🔧 chore(templates): align agent templates and docs
- drop implementation-plan template and references - add AGENT_RULES.local.md precedence in templates - add plan meta guidance and CN updates
This commit is contained in:
parent
efb93f14c1
commit
eb75036b64
165
AGENTS.md
165
AGENTS.md
|
|
@ -1,146 +1,143 @@
|
||||||
# Agent Instructions (playbook)
|
# 代理指引(playbook)
|
||||||
|
|
||||||
> About the special nature of the playbook repo:
|
> 关于 playbook 仓库的特殊性:
|
||||||
>
|
>
|
||||||
> - In the playbook repo: ruleset templates live in `rulesets/`
|
> - 在 playbook 仓库中:规则集模板位于 `rulesets/`
|
||||||
> - In target projects: after sync from playbook, rulesets live in `.agents/`
|
> - 在目标项目中:同步后规则集位于 `.agents/`
|
||||||
> - AI agents read `.agents/` in the target project root (generated by sync_standards.sh)
|
> - AI 代理读取目标项目根目录的 `.agents/`(由 sync_standards.sh 生成)
|
||||||
>
|
>
|
||||||
> This document applies to target projects. The playbook repo itself has no
|
> 本文适用于目标项目。playbook 仓库自身没有源代码,不需要 AI 代理规则。
|
||||||
> source code and does not need AI agent rules.
|
|
||||||
|
|
||||||
Use the rules under `.agents/` as the source of truth:
|
以 `.agents/` 下规则为准:
|
||||||
|
|
||||||
- Entry: `.agents/index.md`
|
- 入口:`.agents/index.md`
|
||||||
- Language rules: `.agents/tsl/index.md`, `.agents/cpp/index.md`,
|
- 语言规则:`.agents/tsl/index.md`、`.agents/cpp/index.md`、
|
||||||
`.agents/python/index.md`, `.agents/markdown/index.md`
|
`.agents/python/index.md`、`.agents/markdown/index.md`
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## Three-layer architecture (layered knowledge base)
|
## 三层架构(分层知识库)
|
||||||
|
|
||||||
This repo organizes agent rules and knowledge into three layers:
|
本仓库将代理规则与知识分为三层:
|
||||||
|
|
||||||
### Layer 1: `.agents/` (minimal hard rules, <= 50 lines per language)
|
### Layer 1: `.agents/`(最小硬规则,每种语言 ≤ 50 行)
|
||||||
|
|
||||||
- Load: automatic, always in context
|
- 加载:自动,始终在上下文中
|
||||||
- Content: hard constraints and safety red lines
|
- 内容:硬约束与安全红线
|
||||||
- Role: quick decisions on what can or cannot be done
|
- 作用:快速判断能做/不能做
|
||||||
- Size control: TSL 44 lines | Python 45 lines | C++ 47 lines | Markdown 31 lines
|
- 规模控制:TSL 44 行 | Python 45 行 | C++ 47 行 | Markdown 31 行
|
||||||
|
|
||||||
### Layer 2: `codex/skills/` (on-demand, 100-1000 lines per skill)
|
### Layer 2: `codex/skills/`(按需加载,每个 skill 100-1000 行)
|
||||||
|
|
||||||
- Load: triggered by `$<skill-name>` or inferred by the agent
|
- 加载:由 `$<skill-name>` 触发或由代理判定
|
||||||
- Content: how-to guidance, best practices, workflows
|
- 内容:操作指南、最佳实践、工作流
|
||||||
- Role: detailed guidance on how to do the task
|
- 作用:指导具体怎么做
|
||||||
|
|
||||||
Key skills:
|
关键技能:
|
||||||
|
|
||||||
- `$tsl-guide` - progressive TSL syntax training (basic/advanced/functions/best practices)
|
- `$tsl-guide` - TSL 渐进式语法训练(基础/高级/函数/最佳实践)
|
||||||
- `$commit-message` - commit message convention
|
- `$commit-message` - 提交信息规范
|
||||||
- `$style-cleanup` - formatting/style cleanup
|
- `$style-cleanup` - 格式与风格整理
|
||||||
- `$bulk-refactor-workflow` - safe bulk refactor workflow
|
- `$bulk-refactor-workflow` - 安全批量重构流程
|
||||||
|
|
||||||
### Layer 3: `docs/` (authoritative static docs)
|
### Layer 3: `docs/`(权威静态文档)
|
||||||
|
|
||||||
- Load: on-demand for specific sections
|
- 加载:按需读取特定章节
|
||||||
- Content: full language manuals, code style, toolchain config
|
- 内容:完整语言手册、代码风格、工具链配置
|
||||||
- Role: the final authority
|
- 作用:最终权威
|
||||||
- Conflict handling: when rules conflict, follow `docs/`
|
- 冲突处理:规则冲突时以 `docs/` 为准
|
||||||
|
|
||||||
Note: the function library is split under `docs/tsl/syntax_book/function/`.
