一键导入
review-architecture
Architecture pattern compliance review. Evaluates Type-State, Channel-Based, Iterator Pipelines, Actor Model, and Minimal Testing patterns.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Architecture pattern compliance review. Evaluates Type-State, Channel-Based, Iterator Pipelines, Actor Model, and Minimal Testing patterns.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Duplicate code detection using similarity-rs. Identifies refactoring candidates based on semantic similarity.
Duplicate code detection using similarity-rs. Identifies refactoring candidates based on semantic similarity.
Run performance benchmarks with criterion. Compare against baselines and profile hotspots.
Implementation verification - runs format, lint, test, and build checks on the workspace.
Production readiness audit - checks unwrap elimination, error handling, clippy, docs, channel usage, and test count.
Release deployment process for ccswarm. Version update, quality gates, build, tag, publish.
| name | review-architecture |
| description | Architecture pattern compliance review. Evaluates Type-State, Channel-Based, Iterator Pipelines, Actor Model, and Minimal Testing patterns. |
| user-invocable | true |
| context | fork |
| agent | architecture-reviewer |
When subagents are enabled in Codex, prefer delegating this workflow to the architecture-reviewer custom agent.
Review ccswarm architecture pattern compliance based on CLAUDE.md and docs/ARCHITECTURE.md.
Evaluate these 5 patterns:
| Pattern | Search For | Avoid |
|---|---|---|
| Type-State | PhantomData, impl<S: State> | Runtime state enums |
| Channel-Based | mpsc::channel, broadcast::channel | Arc<Mutex<...>> |
| Iterator Pipelines | .iter().filter().map().collect() | Manual for loops |
| Actor Model | Receiver<Message>, recv().await | Shared mutable state |
| Minimal Testing | ~8-10 focused tests | 300+ fragile tests |
Output a JSON report with per-pattern { status, usage_count, score }, overall_score, and recommendations.