メニュー
Use when verifying one appraisal lane for one candidate bundle revision before editorial approval or publication.
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 producing a cross-record synthesis report for one domain or bounded set of taxonomy scope units after baseline review or review update records have been published.
Use when deciding whether an appraised candidate bundle should receive comments, changes requested, rejection, approval, or publication.
Use when checking an already scoped research unit for material changes since the latest baseline-review pass, publication, or review-update pass.
Use when drafting or revising paper-facing literature-review prose from already-collected research records, especially background sections that need inline source citations for substantive claims.
Use when initializing baseline coverage for one bounded research scope unit by staging source, artifact, finding, and claim records into a candidate bundle.
Use when deciding what needs attention now in the active lit-review-studio domain, including coverage gaps, bundle readiness, source-access issues, source-summary gaps, and thin claim support.
| name | evidence-appraisal |
| description | Use when verifying one appraisal lane for one candidate bundle revision before editorial approval or publication. |
Appraise one lane for one candidate bundle revision. Produce a structured evidence appraisal; do not revise the staged records during the same pass.
lit-review-studio.config.json and the active LIT_REVIEW_STUDIO_DOMAIN value.domain-packs/<domain-id>/appraisal-lanes.v1.jsondomain-packs/<domain-id>/evidence-ladder.v1.jsondomain-packs/<domain-id>/extraction-schema.v1.jsondomain-packs/<domain-id>/skills/evidence-appraisal.mddata/candidate-bundles/<bundle-id>.jsonLIT_REVIEW_STUDIO_DOMAIN=<domain-id> npm run research:bundle -- status --bundle <bundle-id>
LIT_REVIEW_STUDIO_DOMAIN=<domain-id> npm run research:appraise-evidence -- status --bundle <bundle-id>
LIT_REVIEW_STUDIO_DOMAIN=<domain-id> npm run research:appraise-evidence -- scaffold --bundle <bundle-id> --lane <lane>
verdict, blocking, summary, and findings based on the appraisal. Use needs_human_judgment when the source cannot be checked reliably.LIT_REVIEW_STUDIO_DOMAIN=<domain-id> npm run research:appraise-evidence -- apply --file <draft-path>
data/evidence-appraisals/<appraisal-id>.json record for the lane.evidence_appraisal_ids on the candidate bundle.