|
注:函数库拆分在 `docs/tsl/syntax_book/function/` 下。
|
||||||
Do not load the whole directory. Load only the needed fragments.
|
不要加载整个目录,只加载需要的片段。
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## Usage scenarios
|
## 使用场景
|
||||||
|
|
||||||
### Scenario 1: write a simple TSL function
|
### 场景 1:编写简单的 TSL 函数
|
||||||
|
|
||||||
```text
|
```text
|
||||||
1. Auto read .agents/tsl/index.md (44 lines)
|
1. 自动读取 .agents/tsl/index.md(44 行)
|
||||||
2. Trigger $tsl-guide, load SKILL.md (192 lines)
|
2. 触发 $tsl-guide,加载 SKILL.md(192 行)
|
||||||
3. Generate code
|
3. 生成代码
|
||||||
|
|
||||||
Token cost: ~6,000 tokens
|
Token 消耗:~6,000 tokens
|
||||||
```
|
```
|
||||||
|
|
||||||
### Scenario 2: write a TSL class
|
### 场景 2:编写 TSL 类
|
||||||
|
|
||||||
```text
|
```text
|
||||||
1. Auto read .agents/tsl/index.md (44 lines)
|
1. 自动读取 .agents/tsl/index.md(44 行)
|
||||||
2. Trigger $tsl-guide, load SKILL.md + references/advanced.md
|
2. 触发 $tsl-guide,加载 SKILL.md + references/advanced.md
|
||||||
3. Generate code
|
3. 生成代码
|
||||||
|
|
||||||
Token cost: ~10,000 tokens
|
Token 消耗:~10,000 tokens
|
||||||
```
|
```
|
||||||
|
|
||||||
### Scenario 3: find a TSL function library entry
|
### 场景 3:查询 TSL 函数库条目
|
||||||
|
|
||||||
```text
|
```text
|
||||||
1. Auto read .agents/tsl/index.md (44 lines)
|
1. 自动读取 .agents/tsl/index.md(44 行)
|
||||||
2. Trigger $tsl-guide, load references/functions_index.md
|
2. 触发 $tsl-guide,加载 references/functions_index.md
|
||||||
3. Use rg to locate the function fragment
|
3. 使用 rg 定位函数片段
|
||||||
4. Return the answer
|
4. 返回答案
|
||||||
|
|
||||||
Token cost: ~8,000 tokens
|
Token 消耗:~8,000 tokens
|
||||||
```
|
```
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## Performance metrics
|
## 性能指标
|
||||||
|
|
||||||
| Metric | Before | Now | Improvement |
|
| 指标 | 之前 | 现在 | 改善 |
|
||||||
| ------------------- | ---------- | --------- | ----------- |
|
| --------------- | -------- | -------- | ---- |
|
||||||
| .agents size | ~500 lines | 168 lines | -66% |
|
| .agents 规模 | ~500 行 | 168 行 | -66% |
|
||||||
| Persistent tokens | ~12,500 | ~4,200 | -66% |
|
| 持久化 tokens | ~12,500 | ~4,200 | -66% |
|
||||||
| Avg scenario tokens | ~12,500 | ~10,500 | -16% |
|
| 场景平均 tokens | ~12,500 | ~10,500 | -16% |
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## Maintenance principles
|
## 维护原则
|
||||||
|
|
||||||
### .agents/ modification rules
|
### .agents/ 修改规则
|
||||||
|
|
||||||
Do:
|
可做:
|
||||||
|
|
||||||
- Add new security vulnerability types
|
- 增加新的安全漏洞类型
|
||||||
- Update core conventions (file names, format rules)
