JPeetz/agent-skills / skills/code-quality/clean-pro-review-gates
clean-pro-review-gates
FlaggedUse this skill when reviewing any AI-generated or modified code, tests, docs, or infrastructure before merging. Applies a 5-gate review framework — code quality (15 LLM failure modes), tests, docs, security (OWASP Top 10:2025/CWE Top 25/LLM Top 10), and CI/CD/container/IaC hardening — with each gate mapping violations to published research on how LLMs systematically fail.
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 1.9 KB |
| LICENSE | other | 1.1 KB |
| SKILL.md | skill md | 12.9 KB |
| evals/evals.json | config | 10.4 KB |
| references/code-quality-gate.md | markdown | 5.9 KB |
| references/docs-review-gate.md | markdown | 3.1 KB |
| references/infra-hardening-gate.md | markdown | 5.0 KB |
| references/security-review-gate.md | markdown | 6.8 KB |
| references/security-scan-notes.md | markdown | 1.1 KB |
| references/test-review-gate.md | markdown | 4.3 KB |
CHANGELOG.md
View on GitHub# Changelog
## Unreleased
### Changed
- Description rewritten to be trigger-first ("Use this skill when ...") and under 1024 chars per the agentskills.io spec.
## v1.0.0 (2026-09-07)
### Initial Release — Combined 5-Gate Review Framework
This is the initial packaged release of clean-pro-review-gates, adapted from Khaled Ghallab's clean-pro-skills repository. The five original standalone skills (clean-code-pro, clean-test-pro, clean-docs-pro, clean-security-pro, clean-infra-pro) have been:
- **Combined** into a single unified meta-skill with a common framework, severity guide, and cross-gate interaction model
- **Improved** with explicit cross-gate interaction tracking — findings that span multiple gates are now called out
- **Enhanced** with a standard 5-step workflow showing exactly how to scope, run, report, and self-check each gate
- **Adapted** with Hermes-compatible YAML frontmatter, tags, and related_skills references
- **Validated** with eval test cases covering all 5 gates
### Original Work
Based on https://github.com/Khaled-Ghallab/clean-pro-skills (MIT © Khaled Ghallab):
- clean-code-pro — production code review with 15 LLM failure modes
- clean-test-pro — test code review with 10 rules + LLM-app testing
- clean-docs-pro — documentation accuracy verification
- clean-security-pro — security review mapped to OWASP/CWE/LLM Top 10
- clean-infra-pro — CI/CD, container, and IaC hardening
### Key Improvements vs. Originals
- Cross-gate interaction table added (SKILL.md)
- Standardized 5-step review workflow with scoping, execution, and reporting phases
- Self-check checklists consolidated per gate for quick verification
- added evals/evals.json with 15 test cases covering all gates
- Hermes metadata with tags and related_skills references
- AI failure modes tables added to each gate reference file
- Severity guide unified across all gates (Critical/High/Medium/Low)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |