メニュー
Use after significant actions (commits, decisions, refactors) or when asked to triage changes — classifies knowledge items as existing or new and provides topology hints for sync and capture.
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 user is new to Autology, asks "how does Autology work", wants to learn about knowledge capture, or requests a guided introduction.
Use after significant project actions — commit, push, PR — or when the team settles on how to build or operate the system: a technology choice, a process, a rule, or a standard. Running close to the action keeps captured knowledge more accurate and complete.
Use to permanently record a project decision, convention, pattern, or known issue into the knowledge base (docs/) — triggers on explicit save intent ("remember this", "save this", "document this"), decision or convention announcements ("we decided", "settled on", "the rule is"), or triage output classifying new items to capture. Distinct from conversational memory — this writes to docs/.
Use whenever the user asks about this project's decisions, architecture, conventions, or how something works in this codebase — do NOT answer from general knowledge, always look it up in docs/. Trigger on questions like "why did we choose X?", "how does Y work here?", "what's our convention for Z?", "what docs reference X?", or any question about this project's specific choices. Also use for explicit /autology:explore-knowledge commands (overview, neighborhood, path). Searches docs/, follows wikilinks, and synthesizes grounded answers from the knowledge base.
Use when existing autology docs/ nodes need syncing or updating — when a doc is out of date after a code change, after refactors, when triage identifies existing nodes to verify, or for periodic full audits. Not for new items (use capture) or knowledge questions (use explore).
| name | triage-knowledge |
| description | Use after significant actions (commits, decisions, refactors) or when asked to triage changes — classifies knowledge items as existing or new and provides topology hints for sync and capture. |
Scan docs/ against conversation context or an action summary. Classify each knowledge item as existing or new, and return topology hints (connected nodes, shared tags) so sync and capture can use them during execution.
From conversation or action summary, identify:
For each item:
For matched nodes:
For unmatched new items:
Autology — Triage Results
Existing (→ sync)
- docs/foo.md — matches [item description] Connected: [[bar]], [[baz]] | Tags: arch, api | Hub (5 links)
- docs/qux.md — matches [item description] Connected: [[foo]] | Tags: convention | Orphan-adjacent
New (→ capture)
- [item description] — no matching node Suggested relations: [[foo]], [[bar]] (shared tags: architecture)
- [item description] — no matching node Suggested relations: none
If no existing docs match any items, use empty-state format:
Autology — Triage Results
No existing matches found. All items classified as new.
New (→ capture)
- [item description] — no matching node Suggested relations: [[foo]] (shared tags: architecture)
| Mistake | Fix |
|---|---|
| Judge relevance by keyword match alone | Read the file to confirm actual relevance |
| Omit topology hints | sync/capture rely on connected/suggested relations — always include |
| Ignore implicit relations | Check tags and content overlap even without wikilinks |
