← ClaudeAtlas

review-researchlisted

This skill should be used for RESEARCH.md artifact reviewer — validates that all findings cite evidence, confidence levels are justified, pitfalls are actionable, and recommendations are concrete and implementable
alo-exp/silver-bullet · ★ 5 · AI & Automation · score 76
Install: claude install-skill alo-exp/silver-bullet
# review-research RESEARCH.md reviewer skill. Implements the artifact-reviewer framework interface to validate a RESEARCH.md file against SB research quality criteria. Returns structured PASS/ISSUES_FOUND findings. ## Loading Rules This reviewer MUST load the following before executing any review: - `@skills/artifact-reviewer/rules/reviewer-interface.md` — interface contract (input/output shape, prohibitions) - `@skills/artifact-reviewer/rules/review-loop.md` — 2-pass loop mechanism and audit trail format ## Usage ``` /artifact-reviewer <research-path> ``` Or invoke directly: ``` /review-research <research-path> ``` ## Input | Field | Type | Required | Description | |-------|------|----------|-------------| | artifact_path | string | YES | Path to RESEARCH.md file to review | | source_inputs | string[] | NO | Optional paths (e.g., phase CONTEXT.md for key questions) | | review_context | string | NO | Additional context string (e.g., phase name for key question matching) | ## Quality Criteria Read the artifact at `artifact_path` completely before evaluating any criterion. Validate every criterion explicitly — do NOT skip sections. ### QC-1: Key Questions Are Addressed (when review_context available) If `review_context` or `source_inputs` includes a phase CONTEXT.md with a list of key research questions, every listed key question MUST have a corresponding finding or section in the RESEARCH.md that addresses it. **If any key question is unanswered:** Emit ISSUE fin