メニュー
Use when navigating a repo's code or its Atlas — locating a definition/usage/file, tracing an import, or finding which zone/decision/spec explains something. Reach here before reflexive grep+Read.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when the user wants to adopt this knowledge base, onboard a brownfield vault, act on "atlas adopt reported unclassified notes", or migrate existing docs/mind into atlas. Deterministic adopt first; this skill classifies leftover notes and proposes zone cards without stamping.
Use when finishing a change in a repo that has an Atlas — before ending the session or opening a PR, to keep the vault's zone cards, stamps, and ledger entries in sync with the code just changed.
Use when an Atlas vault is empty or near-empty (0–2 zones after atlas init) — bootstrap 4–8 seeded zone cards from a real codebase analysis. Also use for "seed the mind", "initial zones", "first map pass", "bootstrap atlas", or atlas-fleet seed-empty.
Use when the user wants to update atlas, an atlas update is available, doctor or status reports a version nudge / pending migrations, or they ask to bring the vault to latest. Deterministic migrate first; this skill handles AI-merge of locally edited vendored files.
Use when authoring or editing an Atlas note (zone, decision, spec, plan, idea, debt, pillar) — the summary and section structure determine what a retrieval engine surfaces later.
| name | atlas-nav |
| description | Use when navigating a repo's code or its Atlas — locating a definition/usage/file, tracing an import, or finding which zone/decision/spec explains something. Reach here before reflexive grep+Read. |
Default to this repo's configured retrieval engine over grep+read-whole-file
— same correctness, far fewer tokens read. If this repo uses the ctx-search
adapter (adapters/ctx-search/), that engine is ctx_search (the
context-mode MCP tool), kept fresh automatically by a SessionStart hook.
Otherwise use whatever retrieval engine the repo documents, or fall back to
grep — this skill's routing logic applies either way.
With ctx_search: call it with NO project param — it defaults to the
repo (cwd), which is where both buckets are indexed. Results are tagged
Source: code:… / Source: atlas:…; narrow with source: code /
source: atlas. Folders listed in atlas.config.json →
retrieval.excludeFromSearch (default drafts/, visuals/) are never in
the index — don't expect hits from them.
| Intent | Tool |
|---|---|
| Known file path | Read directly — no search |
| Exact symbol ("where is X defined / who calls X") | LSP / go-to-definition, if available |
| Broad ("where is X / which note explains Y / find the invariant / which spec") | Configured retrieval engine (ctx_search if this repo has the adapter) |
| Engine result empty/wrong, or an exhaustive match list is needed | grep + Read fallback |
Atlas hits (Source: atlas:…) — the snippet usually captures the
zone/decision summary inline; no follow-up read needed for orientation.
Code hits (Source: code:…) — use the engine to RANK, then Read the top
~3 whole hit files; snippets alone miss the answer span.
node scripts/nav-refresh-index.mjs --force, then retry.