Use when reviewing React components, hooks, state management, rendering performance, or upgrade plans where evidence-backed critique with security/new-hire/ops perspectives is required.
Run a harsh-critic style review with React-specific checks, explicit evidence requirements, and context-driven audience perspectives.
Use react-critic when you need to:
The router (js-critic-router) dispatches here when it detects: React imports, JSX/TSX with hooks (useState, useEffect, etc.), React component patterns — without Next.js or React Native signals.
Use external skills as references only.
Rules:
Confirm review target and scope.
Make 3-5 pre-commitment predictions about likely React failure points before deep review.
Run protocol phases in order: verification, multi-perspective analysis, explicit gap analysis, synthesis.
If reviewing plans/specs, also run plan-specific checks: key assumptions extraction, pre-mortem, dependency audit, ambiguity scan, feasibility check, rollback analysis, and devil's-advocate challenge for major decisions.
Run mandatory self-audit before finalizing findings:
Open Questions (unscored).Run Realist Check on every surviving CRITICAL/MAJOR finding:
SECURITY EXPLOITABILITY GATE (mandatory for all security-related findings):
[UNCONFIRMED] and move it to Open Questions. Do NOT leave unconfirmed security findings in scored sections.Recalibration rules:
Mitigated by: ... rationale.Apply shared JS and React rubrics.
Activate audiences based on audience matrix.
Load at most 2-3 specialist external skills from the routing map.
Return structured verdict with evidence.
Use this exact top-level structure:
VERDICT: [REJECT | REVISE | ACCEPT-WITH-RESERVATIONS | ACCEPT]Overall AssessmentPre-commitment PredictionsCritical FindingsMajor FindingsMinor FindingsWhat's MissingAmbiguity Risks (plan reviews only)Multi-Perspective NotesVerdict JustificationOpen Questions (unscored)Rules:
file:line or backtick-quoted artifact reference).None.Open Questions only.Verdict Justification, state whether escalation to adversarial review happened and why.Always run:
Context-driven (activate when triggered):
Perspective notes must appear in Multi-Perspective Notes.
Always check these before final verdict:
Open Questions.