使用 Obsidian Vault Pipeline 自动化整理知识库。 **触发场景：** - 用户说 "运行 WIGS 流程"、"整理 Obsidian Vault"、"处理知识库" - 用户说 "提取 Evergreen"、"更新 MOC"、"运行 Pipeline" - 用户提到 "整理笔记"、"知识管理"、"处理书签" - 用户说 "质检"、"质量检查"、"检查一致性" **Vault 位置设置：** 默认使用当前工作目录作为 vault 根目录，或通过 `--vault-dir` 参数指定。 只要用户提到 Obsidian、知识管理、WIGS、Pipeline、Evergreen、MOC 等关键词，就立即使用此 skill。 --- # Obsidian Vault Pipeline Skill ## 概述 此 skill 用于帮助用户运行 Obsidian Vault Pipeline 自动化知识管理流程。 ## 安装 ```bash pip install obsidian-vault-pipeline ``` ## Vault 位置设置 Pipeline 自动检测 vault 位置（按优先级）： 1. **当前工作目录** - 默认使用 `cwd` 2. ** `--vault-dir` 参数** - 显式指定 3. **环境变量** - `VAULT_DIR` **最佳实践：** ```bash cd /path/to/my-vault # 进入 vault 目录 ovp --check # 检查环境 ovp --full # 运行完整 pipeline ``` ## 可用命令 | 命令 | 说明 | |------|------| | `ovp --check` | 检查环境配置 | | `ovp --init` | 初始化配置（交互式） | | `ovp --full` | 运行完整 pipeline | | `ovp-article --process-inbox` | 处理 50-Inbox/01-Raw/ 中的文章 | | `ovp-evergreen --recent 7` | 提取最近7天的 Evergreen 笔记 | | `ovp-moc --scan` | 扫描并更新 MOC 索引 | | `ovp-quality --recent 7` | 质量检查 | ## 标准操作流程 ### 1. 首次使用 ```bash # 进入 vault 目录 cd my-vault # 检查环境 ovp --check # 如果提示未配置，运行初始化 ovp --init ``` ### 2. 日常处理 ```bash # 放入新文章到 50-Inbox/01-Raw/ cp article.md my-vault/50-Inbox/01-Raw/ # 运行 pipeline ovp --full ``` ### 3. WIGS 完整性检查 ```bash # 5层一致性检查 ./60-Logs/scripts/check-consistency.sh # 自动修复低风险问题 ./60-Logs/scripts/repair.sh --auto ``` ## 配置文件 在 vault 根目录创建 `.env`： ```bash AUTO_VAULT_API_KEY=your_api_key AUTO_VAULT_API_BASE=https://api.minimaxi.com/anthropic AUTO_VAULT_MODEL=minimax/MiniMax-M2.5 ``` ## 触发词映射 | 用户说 | 执行命令 | |--------|----------| | "运行 WIGS 流程" | `./60-Logs/scripts/check-consistency.sh` | | "整理 Obsidian" | `ovp --full` | | "处理文章" | `ovp-article --process-inbox` | | "提取 Evergreen" | `ovp-evergreen --recent 7` | | "更新 MOC" | `ovp-moc --scan` | | "质量检查" | `ovp-quality --recent 7` | | "检查一致性" | `./60-Logs/scripts/check-consistency.sh` | ## 处理流程 ``` 50-Inbox/01-Raw/ → ovp-article → 20-Areas/深度解读 20-Areas/ →
Fast vault Q&A — quick lookups, decision history, blocker status, doc search. Uses QMD hybrid search when available, falls back to vault grep. Use for "/ask what did we decide about auth?" or "/ask who's blocked?".
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.
- 📁 commands/
- 📁 hooks/
- 📁 references/
- 📄 architecture.md
- 📄 install.sh
- 📄 LICENSE
Operate any Obsidian vault as a living second brain. Use this skill whenever the user asks Claude to read, write, update, search, or manage their Obsidian vault — including saving notes from conversation, creating daily entries, updating kanban boards, logging dev work, managing people notes, capturing decisions, tracking deals, or maintaining any vault structure. Also triggers when the user wants to bootstrap a new vault from scratch, run a vault health check, or drop a _CLAUDE.md into their vault so all Claude surfaces share the same operating rules. Use proactively whenever the conversation produces information worth preserving (decisions, people met, projects started, tasks completed, lessons learned). --- # Obsidian Second Brain > Claude operates your Obsidian vault as a living OS — not a note-taking app. > Everything worth remembering gets saved. Every update propagates everywhere it belongs. --- ## Quick Start ### 0. Verify MCP is available This skill uses the [`mcp-obsidian`](https://github.com/calclavia/mcp-obsidian) MCP server. The tool names below (`get_file_contents`, `list_files_in_vault`, `search`, `append_content`, `write_file`) are specific to that package. If you are using a different Obsidian MCP server, tool names may differ — check that server's documentation. **If MCP vault tools are unavailable:** fall back to reading and writing files directly via the filesystem using standard file tools (Read, Write, Edit, Glob). The vault is plain markdown files — all operations can be done without MCP, just more verbosely. Tell the user: > "The obsidian-vault MCP server isn't connected — I'll read/write vault files directly instead. To enable MCP for faster vault access, run: `claude mcp add obsidian-vault -s user -- npx -y mcp-obsidian \"/path/to/your/vault\"`" ### 1. First time in a vault → read `_CLAUDE.md` Before doing anything in a vault, check if `_CLAUDE.md` exists at the vault root: ``` get_file_contents("_CLAUDE.md") ```
- 📁 assets/
- 📁 references/
- 📄 SKILL.md
Conducts a structured gap assessment of an organization's readiness against ISO 42001:2023 (AI Management System standard). Runs an interview-style evaluation across all mandatory clauses (4-10) and applicable Annex A controls. Produces a scored gap assessment report saved to the vault, a draft Statement of Applicability, and a prioritized list of gaps to address before certification. Requires a vault created by /setup-iso42001-vault.
- 📁 references/
- 📄 README.md
- 📄 SKILL.md
Interact with the Obsidian vault using only the `obsidian` CLI command via Bash. Use this skill when the user wants to read, create, edit, search, append, or manage notes in their Obsidian vault.
Use when the user says "add a facade", "new tool", "extend vault", "add brain feature", "new skill", or "extend agent". For extending the agent's own internals with vault-first knowledge gathering. --- # Agent Dev — Vault-First Internal Development Develop the agent's own internals with the vault as the primary source of truth. The vault knows more about the agent than any code scan or model training data. Always search the vault first, extract maximum context, and only then touch code. ## When to Use Any time the work target is the agent's own codebase: adding tools, extending facades, modifying vault operations, brain features, skills, or transport. Not for projects that merely _use_ the agent. ## Core Principle **Vault first. Before code. Before training data. Always.** The vault is the authoritative source for how the agent works. Do not rely on general knowledge from training data — it is outdated and lacks project-specific decisions. Do not scan the codebase to understand architecture — the vault already has it. ## Orchestration Sequence ### Step 1: Search the Vault (MANDATORY — before anything else) Before reading any source file, before making any plan, before offering any advice: ```
