plan-editing-conventions by closedloop-ai/claude-plugins
npx skills add https://github.com/closedloop-ai/claude-plugins --skill plan-editing-conventions创建和修改以 plan.json 格式存储的实施计划的规范。
relative/path.ts)计划以 plan.json 格式存储,包含以下关键字段:
{
"content": "# Implementation Plan\n\n## Stage 1: ...\n\n### T-1.1: Task Title\n...",
"acceptanceCriteria": [...],
"pendingTasks": [...],
"completedTasks": [...],
"manualTasks": [...],
"openQuestions": [...],
"answeredQuestions": [...],
"gaps": [...],
"amendments": [...]
}
content : 完整的 Markdown 计划,作为带有转义换行符(\n)的 JSON 字符串。这是人类可读的计划文本。广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
重要:content 字段是一个 JSON 字符串。编辑时:
\n 转义序列表示换行,而不是字面换行符code:extract-plan-md 技能同步 plan.md任务使用 T-X.Y ID 规范,其中 X 是阶段编号,Y 是该阶段内的任务编号。
计划内容中的每个任务应遵循以下结构:
### T-X.Y: [任务标题]
**文件:** `path/to/file.ext`
**复杂度:** S | M | L
**验收标准引用:** AC-001, AC-002
**描述:** 简要描述此任务完成的内容。
**实施细节:**
[根据情况包含以下一项或多项:]
**映射表:** (用于分发/转换任务)
| 源 | 目标 | 备注 |
|--------|--------|-------|
| category_a | target_file_a.md | 章节: XYZ |
| category_b | target_file_b.md | 章节: ABC |
**算法:** (用于逻辑繁重的任务)
1. 从 `source_path` 加载输入
2. 使用 `specific_method()` 解析
3. 对每个项目:
a. 使用模式 X 进行转换
b. 根据模式 Y 进行验证
4. 将输出写入 `target_path`
**代码模板:** (用于创建新文件)
```python
# 要创建的实际代码结构
from typing import TypedDict
class ConfigType(TypedDict):
field_a: str
field_b: int
def main_function(config: ConfigType) -> Result:
"""解释目的的文档字符串。"""
pass
修改前后示例: (用于修改任务)
# 修改前 (当前代码)
def old_approach():
pass
# 修改后 (包含更改)
def new_approach():
# 新增: 更改说明
pass
## 结构化数组格式
### pendingTasks / completedTasks
```json
{
"id": "T-1.1",
"description": "任务描述",
"acceptanceCriteria": ["AC-001", "AC-002"]
}
{
"timestamp": "2024-01-01T00:00:00",
"changes": ["更改描述 1", "更改描述 2"],
"conversation": [...]
}
为涉及以下内容的任务提取实施细节:
细节提取清单:
跳过细节提取的情况:
修改现有计划时:
content 字段和结构化数组pendingTasks 和 completedTasks 数组code:extract-plan-md 重新生成 plan.md每周安装数
1
仓库
GitHub 星标
71
首次出现
今天
安全审计
安装于
windsurf1
amp1
cline1
openclaw1
opencode1
cursor1
Conventions for creating and modifying implementation plans stored as plan.json.
relative/path.ts)The plan is stored as plan.json with these key fields:
{
"content": "# Implementation Plan\n\n## Stage 1: ...\n\n### T-1.1: Task Title\n...",
"acceptanceCriteria": [...],
"pendingTasks": [...],
"completedTasks": [...],
"manualTasks": [...],
"openQuestions": [...],
"answeredQuestions": [...],
"gaps": [...],
"amendments": [...]
}
content : The full markdown plan as a JSON string with escaped newlines (\n). This is the human-readable plan text.CRITICAL : The content field is a JSON string. When editing:
\n escape sequences for newlines, NOT literal line breaksplan.md via the code:extract-plan-md skillTasks use the T-X.Y ID convention where X is the stage number and Y is the task number within that stage.
Each task in the plan content should follow this structure:
### T-X.Y: [Task Title]
**Files:** `path/to/file.ext`
**Complexity:** S | M | L
**AC Refs:** AC-001, AC-002
**Description:** Brief description of what this task accomplishes.
**Implementation Details:**
[Include one or more of the following as appropriate:]
**Mapping Table:** (for distribution/transformation tasks)
| Source | Target | Notes |
|--------|--------|-------|
| category_a | target_file_a.md | Section: XYZ |
| category_b | target_file_b.md | Section: ABC |
**Algorithm:** (for logic-heavy tasks)
1. Load input from `source_path`
2. Parse using `specific_method()`
3. For each item:
a. Transform using pattern X
b. Validate against schema Y
4. Write output to `target_path`
**Code Template:** (for new file creation)
```python
# Actual code structure to be created
from typing import TypedDict
class ConfigType(TypedDict):
field_a: str
field_b: int
def main_function(config: ConfigType) -> Result:
"""Docstring explaining purpose."""
pass
Before/After Example: (for modification tasks)
# BEFORE (current code)
def old_approach():
pass
# AFTER (with changes)
def new_approach():
# Added: explanation of change
pass
## Structured Array Format
### pendingTasks / completedTasks
```json
{
"id": "T-1.1",
"description": "Task description",
"acceptanceCriteria": ["AC-001", "AC-002"]
}
{
"timestamp": "2024-01-01T00:00:00",
"changes": ["Description of change 1", "Description of change 2"],
"conversation": [...]
}
Extract implementation details for tasks that involve:
Detail extraction checklist:
Skip detail extraction for:
When amending an existing plan:
content field and structured arrays as neededpendingTasks and completedTasks arraysplan.md via code:extract-plan-md after editsWeekly Installs
1
Repository
GitHub Stars
71
First Seen
Today
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
windsurf1
amp1
cline1
openclaw1
opencode1
cursor1
开源项目教练指南 - 诊断问题、制定行动计划、优化开源项目运营
31,600 周安装
房地产专家系统:MLS集成、虚拟看房、AI估值与物业管理技术解决方案
206 周安装
TypeScript/JavaScript 开发技能 - 掌握 Metabase 开源项目开发流程与工具
206 周安装
Upstash Redis SDK 完整指南 - Redis-JS 安装、使用与性能优化教程
206 周安装
Tavily API 网络搜索技能 - 实现网页爬取、内容提取和智能研究功能
206 周安装
企业合规助手:GDPR、CCPA等隐私法规合规指南与数据处理协议审查清单
206 周安装
DeepSpeed 开发助手:官方文档指南、API 使用与性能优化教程
207 周安装