Writing Plans logo

Writing Plans

CommunityPopular
jnMetaCode
writing-plans

当你有规格说明或需求用于多步骤任务时使用,在动手写代码之前

Overview

PublisherjnMetaCode
Repositorysuperpowers-zh
Skill namewriting-plans
Stars
8.1K
Forks
758
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jnMetaCode on GitHub. Read the source before you install it.

Installation

Install the Writing Plans AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git /tmp/superpowers-zh
mkdir -p .claude/skills
cp -r /tmp/superpowers-zh/skills/writing-plans .claude/skills/writing-plans
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Writing Plans in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Writing Plans on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Writing Plans is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

编写计划

概述

编写全面的实现计划,假设工程师对我们的代码库零上下文,且品味存疑。记录他们需要知道的一切:每个任务要修改哪些文件、代码、测试、可能需要查阅的文档、如何测试。将整个计划拆成小步骤任务。DRY。YAGNI。TDD。频繁 commit。

假设他们是有经验的开发者,但对我们的工具链和问题领域几乎一无所知。假设他们不太擅长测试设计。

开始时宣布: "我正在使用 writing-plans 技能创建实现计划。"

上下文: 此技能应在专用 worktree 中运行(由 brainstorming 技能创建)。

计划保存位置: docs/superpowers/plans/YYYY-MM-DD-<feature-name>.md

  • (用户对计划位置的偏好优先于此默认值)

范围检查

如果规格涵盖了多个独立子系统,它应该在头脑风暴阶段就被拆分为子项目规格。如果没有,建议将其拆分为独立的计划——每个子系统一个。每个计划应该能独立产出可工作、可测试的软件。

文件结构

在定义任务之前,先列出将要创建或修改的文件以及每个文件的职责。这是锁定分解决策的地方。

  • 设计边界清晰、接口定义良好的单元。每个文件应有一个明确的职责。
  • 你对能一次放入上下文的代码推理得最好,文件越专注你的编辑越可靠。优先选择小而专注的文件,而非承担过多功能的大文件。
  • 一起变更的文件应放在一起。按职责拆分,而非按技术层级拆分。
  • 在现有代码库中,遵循已有模式。如果代码库使用大文件,不要单方面重构——但如果你正在修改的文件已经变得难以管理,在计划中包含拆分是合理的。

此结构决定了任务分解。每个任务应产出独立的、有意义的变更。

任务粒度定界

一个任务是能独立承载自己那一轮测试循环、且值得一个全新审查者把关的最小单元。划任务边界时:把搭建、配置、脚手架和文档这些步骤,折进那个真正需要它们的交付物所在的任务里;只在「审查者有可能否掉这个任务、同时批准它旁边那个」的地方才拆开。每个任务都以一个可独立测试的交付物结束。

小步骤任务粒度

每步是一个操作(2-5 分钟):

  • "编写失败的测试" - 一步
  • "运行它确认失败" - 一步
  • "实现最少代码让测试通过" - 一步
  • "运行测试确认通过" - 一步
  • "Commit" - 一步

计划文档头部

每个计划必须以此头部开始:

markdown
# [功能名称] 实现计划

> **面向 AI 代理的工作者:** 必需子技能:使用 subagent-driven-development(推荐)或 executing-plans 逐任务实现此计划。步骤使用复选框(`- [ ]`)语法来跟踪进度。

**目标:** [一句话描述要构建什么]

**架构:** [2-3 句话描述方案]

**技术栈:** [关键技术/库]

**规格:** [本计划所实现的规格 / 设计文档路径 —— 计划的论证依据来自规格,所以规格要跟着计划一起走;执行者两份都读]


## 全局约束

[来自规格的项目级要求 —— 版本下限、依赖限制、命名与文案规则、平台要求 —— 每条一行,数值从规格里逐字照抄。每个任务的要求都隐含包含本节。]

---

任务结构

markdown
### 任务 N:[组件名称]

**文件:**
- 创建:`exact/path/to/file.py`
- 修改:`exact/path/to/existing.py:123-145`
- 测试:`tests/exact/path/to/test.py`

- [ ] **步骤 1:编写失败的测试**

```python
def test_specific_behavior():
    result = function(input)
    assert result == expected
```

- [ ] **步骤 2:运行测试验证失败**

运行:`pytest tests/path/test.py::test_name -v`
预期:FAIL,报错 "function not defined"

- [ ] **步骤 3:编写最少实现代码**

```python
def function(input):
    return expected
```

- [ ] **步骤 4:运行测试验证通过**

运行:`pytest tests/path/test.py::test_name -v`
预期:PASS

- [ ] **步骤 5:Commit**

```bash
git add tests/path/test.py src/path/file.py
git commit -m "feat: add specific feature"
```

禁止占位符

每个步骤都必须包含工程师需要的实际内容。以下是计划缺陷——绝不要写出来:

  • "待定"、"TODO"、"后续实现"、"补充细节"
  • "添加适当的错误处理" / "添加验证" / "处理边界情况"
  • "为上述代码编写测试"(没有实际测试代码)
  • "类似任务 N"(重复代码——工程师可能不按顺序阅读任务)
  • 只描述做什么而不展示怎么做的步骤(代码步骤必须有代码块)
  • 引用了未在任何任务中定义的类型、函数或方法

自检

编写完整计划后,以全新视角审视规格并对照检查计划。这是你自己执行的检查清单——不是子代理调度。

1. 规格覆盖度: 浏览规格中的每个章节/需求。你能指出实现它的任务吗?列出所有遗漏。

2. 占位符扫描: 搜索计划中的红旗——上方"禁止占位符"章节中的任何模式。修复它们。

3. 类型一致性: 后续任务中使用的类型、方法签名和属性名是否与前面任务中定义的一致?任务 3 中叫 clearLayers() 但任务 7 中叫 clearFullLayers() 就是 bug。

如果发现问题,直接内联修复。无需重新审查——修好继续推进。如果发现规格中的需求没有对应任务,就添加任务。

执行交接

保存计划后,提供执行选项:

"计划已完成并保存到 docs/superpowers/plans/<filename>.md。两种执行方式:

1. 子代理驱动(推荐) - 每个任务调度一个新的子代理,任务间进行审查,快速迭代

2. 内联执行 - 在当前会话中使用 executing-plans 执行任务,批量执行并设有检查点

选哪种方式?"

如果选择子代理驱动:

  • 必需子技能: 使用 subagent-driven-development
  • 每个任务一个新子代理 + 两阶段审查

如果选择内联执行:

  • 必需子技能: 使用 executing-plans
  • 批量执行并设有检查点供审查

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Writing Plans AI skill do?

当你有规格说明或需求用于多步骤任务时使用,在动手写代码之前

Why use Writing Plans on TypingMind?

Because you install it once and use it with any model. Writing Plans is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Writing Plans in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/writing-plans. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Writing Plans?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Writing Plans?

As many as you like. As long as a model supports skills, you can use Writing Plans with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Writing Plans AI skill free?

Yes. It is published on GitHub by jnMetaCode under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