Requirement Convergence
shinpr/claude-code-workflows
Separates the outcome a change must produce from the requirements proposed to reach it, records what the user excluded, and bands cost from structure.
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。
MITAuto-check passed
Install Requirement Convergence
$ npx skills add shinpr/ai-coding-project-boilerplate --skill requirement-convergence -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install shinpr/ai-coding-project-boilerplate requirement-convergence --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/shinpr/ai-coding-project-boilerplate.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills-zh-CN/requirement-convergence .claude/skills/requirement-convergence && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "requirement-convergence" agent skill from https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-zh-CN/requirement-convergence into .claude/skills/requirement-convergence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "requirement-convergence", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-zh-CN/requirement-convergenceType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add shinpr/ai-coding-project-boilerplate --skill requirement-convergence -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install shinpr/ai-coding-project-boilerplate requirement-convergence --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shinpr/ai-coding-project-boilerplate.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills-zh-CN/requirement-convergence .agents/skills/requirement-convergence && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "requirement-convergence" agent skill from https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-zh-CN/requirement-convergence into .agents/skills/requirement-convergence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "requirement-convergence", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add shinpr/ai-coding-project-boilerplate --skill requirement-convergence -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install shinpr/ai-coding-project-boilerplate requirement-convergence --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shinpr/ai-coding-project-boilerplate.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills-zh-CN/requirement-convergence .cursor/skills/requirement-convergence && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "requirement-convergence" agent skill from https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-zh-CN/requirement-convergence into .cursor/skills/requirement-convergence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "requirement-convergence", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/shinpr/ai-coding-project-boilerplate.git --path .claude/skills-zh-CN/requirement-convergence--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add shinpr/ai-coding-project-boilerplate --skill requirement-convergence -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install shinpr/ai-coding-project-boilerplate requirement-convergence --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shinpr/ai-coding-project-boilerplate.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills-zh-CN/requirement-convergence .gemini/skills/requirement-convergence && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "requirement-convergence" agent skill from https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-zh-CN/requirement-convergence into .gemini/skills/requirement-convergence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "requirement-convergence", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install shinpr/ai-coding-project-boilerplate requirement-convergenceInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add shinpr/ai-coding-project-boilerplate --skill requirement-convergence -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/shinpr/ai-coding-project-boilerplate.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills-zh-CN/requirement-convergence .github/skills/requirement-convergence && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "requirement-convergence" agent skill from https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-zh-CN/requirement-convergence into .github/skills/requirement-convergence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "requirement-convergence", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add shinpr/ai-coding-project-boilerplate --skill requirement-convergence -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install shinpr/ai-coding-project-boilerplate requirement-convergence --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/shinpr/ai-coding-project-boilerplate.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills-zh-CN/requirement-convergence .opencode/skills/requirement-convergence && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "requirement-convergence" agent skill from https://github.com/shinpr/ai-coding-project-boilerplate/tree/main/.claude/skills-zh-CN/requirement-convergence into .opencode/skills/requirement-convergence/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "requirement-convergence", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
requirement-convergence- GitHub stars
- 234
- Token cost
- ~545 tokens
- SKILL.md length
- 103 words
- Files
- 2 (incl. references)
- Skills in repo
- 41
- Repo updated
- First seen
- Licence
- MIT
At a glance
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。
- Works in 3 steps: 从提示词中读取收敛记录。 → 将 nonGoals 视为当前变更排除在外的内容，将… → 将 weak-but-explicit…
- SKILL.md covers 目的, 收敛字段, 询问协议 and 存储协议, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Requirement Convergence is an agent skill from shinpr/ai-coding-project-boilerplate. 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。
Its SKILL.md is about 550 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/criteria.md`).
The repository describes itself as: Agentic coding TypeScript boilerplate for Claude Code: sub-agent workflows with built-in quality checks and context engineering. The licence is MIT.
Example prompts
- “做到什么程度/范围外是什么/是否值得做”
- “/requirement-convergence”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- 从提示词中读取收敛记录。
- 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。
- 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。
What it can do on your machine
Read from SKILL.md and the folder at commit 56913a2. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Requirement Convergence loads about 545 tokens when it runs, and up to ~1.5k if it reads all its reference files. Until then it costs about 32 tokens; SKILL.md has 103 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from shinpr/ai-coding-project-boilerplate at commit 56913a2, republished under its MIT licence (© shinpr). 103 words, ~545 tokens.
Download SKILL.mdSave it as
.claude/skills/requirement-convergence/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- requirement-convergence
- description
- 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。
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
- 从提示词中读取收敛记录。
- 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。 - 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
© shinpr, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (references) in .claude/skills-zh-CN/requirement-convergence of shinpr/ai-coding-project-boilerplate.
- SKILL.md
- references/criteria.md
Open the folder on GitHubat commit 56913a2
Compare with similar skills
Requirement Convergence next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Requirement Convergence this skillshinpr/ai-coding-project-boilerplate | 234 | — | ~545 | Automated safety check: Pass | MIT | |
| Requirement Convergenceshinpr/claude-code-workflows | 694 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Requirementsrizsotto/Bear | 6.5k | — | ~2k | Automated safety check: Pass | GPL-3.0 | |
| Convergenceparcadei/Continuous-Claude-v3 | 3.9k | 1 repos | ~316 | Automated safety check: Notes | MIT | |
| Aria Required Attrthedaviddias/Front-End-Checklist | 74k | — | ~459 | Automated safety check: Pass | MIT | |
| Aria Required Parentthedaviddias/Front-End-Checklist | 74k | — | ~498 | Automated safety check: Pass | MIT |
Similar skills
Requirements
rizsotto/Bear
Write, modify, or review a requirement file under docs/requirements -- pick the single owning file, keep the text contract-only, name IDs so they need no explanation, and verify cross-references and…
Convergence
parcadei/Continuous-Claude-v3
Problem-solving strategies for convergence in real analysis. An agent skill from parcadei/Continuous-Claude-v3.
Aria Required Attr
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Include required ARIA attributes for roles.
Aria Required Parent
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Ensure ARIA roles are contained by required parent roles.
Browser Required
thedaviddias/Front-End-Checklist
A skill your agent uses when auditing slow page loads, heavy assets, or rendering delays related to Perform browser-based performance audits.
More from shinpr/ai-coding-project-boilerplate
All 41 skills in this repoIntegration E2E Testing
shinpr/ai-coding-project-boilerplate
Selects and designs the smallest integration/E2E test set that proves accepted behavior at an observable boundary.
Skill Optimization
shinpr/ai-coding-project-boilerplate
Evaluates and optimizes skill file quality using 9 content patterns and 10 editing principles.
Frontend Technical Spec
shinpr/ai-coding-project-boilerplate
Defines React environment, component architecture, state/data flow, build verification, and frontend non-functional criteria from repository evidence.
Frontend Typescript Rules
shinpr/ai-coding-project-boilerplate
Applies React/TypeScript type safety, component design, and state management rules.
Implementation Approach
shinpr/ai-coding-project-boilerplate
Selects implementation strategy (vertical slice, horizontal, or hybrid) with risk assessment.
Subagents Orchestration Guide
shinpr/ai-coding-project-boilerplate
Coordinates subagents through scale-based planning, approval, implementation, verification, and escalation flows.
Questions about Requirement Convergence
What does Requirement Convergence 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。. Requirement Convergence is an agent skill from shinpr/ai-coding-project-boilerplate.
How do I install Requirement Convergence in Claude Code?
Run `npx skills add shinpr/ai-coding-project-boilerplate --skill requirement-convergence -a claude-code`. Or copy the skill folder (.claude/skills-zh-CN/requirement-convergence in shinpr/ai-coding-project-boilerplate) into .claude/skills/requirement-convergence in your project. Claude Code loads it when a task matches its description.
How do I install Requirement Convergence in Codex?
Run `npx skills add shinpr/ai-coding-project-boilerplate --skill requirement-convergence -a codex`. Or copy the skill folder (.claude/skills-zh-CN/requirement-convergence in shinpr/ai-coding-project-boilerplate) into .agents/skills/requirement-convergence in your project. Codex loads it when a task matches its description.
Can I use Requirement Convergence in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add shinpr/ai-coding-project-boilerplate --skill requirement-convergence -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/requirement-convergence, .gemini/skills/requirement-convergence, .github/skills/requirement-convergence and .opencode/skills/requirement-convergence in your project.
What does Requirement Convergence need to run?
SKILL.md names no scripts, command-line tools or credentials: Requirement Convergence is instructions for the agent only.
Does Requirement Convergence access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Requirement Convergence safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Requirement Convergence use?
Requirement Convergence is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Requirement Convergence use?
About 545 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 965 tokens, read only when the agent opens those files.
What are the alternatives to Requirement Convergence?
Skills that share tags, products or a category with Requirement Convergence: Requirement Convergence (shinpr/claude-code-workflows, 694 stars), Requirements (rizsotto/Bear, 6.5k stars), Convergence (parcadei/Continuous-Claude-v3, 3.9k stars) and Aria Required Attr (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Requirement Convergence?
shinpr (a GitHub user) maintains it in shinpr/ai-coding-project-boilerplate, which has 234 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 4, 2026.
Source: shinpr/ai-coding-project-boilerplate on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.