|
- 更新核心约定(文件名、格式规则)
|
||||||
- Add non-negotiable hard constraints
|
- 添加不可妥协的硬性约束
|
||||||
|
|
||||||
Do not:
|
不可做:
|
||||||
|
|
||||||
- Add recommended best practices (put them in a skill)
|
- 添加推荐型最佳实践(放到 skill)
|
||||||
- Add detailed syntax explanations (put them in a skill or docs)
|
- 添加详细语法解释(放到 skill 或 docs)
|
||||||
- Exceed the 50-line limit (split into skills)
|
- 超过 50 行限制(拆分为 skill)
|
||||||
|
|
||||||
### Skills creation rules
|
### Skills 创建规则
|
||||||
|
|
||||||
Do:
|
可做:
|
||||||
|
|
||||||
- Add new workflows (e.g., code-review)
|
- 增加新流程(如 code-review)
|
||||||
- Teach a new language from scratch (e.g., tsl-guide)
|
- 从零教授新语言(如 tsl-guide)
|
||||||
- Add cross-language common knowledge (e.g., style-cleanup)
|
- 添加跨语言通用知识(如 style-cleanup)
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## FAQ
|
## FAQ
|
||||||
|
|
||||||
Q: Why is .agents/ so small?
|
Q:为什么 .agents 这么小?
|
||||||
A: Because it is loaded every conversation. Keeping it under 50 lines saves
|
A:因为它会在每次对话加载。控制在 50 行内可减少约 71% 的持久 token 消耗。
|
||||||
about 71% of persistent token usage.
|
|
||||||
|
|
||||||
Q: Why does TSL need a dedicated tsl-guide skill?
|
Q:为什么 TSL 需要专门的 tsl-guide?
|
||||||
A: TSL is not pre-trained. The agent needs from-scratch teaching.
|
A:TSL 非预训练语言,需要从零教学。
|
||||||
|
|
||||||
Q: What if my project has custom conventions?
|
Q:如果项目有自定义约定怎么办?
|
||||||
A: Fork playbook into the project (git subtree) and modify the project's
|
A:将 playbook 以 git subtree 方式引入项目,并修改项目的 `.agents/`。
|
||||||
`.agents/`.
|
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
## Related docs
|
## 相关文档
|
||||||
|
|
||||||
- Skills usage guide: `SKILLS.md`
|
- Skills 使用指南:`SKILLS.md`
|
||||||
- Development standards: `docs/index.md`
|
- 开发规范:`docs/index.md`
|
||||||
- Project README: `README.md`
|
- 项目 README:`README.md`
|
||||||
|
|
|
||||||
|
|
@ -45,7 +45,7 @@ Playbook:TSL(`.tsl`/`.tsf`)+ C++ + Python + Markdown(代码格式化)
|
||||||
|
|
||||||
`templates/` 目录除了语言配置模板外,还包含 AI 代理工作环境的项目架构模板:
|
`templates/` 目录除了语言配置模板外,还包含 AI 代理工作环境的项目架构模板:
|
||||||
|
|
||||||
- `templates/memory-bank/`:项目上下文文档模板(project-brief、tech-stack、architecture、progress、decisions、implementation-plan)
|
- `templates/memory-bank/`:项目上下文文档模板(project-brief、tech-stack、architecture、progress、decisions)
|
||||||
- `templates/prompts/`:工作流程模板(agent-behavior、clarify、verify)
|
- `templates/prompts/`:工作流程模板(agent-behavior、clarify、verify)
|
||||||
- `templates/AGENTS.template.md`:路由中心模板(项目主入口)
|
- `templates/AGENTS.template.md`:路由中心模板(项目主入口)
|
||||||
