菜单
Use Open Second Brain to read, write, and maintain an agent-owned second brain in an Obsidian-compatible Markdown vault. The agent owns one top-level directory (`Brain/`). User-authored notes live wherever the operator names them and are read-only inputs when listed in `notes.read_paths`.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Use when adding, renaming, reviewing, or explaining Brain schema tokens, aliases, prefixes, link types, extractability, or expert routing in Open Second Brain vaults.
Use when the user explicitly mentions codegraph, asks structural code questions such as callers/callees/impact, asks where a symbol is defined, asks what breaks if a symbol changes, or asks for an architectural overview of a code repository. Skip for prose-only or vault-only questions.
Bring Open Second Brain semantic search online — embedding API key, sqlite-vec extension, first reindex, optional periodic refresh. INVOKE when the user mentions "embeddings", "semantic search", "vector index", or after `o2b search check` reports `vec_extension: unavailable`, `embedding_key: missing`, or any line in its `recommendations:` block. SKIP when the user is asking conceptual questions about embeddings or comparing providers without intent to set up — answer those directly.
Append-only operational event logging for Open Second Brain. Daily Markdown notes are the default backend. INVOKE this skill (and call `event_log_append`) immediately after producing any durable artifact in the current turn — code shipped, bug fixed, refactor merged, config or deployment change, instruction-file edit (CLAUDE.md / AGENTS.md / plugin docs / system prompts), content artifact created (post, draft, documentation, marketing copy, release notes), research or investigation that produced a concrete finding or decision worth recalling later, or discovery of an external fact (CLI behaviour change, API quirk, undocumented edge case) that future sessions should know. SKIP for pure discussion, exploration, read-only queries, and planning that has not yet produced an artifact. If unsure, ask "would future-me want to find this in the log by searching for it later?" — if yes, log it. WRITE the `message` in the same natural language the user has been speaking with you in this session — never default to English
基于 SOC 职业分类
| name | open-second-brain |
| description | Use Open Second Brain to read, write, and maintain an agent-owned second brain in an Obsidian-compatible Markdown vault. The agent owns one top-level directory (`Brain/`). User-authored notes live wherever the operator names them and are read-only inputs when listed in `notes.read_paths`. |
Use this skill when a user asks an agent to use, configure, inspect, or maintain Open Second Brain.
Open Second Brain owns one top-level directory in the vault: Brain/. Everything the agent writes lives under it.
Brain/ - agent-writable observing memory. Taste signals, accreted preferences (unconfirmed → confirmed → retired), evidence log, snapshots. Operations go through MCP tools brain_feedback, brain_apply_evidence, brain_dream, brain_brief, brain_query, brain_doctor - see the brain-memory skill for the calling protocol. CLI counterparts: o2b brain *.notes.read_paths in Brain/_brain.yaml; the agent never writes to them.Brain/. Never write to user-authored note folders.Brain/log/, preferences live in Brain/preferences/.o2b brain ..., o2b doctor, o2b status) over guessing file paths.o2b status or second_brain_status MCP tool.Brain/_BRAIN.md - this is the per-vault contract for agents.brain_feedback (see the brain-memory skill).brain_apply_evidence (see the brain-memory skill).second_brain_query.If a write operation might affect anything outside the Brain/ directory, ask for explicit confirmation. When in doubt, prefer Brain/.
brain-memory skill — when and how to call brain_feedback / brain_apply_evidence.Brain/_BRAIN.md (in each vault) — operating manual for that vault, generated by o2b brain init.docs/plans/2026-05-15-brain-observing-memory.md (in the repo) — full design.