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.
変更が生むべき成果と、そこへ至るために提案された要件を切り分け、ユーザーが除外したものを記録し、構造からコストをおおまかな区分で見積もる。要件がワークフローに入った時点、設計を始める前、または「どこまでやるか/スコープ外は何か/やる価値があるか」が言及された時に使用。
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-ja/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-ja/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-ja/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-ja/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-ja/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-ja/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-ja/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-ja/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-ja/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-ja/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-ja/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-ja/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-ja/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-ja/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
- ~700 tokens
- SKILL.md length
- 110 words
- Files
- 2 (incl. references)
- Skills in repo
- 41
- Repo updated
- First seen
- Licence
- MIT
At a glance
変更が生むべき成果と、そこへ至るために提案された要件を切り分け、ユーザーが除外したものを記録し、構造からコストをおおまかな区分で見積もる。要件がワークフローに入った時点、設計を始める前、または「どこまでやるか/スコープ外は何か/やる価値があるか」が言及された時に使用。
- Works in 3 steps: プロンプトから収束記録を読む。 → nonGoals は今回の変更から除外し、desired-future… → weak-but-explicit…
- SKILL.md covers 目的, 収束フィールド, ヒアリングプロトコル and 保存プロトコル, 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. 変更が生むべき成果と、そこへ至るために提案された要件を切り分け、ユーザーが除外したものを記録し、構造からコストをおおまかな区分で見積もる。要件がワークフローに入った時点、設計を始める前、または「どこまでやるか/スコープ外は何か/やる価値があるか」が言及された時に使用。
Its SKILL.md is about 700 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
- “/requirement-convergence”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- プロンプトから収束記録を読む。
- nonGoals は今回の変更から除外し、desired-future 要件を作る対象として扱う。採用されていない評価依頼、推測的なアイデア、指定された実装手段、エージェントが提案した機能は実装作業を生まない。評価した選択肢を判断の履歴として残せるのは、承認済みADRがそれを扱…
- weak-but-explicit のフィールドは、確定した判断ではなく記録された未解決の論点として扱い、作業がその解決に依存する場合はエスカレーションする。
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 700 tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 40 tokens; SKILL.md has 110 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). 110 words, ~700 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
- 変更が生むべき成果と、そこへ至るために提案された要件を切り分け、ユーザーが除外したものを記録し、構造からコストをおおまかな区分で見積もる。要件がワークフローに入った時点、設計を始める前、または「どこまでやるか/スコープ外は何か/やる価値があるか」が言及された時に使用。
要件収束
目的
要件は、膨らんだ状態、曖昧な状態、狙う成果を外した状態で届く。能力の高いモデルはその3つをまとめて筋の通った計画に組み直し、忠実に作り上げてしまう — 求められたものが間違っていたときに、求められたとおりのものを届けることになる。
このスキルは何を作るかを収束させる。どう作るか、そして変更にどのドキュメントが必要かは、何を作るかが決まった後に定める。
収束フィールド
| フィールド | 通過条件 |
|---|---|
outcome | 観測可能な結果が1つ。それに寄与しない要件は不要である。 |
requirements[] | 作る対象に関わる各項目に current-state または desired-future のラベルが付いている。 |
nonGoals[] | ユーザーが挙げたもの。または、除外すべきものはないとユーザーが述べたこと。 |
cost | 区分1つと、それを決めた構造上の根拠、および残っている不明点。 |
cost はおおまかな区分であり、作業計画書がスケジュールの根拠にする工数見積ではない — 要件の段階では人日を裏付けられない。残っている不明点は、規模そのものよりも判断に影響する。
分類は、アナライザが言い換えたものではなく、保持しているユーザー自身の文言から行う。評価を求める文言、推測的なアイデアを述べる文言、実装手段を提案する文言は、収束中は判断のための候補としてのみ扱う。requirements[] や後続作業で参照されるドキュメントに入れるのは、ユーザーが明示的に採用したものだけとする。
各フィールドは自身の readiness ラベルを持つ: ready、weak、weak-but-explicit（weak だが、未解決のまま残すことにユーザーが同意した状態）。weak-but-explicit を設定できるのはユーザーだけである。該当する全フィールドが ready または weak-but-explicit になった時点で、要件は収束したとみなす。
フィールドごとの判断ルール: references/criteria.md。
ヒアリングプロトコル
利用可能なスコープとコストのエビデンスを、聞き出す作業と判定の両方に用いる。質問するのは、リポジトリからは答えられないプロダクト上の選択だけとする。requirements[] と除外事項のヒアリングは、ユーザーが依頼した機能から組み立てる。分析中に見つかった隣接する機能はどちらにも含めないので、ユーザーは依頼していない機能を却下する必要がない。スコープとコストを再分析するのは、回答が分析対象または必要なスコープエビデンスを変える場合に限る。
開始前に以下のステップを登録し、完了ごとにその根拠を記録する:
| ステップ | 行うこと | 完了の根拠 |
|---|---|---|
| 1 | 利用可能なスコープの事実を述べ、そこから要件について何が言えるかを分けて示す | 事実が、その分析エビデンスとともに列挙されている |
| 2 | ready に達していないフィールドについて、1メッセージあたり最大2問で質問する | ready に達していないフィールドごとに1問 |
| 3 | 各回答をそのフィールドの値として記録する | 値が、ユーザーが明示的に選んだ選択肢、またはユーザー自身が述べた言い回しになっている |
| 4 | 記録した値がまだ通過条件を満たさない場合は1度だけ聞き直し、2度目の回答のままでよいとユーザーが同意した時点でそのフィールドを weak-but-explicit とする | 記録された回答が2つ、またはそこで止めることへのユーザーの同意 |
| 5 | 各フィールドを通過条件に照らして判定し、記録を完成させる | 全フィールドにラベルが付いた収束記録 |
保存プロトコル
| 保持先 | 保持する内容 |
|---|---|
| 現在の収束記録 | 全フィールドとその readiness ラベル |
PRD の 成功基準 と Out of Scope | outcome、およびユーザーが挙げた nonGoals |
Design Doc の Requirement Convergence | PRD がない場合は上と同じ内容。加えて weak-but-explicit のまま残ったフィールドは常にここへ記録する |
どちらのドキュメントも生成しない場合は、現在のコンテキストに記録を保持する。
参照プロトコル
- プロンプトから収束記録を読む。
nonGoalsは今回の変更から除外し、desired-future要件を作る対象として扱う。採用されていない評価依頼、推測的なアイデア、指定された実装手段、エージェントが提案した機能は実装作業を生まない。評価した選択肢を判断の履歴として残せるのは、承認済みADRがそれを扱う場合だけである。weak-but-explicitのフィールドは、確定した判断ではなく記録された未解決の論点として扱い、作業がその解決に依存する場合はエスカレーションする。
品質チェックリスト
- 質問の前にスコープの事実を提示した
-
nonGoalsがユーザーから出たもの、または除外すべきものはないとユーザーが述べたものになっている - 該当する全フィールドが
ready、またはユーザーの同意によるweak-but-explicitになっている
References
- references/criteria.md — フィールドごとの判断ルール、コストの入力、チャレンジの強度、手段すり替えの検出
© 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-ja/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 | — | ~700 | 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?
変更が生むべき成果と、そこへ至るために提案された要件を切り分け、ユーザーが除外したものを記録し、構造からコストをおおまかな区分で見積もる。要件がワークフローに入った時点、設計を始める前、または「どこまでやるか/スコープ外は何か/やる価値があるか」が言及された時に使用。. 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-ja/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-ja/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 700 tokens (SKILL.md is roughly 2.8k 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 1.1k 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.