Audit saved project learnings against the current codebase to find outdated explanations, overlapping documents, and contradictions. Maintain the documentation with evidence-based updates, consolidation, replacement, or deletion, and deliver a per-document report with committed changes when applicable.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Refresh the repo's captured learnings against the current codebase. Use when auditing stale, overlapping, superseded, or drifted learnings; avoid general refactor, debugging, or code review unless the learnings store is explicit.
설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
Audit the learnings under <root>/solutions/ against the current codebase, apply the maintenance actions the evidence supports, and deliver a complete per-doc report plus committed changes. The report and the corrected document set are the deliverables. The store only compounds value if every doc can be trusted.
Read references/modes.md now. It reads the mode off the arguments and defines what each mode may apply unattended, the stale-marking fallback, the question tools, and the CONCEPTS.md bootstrap.
Two rules hold in both modes. A failed write is recorded as recommended, and the run continues. And a question is asked through the host's blocking tool, or through the numbered-options fallback that reference defines. It is never silently skipped.
The ordinary refresh judges accuracy: is each doc still true and still distinct. It never deletes an accurate doc for holding knowledge the repo states elsewhere. That second judgment, worth, runs only when the user asked for it and confirmed it. It reads the whole scope against the codebase and can delete accurate docs.
Read the invocation arguments for that intent: the user wants the store cleaned up, culled, pruned, trimmed, upgraded, or brought to the capture bar, in any wording, rather than checked for drift. When the intent is present, state the reading back and confirm before any investigation:
You asked to clean up the learnings. Which do you want?
1. Delete or shorten docs the codebase already explains. A doc goes when a test, a code comment, or the instructions file states the same reasoning, and every cut quotes that file. Drift is fixed too. Scope: <scope>.
2. Fix drift only. Stale paths and links, duplicate docs, and guidance the code no longer supports. Nothing accurate is deleted.
On option 1, read references/worth-audit.md before Investigate; it adds the bar, the evidence rule, and the routing. On option 2, or when the intent is absent, do not read that reference and do not apply its test; the accuracy refresh is the whole run. Non-interactive mode cannot confirm, so references/modes.md states what an inferred intent does there.
Resolve <root> when you first compose a <root>/solutions/ path. Pass the resolved <root>/solutions/ path to any subagent, not the config. Every subagent spawn omits the mode parameter, so the user's permission settings apply.
Resolve the CE artifact root <root> before composing any artifact path.
docs_root from <repo-root>/.compound-engineering/config.yaml only (<repo-root> = git rev-parse --show-toplevel). Do not read it from config.local.yaml. Unset -> <root> is docs, exactly as before..git/. Otherwise stop with an error naming docs_root and the value -- never fall back to docs.<root> as the sole artifact location: create it if absent, compose each path as <root>/<subdir> with this skill's own subdirectory, and never also read docs.Candidates are the .md files under <root>/solutions/, excluding README.md and anything under _archived/. A hint that matches nothing never widens the scope. Read references/scope.md for the narrowing strategy, what each mode does on a miss, the empty-store message, triage order, and the README-row cleanup each action carries.
Read references/investigate.md for the staleness dimensions, auto-memory rules, subagent roles, and category-shape notes.
Check each learning against the current codebase, then check the set for overlap, supersession, and contradiction. A contradiction misleads actively, so it outranks individual staleness.
A knowledge-track learning sometimes points at a guidance file it names or links, such as a skill's SKILL.md, a runbook, or an instruction file. Compare only guidance the learning names. Never search the guidance layer for one.
Every investigation subagent's prompt carries that reference's three Subagent prompt clauses verbatim. Two are search tools and auto-memory. The third is this:
If the learning is knowledge-track and names or links a guidance file (a skill's
SKILL.md, a runbook, a root instruction file), read that file and, when it states a different order or a contradictory rule for the same procedure, return both conflicting quotes plus which side current code follows — or that code witnesses neither. Read only guidance the learning names; do not search for one, and do not edit it.
Every doc gets exactly one outcome: Keep, Update, Consolidate, Replace, or Delete. A doc is never archived in place: there is no _archived/, since version history is the archive.
Read references/classify.md before assigning any of them. It defines each outcome's meaning, the Update/Replace boundary, the auto-delete rule and its pre-checks, the relocation and split rules, the retrieval-value test, unverifiable-is-not-false, pattern docs, and what interactive mode asks.
Two boundaries hold whatever the evidence says. This skill never changes product code. A claim about current mechanics follows current code, but independently supported guidance does not become false merely because implementation stopped satisfying it: classify the doc from the guidance evidence and report the implementation conflict as a potential product regression. And when a learning contradicts guidance, the refresh reports that; it must never edit a skill, runbook, or instruction file.
Read references/per-action-flows.md and follow the section matching each doc's classification, one flow per doc. It defines the criteria, the relocation and split procedures, the replacement subagent contract, and citation cleanup.
After the per-doc actions, reconcile the domain terms flagged during investigation with CONCEPTS.md. Read references/concepts-vocabulary.md unconditionally. Its qualifying criteria are non-obvious, so a "nothing qualifies" judgment reached without reading it is a shortcut, not a result.
Edits apply silently in every mode. The report's CONCEPTS.md line records what the scan found, including "scanned, no qualifying terms".
Print the full report as markdown. It is the deliverable, not an internal summary, and in non-interactive mode it is the only one. Keep it self-contained and never abbreviated, split into Applied and Recommended. Read references/report.md for the summary block, per-file detail, and what belongs under Recommended.
Skip if nothing changed. Otherwise stage only the files this refresh modified, and commit in the repo's convention. Read references/commit.md for the per-mode branch decision and the git-failure fallback.
After the report, check that the project's instructions would lead an agent to <root>/solutions/ before working in a documented area. Do this every time: the store only compounds value when agents can find it. Read references/discoverability.md for what the reader must learn, the smallest-addition rule and its tone, the CONCEPTS.md variant, consent versus a report line per mode, and folding a late edit into the commit.
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Monitor an open GitHub pull request over time, respond to review feedback, and address automated check failures. Apply and push fixes, then report whether it appears ready to merge or what still blocks progress.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Develop independent solutions to a defined problem, compare them against shared requirements, and combine useful contributions into a coherent recommendation. An independent assessment and evidence checks support the selection, while unresolved tradeoffs and verification needs remain explicit.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Turn a vague feature idea into clear requirements through dialogue. Define what to build, its scope, and success criteria, then capture the result in a short chat summary or a requirements document ready for implementation planning.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Review code changes or a pull request for bugs, effects on existing behavior, test gaps, and project standards. Receive findings supported by the code and a clear account of review coverage, with local fixes available when explicitly requested.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Save working changes as local Git commits with messages that explain the outcome. Follow the project's commit style, select files explicitly, and split clearly separate changes into a few logical commits when appropriate.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Commit and push code changes, then open a pull request with a clear title and description. You can also draft or update PR descriptions and hand published requests to the follow-up monitoring workflow.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.