Use when an evaluation coordinator needs normalized findings from target artifacts and research evidence.
Paths: File paths (
shared/,references/,../ln-*) are relative to skills repo root.
Type: L3 Worker Category: 3XX Planning
MANDATORY READ: Load shared/references/evaluation_worker_runtime_contract.md, shared/references/evaluation_summary_contract.md
MANDATORY READ: Load ../ln-310-multi-agent-validator/references/phase2_research_audit.md, ../ln-310-multi-agent-validator/references/penalty_points.md
MANDATORY READ: Load ../ln-310-multi-agent-validator/references/premortem_validation.md, ../ln-310-multi-agent-validator/references/cross_reference_validation.md
mode=story: calculate penalty points across 30 criteria per phase2_research_audit.mdmode=plan_review|context: evaluate criteria #5, #6, #21, #28 only (no penalty accumulation)mode=story: full pipeline — pre-mortem, cross-reference, penalty points across 30 criteria, build fix planmode=plan_review|context: applicability check, stack detection, evaluate criteria #5 (standards), #6 (library versions), #21 (alternatives), #28 (library features) only, normalize findings without penalty accumulationRuntime family:
evaluation-worker-runtimeRequired manifest fields:
identifierphase_ordersummary_kind=review-findingsoperation=findingsRecommended phase_order:
PHASE_0_CONFIGPHASE_1_LOAD_TARGETPHASE_2_PREMORTEM (mode=story, complexity >= Medium)PHASE_3_CROSS_REFERENCE (mode=story, multi-story Epic)PHASE_4_CRITERIA_AUDITPHASE_5_PENALTY_CALCULATION (mode=story only)PHASE_6_NORMALIZE_FINDINGSPHASE_7_WRITE_SUMMARYPHASE_8_SELF_CHECKLoad runtime manifest, target identifiers, and any linked research artifact paths.
Load only the target artifacts needed for the review scope.
Execute pre-mortem analysis per premortem_validation.md:
[pre-mortem] tag, Confidence=LOW.Execute cross-reference analysis per cross_reference_validation.md:
list_issues(project=Epic.id).mode=story: evaluate all 30 criteria against Story/Tasks per phase2_research_audit.md Auto-Fix Actions Reference.mode=plan_review|context: evaluate criteria #5, #6, #21, #28 only (standards + solution groups).phase2_research_audit.md (CRITICAL=10, HIGH=5, MEDIUM=3, LOW=1).penalty_points.md Calculation Rules.penalty_points.md Report Format.Each finding should prefer structured fields such as:
idseveritycategorysubjectevidencerecommendationEmit summary_kind=review-findings.
Payload must include:
worker=ln-312statusoperation=findingswarningsPrefer these fields when available:
findingsmetrics.penalty_total (mode=story)metrics.criteria_violated (list of criterion numbers)metrics.fix_plan (array of {criterion, action, severity})metrics.premortem_summary (when executed)metrics.cross_reference_summary (when executed)penalty_points.md rules (mode=story).pass=true only after summary write.review-findings summary writtenVersion: 1.0.0 Last Updated: 2026-04-10