codex-ab

仓库创建 2026年2月12日最近提交 4 小时前SkillHot 收录 4 小时前

▸ 精选理由

用于验证分面审查方法是否比整体审查发现更多真实问题。

这个 Skill 做什么

对分支 diff 做整体与分维度的 Codex 审查对比实验，并分类汇报发现与结论。

对分支 diff 做 A/B 比较：一个整体的 Codex 审查对上三条按维度（比如安全）分开的审查，逐条比对发现并分类出真问题或误报。适合在分支刚生成、任何 Codex 审查还没跑之前用来评估审查策略效果。输出会把每条发现和整体审查的差异以及最终判断整理成结论供团队参考。

▸ 展开 SKILL.md 英文原文

Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.

开发编程代码审查A/B 实验评估方法Claude Code

505

Stars

Forks

仓库内 Skill

+35

7 日增星

安装 / 使用

给你的 Agent 一句话（通用）

帮我安装这个 skill：https://raw.githubusercontent.com/oliver-kriska/claude-elixir-phoenix/main/.claude/skills/codex-ab/SKILL.md

或 curl 直取 SKILL.md

curl -fsSL "https://raw.githubusercontent.com/oliver-kriska/claude-elixir-phoenix/main/.claude/skills/codex-ab/SKILL.md"

SKILL.MD 节选查看完整文件 ↗

# Codex Panel A/B (contributor instrument — verdict decided)

Answer one question with evidence: **do dimension-focused codex passes find
real issues that one holistic `codex exec review` misses?** Runs both on the
same diff, then classifies every focused finding against the holistic pass.

> **DECIDED 2026-07-10 after 4 runs (2 fresh): panel KILLED.** Fresh-only
> 1 real miss / 1 false positive plus one zero-value run at 4× cost —
> real misses did not outnumber FPs. Kept as contributor tooling (NOT
> distributed) for one possible retest: a UI-heavy diff with a single
> extra liveview-focused pass (2× cost). Scoreboard:
> `.claude/research/2026-07-03-codex-review-integration.md` §7.

## Usa

via SKILL·HOT · 数据来自 GitHub 公开信息 · 原文版权归作者所有