/review-code
- Plan file (plan.json) - Git diff or modified files list - Test results (if available)
$ npx -y skills add catlog22/maestro-flow --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/review-code
Context preview
What this command does when you run it.
- Plan file (plan.json) - Git diff or modified files list - Test results (if available)
Command definition
review-code.mdCode Review
Inputs
- Plan file (plan.json)
- Git diff or modified files list
- Test results (if available)
Dimensions
| Dimension | Critical Issues | |-----------|----------------| | Quality | Empty catch, any casts, @ts-ignore, console.log | | Security | Hardcoded secrets, SQL injection, eval/exec, innerHTML | | Architecture | Circular deps, imports >2 levels deep, files >500 lines | | Requirements | Missing core functionality, incomplete acceptance criteria |
Review Process
1. Gather modified files from executor's state (team_msg get_state) 2. Read each modified file 3. Score per dimension (0-100%) 4. Classify issues by severity (Critical/High/Medium/Low) 5. Generate verdict (BLOCK/CONDITIONAL/APPROVE)
Output
Write review report to {run_dir}/outputs/review-report.md:
- Per-dimension scores
- Issue list with file:line references
- Verdict with justification
- Recommendations (if CONDITIONAL)
Intent-driven workflow orchestration for multi-agent AI development — adaptive lifecycle engine, self-reinforcing knowledge graph, and visual dashboard for Claude Code, Gemini, Codex & more
Repo: catlog22/maestro-flow
Other commands on maestro-flow.
- /maestro-companion
Quick execution for small tasks — minimal run lifecycle (start + done) with evidence recording. Full LLM capability, scoped to mechanically clear tasks.
Open command - /maestro-fork
Create or sync session worktree for parallel dev
Open command - /maestro-guard
Manage editing boundary restrictions
Open command - /maestro-impeccable
Use when designing, auditing, polishing, improving, or codifying frontend UI — websites, dashboards, landing pages, components, design systems
Open command - /maestro-init
Initialize project with auto state detection
Open command - /maestro-issue
Intent-driven issue lifecycle management — describe what you want in natural language (报告一个 bug / 列出开放 issue / 关掉 ISS-xxx / 关联到 task / 扫描发现问题) and the workflow routes to the right operation. Operates on .workflow/issues/. 知识管理走 /maestro-knowledge;knowhow 沉淀走
Open command

