yuxuanhui
91861565bb
- Introduced API guidelines for interface contracts and request handling. - Added design tokens usage guidelines for consistent styling across the project. - Established DTO guidelines for defining request parameters and response data types. - Created frontend structure guidelines to clarify directory organization and code placement rules. - Compiled a comprehensive frontend development guideline document covering various aspects of the development process. - Implemented quality guidelines to ensure code maintainability and adherence to best practices.
33 lines
1.4 KiB
Markdown
33 lines
1.4 KiB
Markdown
---
|
||
id: AI-RD-WORKFLOW
|
||
type: workspace-index
|
||
status: draft
|
||
created: 2026-06-29
|
||
---
|
||
|
||
# AI 研发工作流
|
||
|
||
目标：建设一套 `spec + skill` 双驱动的 AI 研发工作流，让每个需求从原始输入到需求分析、研发需求、详细设计、编码、测试都能被追踪、复用和迭代。
|
||
|
||
## 目录
|
||
|
||
- `00-meta/`：术语、路线图、文档模型、命名规范。
|
||
- `10-standards/`：生命周期、评审门禁、角色边界、追踪规则。
|
||
- `20-skills/`：面向 Codex/AI agent 的 skill 源草稿。
|
||
- `30-templates/`：各阶段文档模板。
|
||
- `40-workflows/`：PM、SE、RD、AI 开发工作流。
|
||
- `50-cases/`：真实或示例需求实例，每个 case 保留完整链路。
|
||
- `60-evaluations/`：skill 评测用例、prompt run、复盘。
|
||
- `90-archive/`：废弃或历史版本资料。
|
||
|
||
## 迭代原则
|
||
|
||
1. 先稳定文档关系，再扩展具体模板字段。
|
||
2. 每个 skill 先以草稿方式在本目录维护，稳定后再安装到 `$CODEX_HOME/skills` 或 `~/.codex/skills`。
|
||
3. 每个真实需求都放入 `50-cases/REQ-yyyymmdd-nnn-name/`，不要把产物散落在规范目录里。
|
||
4. 所有产物必须通过 frontmatter 记录 `id`、`case_id`、`type`、`stage`、`source_ids`、`derived_ids`。
|
||
|
||
## 推荐下一步
|
||
|
||
先完善 `00-meta/artifact-model.md` 和 `10-standards/traceability.md`，再从 `20-skills/pm-requirement-review/SKILL.md` 开始打磨第一个可用 skill。
|