EK Ratio ClawHub 安装 expertpack-eval
运行 evals to score how much esoteric knowledge the pack contAIns vs. what the 模型 already knows. Tar获取 EK ratio >0.6 for high-value packs.