Requirement Convergence logo

Requirement Convergence

Community
shinpr
requirement-convergence

将变更必须产生的结果与为达成该结果而提出的需求区分开来,记录用户明确排除的内容,并根据结构对成本进行分级评估。当需求进入某个工作流时、设计开始之前,或提到“做到什么程度/范围外是什么/是否值得做”时使用。

Overview

Publishershinpr
Repositoryai-coding-project-boilerplate
Skill namerequirement-convergence
Stars
234
Forks
28
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 shinpr on GitHub. Read the source before you install it.

Installation

Install the Requirement Convergence 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.
    https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-zh-CN/requirement-convergence
  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/shinpr/ai-coding-project-boilerplate.git /tmp/ai-coding-project-boilerplate
mkdir -p .claude/skills
cp -r /tmp/ai-coding-project-boilerplate/.claude/skills-zh-CN/requirement-convergence .claude/skills/requirement-convergence
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Requirement Convergence 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 Requirement Convergence 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 Requirement Convergence 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.

需求收敛

目的

收到的需求往往过于臃肿、含糊不清,或指向错误的目标。能力足够的模型会将这三者调和为一个连贯的计划,并忠实地构建它——当被要求的内容本身就是错的时,也精确地交付被要求的内容。

本技能收敛的是要构建什么。如何构建,以及该变更需要哪些文档,都在“要构建什么”确定之后再解决。

收敛字段

字段通过条件
outcome一个可观测的结果。不服务于该结果的需求即为多余。
requirements[]每个与构建相关的项都标注为 current-state 或 desired-future。
nonGoals[]由用户撰写,或用户声明没有范围外项。
cost一个带有结构性依据支撑的分级,加上仍然存在的未知项。

cost 是一个粗略的分级,不是工作计划据以排期的工作量估算;需求无法支撑以人天为单位的估算。其未知项在决策权重上比其规模更重要。

依据所保留的用户原话进行分类,而不是依据分析器对原话的转述。要求评估的措辞、描述设想性想法的措辞,或建议某种机制的措辞,在当前收敛上下文中仅作为供判断参考的候选项保留。只有在用户明确确认之后,候选项才能进入 requirements[] 及长期保留的文档。

每个字段都带有各自的就绪标签:ready、weak,或 weak-but-explicit(弱,且用户同意暂不解决)。只有用户可以设置 weak-but-explicit。当所有适用字段都为 ready 或 weak-but-explicit 时,需求即视为已收敛。

各字段的判断规则见:references/criteria.md。

询问协议

使用现有的范围与成本依据来引出信息并做出判断,然后只就仓库无法回答的产品选择进行提问。requirements[] 和排除项的询问都依据用户提出的能力构建;分析中发现的相邻能力两者都不纳入,因此用户无需拒绝一项自己并未提出的能力。仅当某个答案会改变分析目标或所需的范围依据时,才重新分析范围与成本。

在开始前登记以下步骤,并在每个步骤完成时记录其依据:

步骤动作完成依据
1陈述现有的范围事实,然后单独说明这些事实对需求意味着什么列出事实及其分析依据
2就低于 ready 的字段提问,每条消息最多两个问题每个低于 ready 的字段一个问题
3将每个答案记录为该字段的值该值是用户明确选定的选项,或用户自己提供的措辞
4当已记录的值仍未通过其通过条件时,重新询问一次;若用户同意将第二次回答维持原状,则将该字段标记为 weak-but-explicit两次已记录的答案,或用户同意停止
5依据每个字段的通过条件进行判断,并完成该记录一份每个字段都已标注的收敛记录

存储协议

载体承载内容
当前收敛记录每个字段及其就绪标签
PRD 的 成功标准 和 范围外outcome;用户撰写的 nonGoals
设计文档的 需求收敛在没有 PRD 时承载同样内容,且在任何情况下都承载被标为 weak-but-explicit 的字段

不产生上述任一文档时,将记录保留在当前上下文中。

引用协议

  1. 从提示词中读取收敛记录。
  2. 将 nonGoals 视为当前变更排除在外的内容,将 desired-future 需求视为可构建的范围。未被采纳的评估性请求、设想性想法、指定的实现机制以及由智能体提出的能力不产生任何实现义务;已被采纳的 ADR 可以将已评估过的选项保留作为决策历史。
  3. 将 weak-but-explicit 的字段视为已记录的悬而未决的问题,而非已敲定的决策,当工作依赖于该问题的解决时应上报处理。

质量检查清单

  • 范围事实在提问之前已呈现
  • nonGoals 来自用户,或用户声明没有范围外项
  • 每个适用字段都为 ready,或经用户同意后为 weak-but-explicit

参考资料

  • references/criteria.md — 各字段的判断规则、成本输入、挑战力度、伪装成方案的需求测试

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 Requirement Convergence AI skill do?

将变更必须产生的结果与为达成该结果而提出的需求区分开来,记录用户明确排除的内容,并根据结构对成本进行分级评估。当需求进入某个工作流时、设计开始之前,或提到“做到什么程度/范围外是什么/是否值得做”时使用。

Why use Requirement Convergence on TypingMind?

Because you install it once and use it with any model. Requirement Convergence 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 Requirement Convergence in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-zh-CN/requirement-convergence. 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 Requirement Convergence?

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 Requirement Convergence?

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

Is the Requirement Convergence AI skill free?

Yes. It is published on GitHub by shinpr 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 👇