zhouyilab-workflow

SkillDocs & knowledge

Lets your agent follow the right scope and workflow rules when coding, documenting, or reviewing in the ZhouYiLab repo.

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the zhouyilab-workflow skill

About this skill

Determines scope, tool selection, and delivery boundaries when performing code, documentation, or review tasks in the ZhouYiLab repository.

What this skill tells your AI

The instructions your AI receives, as published by banderzhm/zhouyilab in skills/zhouyilab-workflow/SKILL.md and read by ahel’s review.

优先使用 mcp-Headroom；先检查工具是否可用，不可用则说明并采用本地工具，不编造调用结果。
中文沟通。开始前检查 git status，保留用户已有改动；搜索优先 rg，文件编辑使用 apply_patch。格式化及运行生成器不属于手工文件改写。
诊断、审查任务先给出代码依据，不擅自实现；实施任务按用户范围完成代码、测试与必要文档，不能只修改输出报告掩盖生产逻辑问题。
实施前按本次涉及的职责查阅对应 skill，遇到现有实现与规范冲突时只处理本次相关范围，不能借规范清理无关模块。
不因用户说“规范性优先”便重写第三方子模块或丢弃本地修改；新增依赖、改变公共契约需说明影响。提交、推送、发布按当前用户授权执行。
交付列明实际改动、已运行的构建/测试与未验证范围。生成报告、编译成功、契约验证、排盘对照分别描述，不能宣称有限用例证明所有算法正确。

Advanced