菜单
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Hmbown/CodeWhale --skill verify命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | verify |
| description | Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification. |
| invocation | model+user |
| aliases-for | check-work |
Use when the user wants proof the real surface works, not only unit tests.
Desktop control with accessibility-first observation and actions, pixel fallback, screenshots, zoom, screen recording, and switching between registered computers. Qualified on macOS; Windows, Linux and HarmonyOS backends are experimental.
Scaffold a local Codewhale plugin bundle with a versioned manifest, namespaced Skills, and an explicit trust review.
Review a change, module, or surface for exploitable defects — trust boundaries, authn/authz, injection, secret exposure, filesystem and network reach, dependency risk. Use when the user asks for a security review, audit, or vulnerability check of concrete code. Not for general code review, lint, or compliance paperwork.