obsidian-mind

これはレビュー時に保存された抜粋です。完全で最新の内容は外部ソースを確認してください。

---
name: obsidian-mind
description: >
  Route obsidian-mind work into the right mode: install/bootstrap the vault
  (ShardMind vs git clone), the daily standup/dump/wrap-up session loop,
  capture routes for decisions, incidents, 1:1s, and wins, the performance-graph
  review flow (/om-review-brief, /om-self-review, /om-peer-scan), vault
  maintenance and /om-vault-upgrade migration, multi-agent wiring across
  Claude Code, Codex CLI, and Gemini CLI, and optional QMD semantic search.
  obsidian-mind is a specific ready-made Obsidian vault template giving coding
  agents persistent, session-spanning memory through five lifecycle hooks,
  /om-* commands, subagents, and a competency graph — not a generic
  vault-building or wiki-authoring workflow. Triggers on: obsidian-mind,
  om-standup, om-dump, om-wrap-up, om-review-brief, om-self-review,
  om-peer-scan, om-vault-upgrade, brag doc, North Star.md, performance graph,
  competency notes, session lifecycle hooks, shardmind install obsidian-mind.
allowed-tools: Bash Read Write Edit Glob Grep
compatibility: >
  Claude Code has full support (hooks, commands, subagents, memory system
  out of the box). Codex CLI and Gemini CLI get the same hooks and commands
  via .codex/hooks.json / .gemini/settings.json and read AGENTS.md / GEMINI.md
  natively; other agents (Cursor, Windsurf, GitHub Copilot, JetBrains AI) read
  AGENTS.md for vault conventions with hook support varying by agent. Requires
  Obsidian 1.12+ (for CLI support), Node 22+ LTS (hook scripts use
  --experimental-strip-types), and Git. QMD semantic search is optional.
license: MIT
metadata:
  tags: obsidian-mind, obsidian, agent-memory, persistent-memory, session-hooks, performance-review, brag-doc, shardmind, claude-code, codex-cli, gemini-cli, qmd
  version: "1.0"
  source: https://github.com/breferrari/obsidian-mind
---

# obsidian-mind

Use this skill when the real question is **"which obsidian-mind mode does this request need — install, daily session loop, capture, review, maintenance, multi-agent wiring, or semantic search?"**

obsidian-mind ([breferrari/obsidian-mind](https://github.com/breferrari/obsidian-mind)) is **one specific, ready-made Obsidian vault** — not a generic pattern you build from scratch. Cloning or `shardmind install`-ing it gives a coding agent persistent, session-spanning memory through five lifecycle hooks, `/om-*` slash commands, subagents that run in isolated context windows, and a career/performance graph (competency notes, brag docs, review briefs). "Procedural code owns the environment; the agent owns content" — hooks classify, validate, and inject context deterministically, while the agent decides what to write and where.

The job is not to dump the whole command/hook/subagent surface every time. The job is to:
1. classify the request into one mode,
2. point at the exact command, hook, folder, or install step the README documents,
3. route out honestly when the request actually belongs to a neighboring skill.

## When to use this skill

- Installing or bootstrapping the obsidian-mind vault (ShardMind wizard vs `git clone` vs GitHub template)
- Running the daily loop: morning `/om-standup`, in-the-moment capture, end-of-day `/om-wrap-up`
- Filing a decision, incident, 1:1, or win into the right vault note via the classification hooks or `/om-dump`, `/om-capture-1on1`, `/om-incident-capture`
- Prepping for a review cycle: `/om-self-review`, `/om-review-peer`, `/om-review-brief`, `/om-peer-scan`, or reading the competency/backlink graph
- Auditing or migrating a vault: `/om-vault-audit`, `/om-tidy`, `/om-vault-upgrade`, `shardmind adopt`
- Wiring obsidian-mind into Claude Code, Codex CLI, Gemini CLI, or another `AGENTS.md`-reading agent
- Setting up or explaining the optional QMD semantic-search layer (`qmd` CLI, `.mcp.json`, the `om` MCP server)

## When not to use this skill

- **The user wants a generic Obsidian vault, plugin work, CLI automation, JSON Canvas, or Bases patterns with no ob