by akkie76 · Codex Skill · ★ 88
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Featured in: Code Review
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 88 |
| Forks | 0 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 70/100 |
| Open Issues | 3 |
| Last Updated | 2026-10-11 |
| Created | 2026-09-22 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~14k |
Code Review Skills 日本語 Code Review Skills is an evidence-driven code-review workflow for AI coding agents. It helps Codex and Claude Code find actionable defects while avoiding style-only comments and unsupported speculation. Beta: The review methodology and packaging are under evaluation. Expect changes before the first stable release.
Looking for a code-review-skills alternative? If you're comparing code-review-skills with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Self-hosted AI code reviewer with indexed PR reviews, walkthroughs, vulnerability scanning, dependency graphs,
Self-Hosted LLM Code Review Agent for GitLab, Forgejo and GitHub. Local LLM support
Cross-runtime skills for Claude Code, Codex, and multi-agent workflows.
OrcaCode Review — the open code review harness. Multi-model reviews, merge gates, and no markup. Pay only for
Rules and checks that make Claude Code look around a change, not just at the lines it writes: ten questions be
An LLM council that reviews your coding agent's every move
Explore other popular codex skill tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: