evidence-review

# /evidence-review - Evidence-Controlled Review Skill ## Purpose Create literature-review and review-paper workflows that are traceable from evidence to claim. This skill extends the toolkit's read-note-map-integrate pipeline with stricter evidence-status control, gap mapping, citation-role planning, paragraph-level claim traceability, and overclaim auditing. ## Trigger Words This skill activates on: `evidence review`, `gap review`, `gap map`, `claim traceability`, `overclaim audit`, `review paper`, `scoping review`, `systematic narrative review`, `/evidence-review`. ## Core Rules 1. Keep the central review scope explicit. 2. Separate direct evidence, background evidence, methodological support, workflow/governance support, candidate-only records, unpublished work, and in-progress work. 3. Do not fabricate references, DOI, PMID, sample size, venue, abstracts, results, or claims. 4. Do not treat candidate-only, metadata-only, abstract-only, generated-stub, or manual-review records as full-text evidence. 5. Do not treat adjacent-domain evidence as direct validation of the target domain. 6. Preserve uncertainty and boundary language. 7. Use the project's citation style or placeholder convention. If the project uses review placeholders, preserve `[CITE: CitationKey]`. 8. Draft section by section. Do not assemble a final chapter or paper until section-level controls are clean. ## Workflow ### 1. Scope And Boundary Setup Create a short scope statement with: - central revi...