{
  "markdown": "# Plan Review Skill\n\nA Claude Code skill that runs multi-perspective plan review using parallel VP agents to identify blockers, anti-patterns, conflicts, and regressions before execution.\n\n## Overview\n\nPlan Review spawns three specialized AI agents — VP Product, VP Engineering, and VP Design — to simultaneously review implementation plans, design docs, architecture proposals, and wave plans. Each agent evaluates the plan through their domain lens. Findings are consolidated, ranked by severity, and presented for your approval before any changes are applied.\n\n## Features\n\n- **Parallel VP analysis** — Three perspectives reviewed simultaneously\n- **Four issue categories** — Blockers, Anti-patterns, Conflicts, Regressions\n- **Severity ranking** — Critical, High, Medium, Low with action guidance\n- **Approval workflow** — Review all findings before plan edits are applied\n- **Guided decision** — Ask, then execute: never modifies files without consent\n\n## Usage\n\n```bash\n# Review a plan file\n/plan-review-skill path/to/your-plan.md\n```\n\nOr trigger naturally:\n\n```\n\"Review this plan for blockers and conflicts\"\n\"Get VP feedback on the implementation plan\"\n\"Run a stakeholder review on this design doc\"\n```\n\n## VP Perspectives\n\n| VP Role | Focus Areas |\n|---------|-------------|\n| **VP Product** | User impact, scope creep, dependencies, timelines |\n| **VP Engineering** | Technical debt, anti-patterns, architecture conflicts, regressions |\n| **VP Design** | UX consistency, accessibility, design system alignment |\n\n## Issue Severity Guide\n\n| Severity | Action |\n|----------|--------|\n| Critical | Must address before proceeding |\n| High | Should address before proceeding |\n| Medium | Address in this iteration |\n| Low | Address if time permits |\n\n## Installation\n\nVia Skillsmith MCP:\n\n```\ninstall_skill smith-horn/plan-review-skill\n```\n\nOr manually copy this directory to `~/.claude/skills/plan-review-skill/`.\n\n## Configuration\n\nOptional environment variables:\n\n| Variable | Description |\n|----------|-------------|\n| `PLAN_REVIEW_STRICT` | If `true`, require all Critical issues resolved before approval |\n| `PLAN_REVIEW_AUTO_APPROVE` | If `true`, auto-approve Low severity changes |\n\nCustom VP prompts via `.claude/plan-review-config.json` in your project root.\n\n## Integration\n\nWorks with other Claude Code skills:\n\n| Skill | Integration |\n|-------|-------------|\n| `wave-planner` | Review wave plans before execution |\n| `launchpad` | Integrated as Stage 2 of the end-to-end pipeline |\n| `governance` | Standards audit runs after plan approval |\n| `hive-mind-execution` | Review phase integrates plan-review |\n",
  "bytes": 2623,
  "sha": "7c822e15666fef5b7d8b2c62367525d7da137e5048479c3ba4fb359991888278",
  "repo_slug": "wrsmith108/plan-review-skill",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_wrsmith108_plan_review_skill_plan_review_fe74abe7/readme"
}