review-quality
Language-agnostic code review across four pillars: Clarity, Simplicity, Good Practices, and Security. Produces severity-tagged findings (CRITICAL/WARNING/SUGGESTION). Complements audit-cognitive-debt for dead code and duplication. Part of Codecraft plugin. Use when asked to review code quality, audit security, check best practices, or find code smells.
- License 许可
- MIT
- 所属仓库
- dasobral/skills
- 最近更新
- 2026-08-15
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- review-quality
- description
- Language-agnostic code review across four pillars: Clarity, Simplicity, Good Practices, and Security. Produces severity-tagged findings (CRITICAL/WARNING/SUGGESTION). Complements audit-cognitive-debt for dead code and duplication. Part of Codecraft plugin. Use when asked to review code quality, audit security, check best practices, or find code smells.
02 资源文件 9
- 脚本examples/input/user_service.py5.8 KB
- 参考文档examples/output/user_service_review.md20.2 KB
- 脚本examples/user_service.py5.8 KB
- 参考文档references/platform-orchestration.md1.2 KB
- 参考文档references/platform-paths.md1.3 KB
- 参考文档references/review-checklist.md12.7 KB
- 参考文档references/shared-heuristics.md1.6 KB
- 其他SKILL.md.tmpl11.4 KB
- 参考文档templates/review-report.md5.5 KB
03 SKILL.md 正文
Review Quality
Structured, severity-tagged review across four pillars. Focus on code health and maintainability — not functional correctness (that's for tests).
Step 1 — Resolve Scope
- Path argument
- Attached/mentioned files
- Pasted code block
- Working directory glob for source extensions (exclude build/vendor dirs)
Announce: Reviewing scope: <path>
Step 2 — Load Checklist
Read references/review-checklist.md and references/shared-heuristics.md.
Step 3 — Analyze (Four Pillars)
| Pillar | Focus |
|---|---|
| P1 Clarity | Naming, structure, readability |
| P2 Simplicity | Complexity, over-engineering, YAGNI |
| P3 Good Practices | SOLID, DRY, error handling, testability |
| P4 Security | Injection, secrets, deserialization, deps |
Per finding: severity, pillar tag, file:line, problem, consequence, fix snippet.
Severity rules:
- CRITICAL — security vulnerability or production defect
- WARNING — significant maintainability/reliability issue
- SUGGESTION — minor improvement
Step 4 — Report
Use templates/review-report.md. Output to conversation (not a file unless asked).
Include health summary table and rating: CRITICAL / NEEDS WORK / HEALTHY / EXCELLENT.
Step 5 — Delegate for Large Scopes
For >5 files or >2000 LOC, run parallel module reviewers (one per module), then
synthesize. See references/platform-orchestration.md for platform-specific
parallel worker mechanisms.
Rules
- Real issues only; quote bad code with file:line
- Every CRITICAL/WARNING needs a fix snippet
- Read-only — never modify source unless asked
- For cognitive friction (dead code, duplication), suggest
audit-cognitive-debt
04 同仓库更多 Skills
fixture-skill
Fixture skill used to prove trust inventory coverage.
write-conformant-code
Write code in any language that matches project conventions exactly. Reads CODING_REQUIREMENTS.md, prior review output, or built-in defaults before writing. Part of Codecraft pipeline: analyze → write → review → audit. Use when implementing features, functions, or any code that should fit seamlessly into an existing codebase.
test-crypto-interoperability
Record reproducible cryptographic interoperability cases, including negotiation, fallback, sizes, latency, fragmentation, and negative tests.
scientific-platform-architect
Design scientific computing platforms combining HPC kernels with modern infrastructure. Enforces compute-layer separation (Rust/PyTorch/Python), emulator-first thinking, and right-sized infrastructure. Use for MCMC pipelines, neural emulators, platform design, or scientific code review.
rust-systems
Rust systems engineering for daemons, HTTP APIs, and AOS components. Enforces Tokio/Axum async-first, LiteLLM-compatible OpenAI APIs, workspace layouts, tracing, and systemd-compatible daemon design. Part of AOS Stack plugin. Use for .rs files, Cargo.toml, daemons, or Rust orchestrator services.
run-agent-attack-replay
Aggregate isolated agent attack trials with deterministic side-effect assertions, Wilson intervals, and preserved trace evidence.