obsidian-wiki Agent工作流

Install via pip (recommended)

pip install obsidian-wiki
obsidian-wiki setup --vault /path/to/your/digital/brain

obsidian-wiki setup writes the config to ~/.obsidian-wiki/config and installs every wiki skill into all your AI agents (Claude Code, Cursor, Codex, Gemini, Hermes, Pi, and more). Skills are symlinked to the installed package, so pip install -U obsidian-wiki upgrades them everywhere — just re-run obsidian-wiki setup to pick up new skills. Then open a project in your agent and say "set up my wiki".

obsidian-wiki list              # list the bundled skills
obsidian-wiki info              # show install paths, version, and config
obsidian-wiki doctor            # health-check config, vault shape, and installed skills
obsidian-wiki query "rate limiting"  # query the configured vault from the terminal
obsidian-wiki lint              # lint the configured vault for broken links / metadata gaps
obsidian-wiki setup --project . # also drop project-local skills + AGENTS.md into the current repo
obsidian-wiki setup --copy      # copy skill files instead of symlinking

OBSIDIAN_VAULT_PATH is just any directory where you want your digital brain to live, a new empty folder or an existing Obsidian vault. Omit --vault to be prompted (or set it later in ~/.obsidian-wiki/config).

Install via Skills CLI (deprecated)

npx skills add Ar9av/obsidian-wiki

This only installs the markdown skills into the current agent. It does not write ~/.obsidian-wiki/config, install ~/.obsidian-wiki/sync.sh, or wire the global multi-agent bootstrap that obsidian-wiki setup / setup.sh performs.

Use this path only if you intentionally want a partial, agent-local install and are prepared to manage config yourself. For a complete setup, use Install via pip or Install via git clone instead.

Browse the full skill list at skills.sh/ar9av/obsidian-wiki.

Install via git clone

git clone https://github.com/Ar9av/obsidian-wiki.git
cd obsidian-wiki
bash setup.sh

setup.sh asks for your vault (path to your digital brain) path, writes the config to ~/.obsidian-wiki/config, symlinks skills into all your agents, and installs wiki-update globally so you can use it from any project.

Open the project in your agent and say "set up my wiki". That's it.

Manual setup (if you prefer `setup.sh`)

<details> <summary>Claude Code</summary>

Skills are auto-discovered from .claude/skills/. Either run setup.sh or copy .skills/* to .claude/skills/. The CLAUDE.md file at the repo root is automatically loaded as project context.

cd /path/to/obsidian-wiki && claude "set up my wiki"

<details> <summary>Cursor</summary>

Skills are auto-discovered from .cursor/skills/. The .cursor/rules/obsidian-wiki.mdc file provides always-on context. Either run setup.sh or copy .skills/* to .cursor/skills/. Then type /wiki-setup in the chat. </details>

<details> <summary>Windsurf</summary>

Cascade reads rules from .windsurf/rules/ and skills from .windsurf/skills/. Either run setup.sh or copy .skills/* to .windsurf/skills/. Then tell Cascade: "set up my wiki". </details>

<details> <summary>Codex</summary>

Reads AGENTS.md for project context. setup.sh installs skills globally to ~/.codex/skills/. Either run setup.sh or manually symlink .skills/* to ~/.codex/skills/.

cd /path/to/obsidian-wiki && codex "set up my wiki"

<details> <summary>Gemini CLI</summary>

Reads GEMINI.md and discovers global skills from ~/.gemini/skills/. Either run setup.sh or manually symlink .skills/* to ~/.gemini/skills/.

cd /path/to/obsidian-wiki && gemini "set up my wiki"

<details> <summary>Google Antigravity</summary>

Always-on via .agent/rules/ + .agent/workflows/. setup.sh ships both files and symlinks skills into .agents/skills/. The legacy ~/.gemini/antigravity/skills/ path is also wired. </details>

<details> <summary>Kiro IDE/CLI</summary>

Always-on via .kiro/steering/*.md with inclusion: always. setup.sh symlinks .skills/* into both .kiro/skills/ and ~/.kiro/skills/. Invoke with /wiki-ingest, /wiki-query, etc. </details>

<details> <summary>OpenCode / Aider / Factory Droid / Trae</summary>

All read AGENTS.md at the repo root. setup.sh symlinks skills into ~/.agents/skills/ (shared discovery path). Trae also gets ~/.trae/skills/ and ~/.trae-cn/skills/. </details>

<details> <summary>Hermes</summary>

Reads .hermes.md first, then falls back to AGENTS.md. Skills discovered from ~/.hermes/skills/. Run setup.sh or manually symlink .skills/* there.

```bash cd /path/to/obsidian-wiki && hermes "set up my wiki"

then commit and push manually, or re-run setup.sh to get the sync script

**Hourly auto-sync via cron (can be enabled during setup):**

Keep the repo private if your vault contains personal notes. Nothing is sent to any third-party service — your vault lives on your machines and your GitHub account only.

---

Quick Start

Optional: QMD Semantic Search

By default, wiki-ingest and wiki-query use Grep/Glob for search — fully functional, no extra setup. If your vault grows large or you want concept-level matches across your sources, you can plug in QMD, either through MCP or by letting the agent call the local qmd CLI.

Setup:

1. Install QMD. If you want MCP mode, also add it to your MCP config (see the QMD repo for instructions). 2. Index your wiki and/or source documents:

   qmd index --name wiki /path/to/your/vault
   qmd index --name papers /path/to/your/sources
   

   QMD_WIKI_COLLECTION=wiki       # used by wiki-query
   QMD_PAPERS_COLLECTION=papers   # used by wiki-ingest (source discovery)
   QMD_TRANSPORT=mcp              # mcp | cli
   QMD_CLI_SEARCH_MODE=quality    # quality | balanced | fast
   

QMD_TRANSPORT=mcp preserves the original behavior and uses an agent-configured QMD MCP server. QMD_TRANSPORT=cli runs the local qmd command directly. CLI mode defaults to quality, which uses qmd query with reranking for the best relevance. If that is too slow on CPU, set QMD_CLI_SEARCH_MODE=balanced to use qmd query --no-rerank, or fast for a lighter semantic pass.

What changes with QMD enabled:

• wiki-query runs a semantic pass (lex+vec) against your wiki collection before falling back to Grep. Finds conceptually related pages even when the exact terms don't match.
• wiki-ingest queries your papers collection before writing a new page — surfaces related sources, spots contradictions, and decides whether to create a new page or merge into an existing one.

Both skills degrade gracefully: if QMD_WIKI_COLLECTION / QMD_PAPERS_COLLECTION are not set, they skip the QMD step silently and use Grep instead.

Local CLI utilities

The Python package also ships a few local commands for inspection and maintenance:

obsidian-wiki doctor --json
obsidian-wiki query "what do I know about MCP security?"
obsidian-wiki lint --strict
obsidian-wiki graph-query /path/to/vault "transformer architecture"
obsidian-wiki graph-analyse /path/to/vault --pretty

Use doctor to catch broken setup, stale installs, or malformed vault state. Use query and lint when you want fast local answers without going through an agent prompt. The lower-level graph-query, graph-analyse, batch-plan, cache-*, and ast-extract commands are still available for automation and debugging.

Browser Capture Extension

This repo includes a zero-build Chrome extension at extensions/brain-capture/ for saving web pages and selected text into your vault's _raw/ folder.

To install it:

1. Open chrome://extensions
2. Enable Developer mode
3. Click Load unpacked
4. Select extensions/brain-capture

To find the configured _raw folder from this repo:

awk -F= '/^OBSIDIAN_VAULT_PATH=/{print $2 "/_raw"; exit}' "$(git rev-parse --show-toplevel)/.env"

After capturing pages into _raw/, ask your agent to process them:

/wiki-ingest promote my raw pages

wiki-ingest will read each _raw/ capture, distill it into the right wiki pages, update the manifest/index/log, and remove the promoted raw files so they are not processed twice.

---