- `templates/AGENT_RULES.template.md`:执行流程模板
|
- `templates/AGENT_RULES.template.md`:执行流程模板
|
||||||
|
|
|
||||||
|
|
@ -3,7 +3,7 @@
|
||||||
#### 内容
|
#### 内容
|
||||||
|
|
||||||
- TSL的Web支持
|
- TSL的Web支持
|
||||||
- .Web Tools
|
- Web 工具(.Web Tools)
|
||||||
|
|
||||||
#### TSL的Web支持
|
#### TSL的Web支持
|
||||||
|
|
||||||
|
|
@ -289,7 +289,7 @@ http://www.webiste.com/foo.tsl?name=jack&email=jack@abc.com
|
||||||
|
|
||||||
可以用上面的方式提取数据
|
可以用上面的方式提取数据
|
||||||
|
|
||||||
#### .Web Tools
|
#### Web 工具(.Web Tools)
|
||||||
|
|
||||||
##### 内容
|
##### 内容
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -1,12 +1,13 @@
|
||||||
# Agent Instructions
|
# 代理指引
|
||||||
|
|
||||||
<!-- playbook:framework:start -->
|
<!-- playbook:framework:start -->
|
||||||
|
|
||||||
## 规则优先级
|
## 规则优先级
|
||||||
|
|
||||||
1. 系统/开发者指令与安全约束
|
1. 系统/开发者指令与安全约束
|
||||||
2. 仓库规则:`.agents/` 与本文件
|
2. 项目私有规则:`AGENT_RULES.local.md`(如存在)
|
||||||
3. `AGENT_RULES.md` - 执行流程
|
3. 仓库规则:`.agents/` 与本文件
|
||||||
|
4. `AGENT_RULES.md` - 执行流程
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
|
|
@ -24,6 +25,7 @@
|
||||||
|
|
||||||
### 核心规则
|
### 核心规则
|
||||||
|
|
||||||
|
- **项目私有规则**:[AGENT_RULES.local.md](./AGENT_RULES.local.md)
|
||||||
- **执行流程**:[AGENT_RULES.md](./AGENT_RULES.md)
|
- **执行流程**:[AGENT_RULES.md](./AGENT_RULES.md)
|
||||||
- **AI 行为规范**:[docs/prompts/system/agent-behavior.md](docs/prompts/system/agent-behavior.md)
|
- **AI 行为规范**:[docs/prompts/system/agent-behavior.md](docs/prompts/system/agent-behavior.md)
|
||||||
|
|
||||||
|
|
@ -34,7 +36,6 @@
|
||||||
- **架构设计**:[memory-bank/architecture.md](memory-bank/architecture.md)
|
- **架构设计**:[memory-bank/architecture.md](memory-bank/architecture.md)
|
||||||
- **进度追踪**:[memory-bank/progress.md](memory-bank/progress.md)
|
- **进度追踪**:[memory-bank/progress.md](memory-bank/progress.md)
|
||||||
- **架构决策**:[memory-bank/decisions.md](memory-bank/decisions.md)
|
- **架构决策**:[memory-bank/decisions.md](memory-bank/decisions.md)
|
||||||
- **实施计划**:[memory-bank/implementation-plan.md](memory-bank/implementation-plan.md)
|
|
||||||
|
|
||||||
### 工作流程
|
### 工作流程
|
||||||
|
|
||||||
|
|
@ -48,10 +49,11 @@
|
||||||
|
|
||||||
**AI 应该做的**:
|
**AI 应该做的**:
|
||||||
|
|
||||||
1. 读取 [AGENT_RULES.md](./AGENT_RULES.md)
|
1. 读取 [AGENT_RULES.local.md](./AGENT_RULES.local.md)(如存在)
|
||||||
2. 读取 [memory-bank/](memory-bank/) 核心文档
|
2. 读取 [AGENT_RULES.md](./AGENT_RULES.md)
|
||||||
3. 读取 [docs/prompts/system/agent-behavior.md](docs/prompts/system/agent-behavior.md)
|
3. 读取 [memory-bank/](memory-bank/) 核心文档
|
||||||
4. 查看 `docs/plans/` 下最新计划(如有)或 `memory-bank/implementation-plan.md`
|
4. 读取 [docs/prompts/system/agent-behavior.md](docs/prompts/system/agent-behavior.md)
|
||||||
|
5. 查看 `docs/plans/` 下最新计划(如有)
|
||||||
<!-- playbook:framework:end -->
|
<!-- playbook:framework:end -->
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
|
||||||
|
|
@ -5,18 +5,19 @@
|
||||||
## 优先级
|
## 优先级
|
||||||
|
|
||||||
1. 系统/开发者指令与安全约束
|
1. 系统/开发者指令与安全约束
|
||||||
2. 仓库规则:`.agents/` 与 `AGENTS.md`
|
2. 项目私有规则:`AGENT_RULES.local.md`(如存在)
|
||||||
3. 本文件
|
3. 仓库规则:`.agents/` 与 `AGENTS.md`
|
||||||
|
4. 本文件
|
||||||
|
|
||||||
## 上下文加载(每次会话开始)
|
## 上下文加载(每次会话开始)
|
||||||
|
|
||||||
**必读文档**(按顺序):
|
**必读文档**(按顺序):
|
||||||
|
|
||||||
1. `memory-bank/project-brief.md` - 项目定位、边界、约束
|
1. `AGENT_RULES.local.md` - 项目私有规则(如存在,优先级高于本文件)
|
||||||
2. `memory-bank/tech-stack.md` - 技术栈、工具链
|
2. `memory-bank/project-brief.md` - 项目定位、边界、约束
|
||||||
3. `memory-bank/architecture.md` - 架构设计、模块职责
|
3. `memory-bank/tech-stack.md` - 技术栈、工具链
|
||||||
4. `docs/plans/` - 最新实施计划(如存在)
|
4. `memory-bank/architecture.md` - 架构设计、模块职责
|
||||||
5. `memory-bank/implementation-plan.md` - 当前实施计划(如存在)
|
5. `docs/plans/` - 最新实施计划(如存在)
|
||||||
|
|
||||||
**目的**:让 AI 快速理解项目全貌,避免重复解释。
|
**目的**:让 AI 快速理解项目全貌,避免重复解释。
|
||||||
|
|
||||||
|
|
@ -33,6 +34,13 @@
|
||||||
|
|
||||||
## Plan 规则
|
## Plan 规则
|
||||||
|
|
||||||
|
- **Plan Meta 必填**:Plan 头部 `---` 之后、Task 1 之前插入 `## Plan Meta`,包含:
|
||||||
|
- `Plan Group`(归类任务)
|
||||||
|
- `Parent Plan`(上层/集成计划链接)
|
||||||
|
- `Verification Scope`(local 或 integration)
|
||||||
|
- `Verification Gate`(must-pass)
|
||||||
|
- **不允许中断任务**:Plan 中不应包含必然失败或依赖未确认的信息;未确认项必须在 brainstorming 阶段解决后再产出 Plan
|
||||||
|
- **验证必须可通过**:Plan 内验证应为当前阶段可通过的局部验证;需要集成验证的内容放入上层/集成 Plan
|
||||||
- 不因等待确认而中断可执行步骤;待确认事项在回复中列出
|
- 不因等待确认而中断可执行步骤;待确认事项在回复中列出
|
||||||
- 执行并验证该 Plan 中所有可执行的子任务
|
- 执行并验证该 Plan 中所有可执行的子任务
|
||||||
- 若因缺少信息/决策而阻塞:在 `memory-bank/progress.md` 记录阻塞原因
|
- 若因缺少信息/决策而阻塞:在 `memory-bank/progress.md` 记录阻塞原因
|
||||||
|
|
|
||||||
|
|
@ -14,8 +14,7 @@ templates/
|
||||||
│ ├── tech-stack.template.md
|
│ ├── tech-stack.template.md
|
||||||
│ ├── architecture.template.md
|
│ ├── architecture.template.md
|
||||||
│ ├── progress.template.md
|
│ ├── progress.template.md
|
||||||
│ ├── decisions.template.md
|
│ └── decisions.template.md
|
||||||
│ └── implementation-plan.template.md
|
|
||||||
├── prompts/ # 提示词库模板
|
├── prompts/ # 提示词库模板
|
||||||
│ ├── README.md
|
│ ├── README.md
|
||||||
│ ├── system/
|
│ ├── system/
|
||||||
|
|
@ -82,13 +81,13 @@ scripts\sync_templates.bat -project-root C:\path\to\project -full
|
||||||
project/
|
project/
|
||||||
├── AGENTS.md # 路由中心(主入口)
|
├── AGENTS.md # 路由中心(主入口)
|
||||||
├── AGENT_RULES.md # 执行流程
|
├── AGENT_RULES.md # 执行流程
|
||||||
|
├── AGENT_RULES.local.md # 项目私有规则(可选,手动维护)
|
||||||
├── memory-bank/ # 项目上下文
|
├── memory-bank/ # 项目上下文
|
||||||
│ ├── project-brief.md
|
│ ├── project-brief.md
|
||||||
│ ├── tech-stack.md
|
│ ├── tech-stack.md
|
||||||
│ ├── architecture.md
|
│ ├── architecture.md
|
||||||
│ ├── progress.md
|
│ ├── progress.md
|
||||||
│ ├── decisions.md
|
│ └── decisions.md
|
||||||
│ └── implementation-plan.md
|
|
||||||
└── docs/prompts/ # 提示词库
|
└── docs/prompts/ # 提示词库
|
||||||
├── README.md
|
├── README.md
|
||||||
├── system/agent-behavior.md
|
├── system/agent-behavior.md
|
||||||
|
|
@ -123,7 +122,6 @@ project/
|
||||||
| `architecture.template.md` | 架构设计、模块职责 |
|
| `architecture.template.md` | 架构设计、模块职责 |
|
||||||
| `progress.template.md` | 开发进度追踪 |
|
| `progress.template.md` | 开发进度追踪 |
|
||||||
| `decisions.template.md` | 架构决策记录(ADR) |
|
| `decisions.template.md` | 架构决策记录(ADR) |
|
||||||
| `implementation-plan.template.md` | 当前实施计划 |
|
|
||||||
|
|
||||||
### prompts/
|
### prompts/
|
||||||
|
|
||||||
|
|
@ -138,6 +136,31 @@ project/
|
||||||
### AGENT_RULES.template.md
|
### AGENT_RULES.template.md
|
||||||
|
|
||||||
执行流程规范,定义 AI 的工作循环和约束。
|
执行流程规范,定义 AI 的工作循环和约束。
|
||||||
|
如需项目私有规则,建议创建 `AGENT_RULES.local.md`,其优先级高于 `AGENT_RULES.md`,
|
||||||
|
且不会被同步脚本覆盖。
|
||||||
|
|
||||||
|
### 示例:不跑测试的计划提示词
|
||||||
|
|
||||||
|
当你需要修改代码但暂时不运行测试时,可用以下提示词生成“可执行且不失败”的实施计划:
|
||||||
|
|
||||||
|
```text
|
||||||
|
你是 Codex。先使用 $brainstorming。
|
||||||
|
目标:修改 <模块/功能>,细节如下:<你的需求>
|
||||||
|
约束:
|
||||||
|
- 不跑任何测试(test/ci),但允许做可通过的局部验证(格式化/静态检查/人工 diff)。
|
||||||
|
- Plan 不能包含任何必然失败或未确认的任务;所有依赖必须在 brainstorming 阶段确认清楚。
|
||||||
|
- 采用 writing-plans 的固定头部格式,且在 `---` 之后追加 `## Plan Meta`:
|
||||||
|
- Plan Group: <X>
|
||||||
|
- Parent Plan: <docs/plans/...-design.md>
|
||||||
|
- Verification Scope: local
|
||||||
|
- Verification Gate: must-pass
|
||||||
|
|
||||||
|
流程:
|
||||||
|
1) 先完成 brainstorming,并输出设计文档 `docs/plans/YYYY-MM-DD-<topic>-design.md`。
|
||||||
|
2) 询问我“是否进入 `docs/plans/` 实施计划编写阶段”,确认后使用 writing-plans 生成实现计划。
|
||||||
|
3) 实现计划内明确标注每步要改的文件与命令;验证步骤只包含可通过的局部验证,不包含测试。
|
||||||
|
4) 执行计划并更新 `memory-bank/progress.md`。
|
||||||
|
```
|
||||||
|
|
||||||
### AGENTS.template.md
|
### AGENTS.template.md
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -1,91 +0,0 @@
|
||||||
# 当前实施计划
|
|
||||||
|
|
||||||
## 计划状态
|
|
||||||
|
|
||||||
**计划名称**: {{PLAN_NAME}}
|
|
||||||
**开始时间**: {{START_DATE}}
|
|
||||||
**当前状态**: 进行中 / 已完成 / 已暂停
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## 目标
|
|
||||||
|
|
||||||
{{PLAN_GOAL}}
|
|
||||||
|
|
||||||
**成功标准**:
|
|
||||||
|
|
||||||
- [ ] {{SUCCESS_CRITERIA_1}}
|
|
||||||
- [ ] {{SUCCESS_CRITERIA_2}}
|
|
||||||
- [ ] {{SUCCESS_CRITERIA_3}}
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## 实施步骤
|
|
||||||
|
|
||||||
### 阶段 1: {{PHASE_1_NAME}}
|
|
||||||
|
|
||||||
#### 步骤 1.1: {{STEP_1_1}}
|
|
||||||
|
|
||||||
- [ ] {{TASK_1_1_1}}
|
|
||||||
- [ ] {{TASK_1_1_2}}
|
|
||||||
|
|
||||||
**验证**: {{VERIFICATION_1_1}}
|
|
||||||
|
|
||||||
#### 步骤 1.2: {{STEP_1_2}}
|
|
||||||
|
|
||||||
- [ ] {{TASK_1_2_1}}
|
|
||||||
- [ ] {{TASK_1_2_2}}
|
|
||||||
|
|
||||||
**验证**: {{VERIFICATION_1_2}}
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
### 阶段 2: {{PHASE_2_NAME}}
|
|
||||||
|
|
||||||
#### 步骤 2.1: {{STEP_2_1}}
|
|
||||||
|
|
||||||
- [ ] {{TASK_2_1_1}}
|
|
||||||
- [ ] {{TASK_2_1_2}}
|
|
||||||
|
|
||||||
**验证**: {{VERIFICATION_2_1}}
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## 当前进度
|
|
||||||
|
|
||||||
### 已完成
|
|
||||||
|
|
||||||
- {{COMPLETED_PHASE}}
|
|
||||||
|
|
||||||
### 进行中
|
|
||||||
|
|
||||||
- {{IN_PROGRESS_STEP}}
|
|
||||||
|
|
||||||
### 待开始
|
|
||||||
|
|
||||||
- {{PENDING_STEP}}
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## 风险与问题
|
|
||||||
|
|
||||||
### 风险
|
|
||||||
|
|
||||||
1. **{{RISK_1}}**
|
|
||||||
- 风险:{{RISK_1_DESC}}
|
|
||||||
- 缓解:{{RISK_1_MITIGATION}}
|
|
||||||
|
|
||||||
### 已解决的问题
|
|
||||||
|
|
||||||
1. {{RESOLVED_ISSUE_1}}
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## 下一步行动
|
|
||||||
|
|
||||||
- [ ] {{NEXT_ACTION_1}}
|
|
||||||
- [ ] {{NEXT_ACTION_2}}
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
**最后更新**:{{DATE}}
|
|
||||||
|
|
@ -79,7 +79,7 @@ echo ""
|
||||||
echo "🔍 验证 memory-bank 模板"
|
echo "🔍 验证 memory-bank 模板"
|
||||||
|
|
||||||
MEMORY_BANK_DIR="$TEMPLATES_DIR/memory-bank"
|
MEMORY_BANK_DIR="$TEMPLATES_DIR/memory-bank"
|
||||||
for name in project-brief tech-stack architecture progress decisions implementation-plan; do
|
for name in project-brief tech-stack architecture progress decisions; do
|
||||||
validate_file_exists "$MEMORY_BANK_DIR/$name.template.md" "memory-bank/$name.template.md"
|
validate_file_exists "$MEMORY_BANK_DIR/$name.template.md" "memory-bank/$name.template.md"
|
||||||
done
|
done
|
||||||
|
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue