Killer-Skills Review
Decision support comes first. Repository text comes second.
This page remains useful for teams, but Killer-Skills treats it as reference material instead of a primary organic landing page.
适用场景： Ideal for AI agents that need read agents.md, .codex/config.toml, docs/codex integration 2026-03-22.md, and docs/codex. 本地化技能摘要： # Codex Audit Use this skill when the task is about Codex itself: official capability research, repo integration review, hooks/rules coverage, profile strategy, or stale Codex guidance. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
核心价值
推荐说明： codex-audit helps agents read agents.md, .codex/config.toml, docs/codex integration 2026-03-22.md, and docs/codex. Codex Audit Use this skill when the task is about Codex itself: official capability research
适用 Agent 类型
适用场景： Ideal for AI agents that need read agents.md, .codex/config.toml, docs/codex integration 2026-03-22.md, and docs/codex.
↓ 赋予的主要能力 · codex-audit
! 使用限制与门槛
- 限制说明： If the task spans many files or requires a repo-process review, spawn workflow architect.
- 限制说明： Do not confuse shell approval rules with general writing-policy enforcement; those live in AGENTS.md, hooks, and skills.
- 限制说明： Do not confuse shell approval rules with general writing-policy enforcement; those live in AGENTS.md, hooks, and skills
Why this page is reference-only
- - Current locale does not satisfy the locale-governance contract.
- - The underlying skill quality score is below the review floor.
Source Boundary
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
先决定动作，再继续看上游仓库材料
Killer-Skills 的主价值不应该停在“帮你打开仓库说明”，而是先帮你判断这项技能是否值得安装、是否应该回到可信集合复核，以及是否已经进入工作流落地阶段。
Browser Sandbox Environment
⚡️ Ready to unleash?
Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.
常见问题与安装步骤
以下问题与步骤与页面结构化数据保持一致，便于搜索引擎理解页面内容。
? FAQ
codex-audit 是什么？
适用场景： Ideal for AI agents that need read agents.md, .codex/config.toml, docs/codex integration 2026-03-22.md, and docs/codex. 本地化技能摘要： # Codex Audit Use this skill when the task is about Codex itself: official capability research, repo integration review, hooks/rules coverage, profile strategy, or stale Codex guidance. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.
如何安装 codex-audit？
运行命令：npx killer-skills add necatiincekara/Quanvolutional-Neural-Network。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。
codex-audit 适用于哪些场景？
典型场景包括：适用任务： Applying Read AGENTS.md, .codex/config.toml, docs/CODEX INTEGRATION 2026-03-22.md, and docs/CODEX、适用任务： Applying Verify Codex capability claims against official OpenAI Codex docs before making recommendations、适用任务： Applying Build a matrix with:。
codex-audit 支持哪些 IDE 或 Agent？
该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。
codex-audit 有哪些限制？
限制说明： If the task spans many files or requires a repo-process review, spawn workflow architect.；限制说明： Do not confuse shell approval rules with general writing-policy enforcement; those live in AGENTS.md, hooks, and skills.；限制说明： Do not confuse shell approval rules with general writing-policy enforcement; those live in AGENTS.md, hooks, and skills。
↓ 安装步骤
-
1. 打开终端
在你的项目目录中打开终端或命令行。
-
2. 执行安装命令
运行：npx killer-skills add necatiincekara/Quanvolutional-Neural-Network。CLI 会自动识别 IDE 或 AI Agent 并完成配置。
-
3. 开始使用技能
codex-audit 已启用，可立即在当前项目中调用。
! 参考页模式
此页面仍可作为安装与查阅参考，但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论，再决定是否继续查看上游仓库说明。
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
codex-audit
安装 codex-audit，这是一款面向AI agent workflows and automation的 AI Agent Skill。查看评审结论、使用场景与安装路径。
