Automated summary
Generates subagent definitions (.claude/agents/*.md) corresponding to a set of skills, following a workflow that includes preflight checks, subagent judgment, design, generation, quality control, and backlog update.
Strengths
- Automates creation of specialized subagents for parallel execution and task delegation.
- Provides clear criteria to decide when subagentification is beneficial vs. when a simpler evaluation file suffices.
- Offers type-specific templates (research, feedback, ideation, validation, parallel-check) to standardize agent structure.
- Integrates a dedicated QC subagent to validate the generated subagents against defined criteria.
Limitations
- Requires a pre-existing skills directory (.claude/skills/) with properly formatted SKILL.md files.
- The judgment step may still need manual interpretation for edge cases.
- Generated subagents are tailored to the Claude Code environment and may not be directly portable.
Use when you need to create a set of specialized, independently executable agents that can operate on specific skills, especially for parallel processing, expert delegation, or quality loops.
Do not use for simple evaluation tasks that can be handled by evaluation criteria files alone, or when the parent task requires full context that cannot be delegated to a subagent.
Security analysis
SafeThe skill only reads and writes markdown files within the local project, uses internal subagents for QC, and does not invoke destructive operations, external network calls, or execute arbitrary commands. No risk of exfiltration or system compromise.
No concerns found
How this analysis is madeExamples
Generate subagent definitions for all skills in the data-ai domain. Use the subagent-generate workflow.I need parallel processing agents for my skills directory. Create subagent definitions that can run independently.Design a feedback agent that reviews code changes using the skills in .claude/skills/. Generate the subagent definition using subagent-generate.name: subagent-generate description: "Skills群に対応するサブエージェント(.claude/agents/*.md)を設計・生成する。「サブエージェント作成」「並列処理エージェント」「専門エージェント」を依頼されたときに使用する。"
Subagent Generate Workflow
Skills群に対応するサブエージェントを生成する。主成果物はoutput/{domain}_agent/.claude/agents/配下のサブエージェント定義。
Instructions
1. Preflight(事前確認)
./assets/subagent_design_guide.mdを先に読み、サブエージェント設計原則を確認する。- 対象エージェントの
.claude/skills/を確認し、既存Skillsを把握する。 - 各SkillのSKILL.mdから
recommended_subagentsを抽出する。
2. サブエージェント判定
重要: サブエージェント化の判定基準
以下の条件を満たす場合のみ .claude/agents/*.md を作成する:
| 条件 | サブエージェント化 | 理由 | |------|-------------------|------| | コンテキスト不要で独立実行可能 | ✅ 必要 | 並列実行のメリットあり | | 専門知識・Skills携帯が必要 | ✅ 必要 | 専門性の分離 | | Web検索・外部情報取得 | ✅ 必要 | 非同期実行可能 | | アイデア出し・ブレスト | ✅ 必要 | 複数観点の並列生成 | | 仮説立案・検証 | ✅ 必要 | 独立した思考プロセス | | フィードバック・レビュー | ✅ 必要 | 客観的評価 | | 単なる評価軸チェック | ❌ 不要 | evaluation/*.mdで十分 | | 親タスクのコンテキスト必須 | ❌ 不要 | サブエージェント化の意味なし |
単なる評価軸の評価(チェックリスト確認等)は evaluation/*.md で対応し、agents/*.md は作成しない。
3. サブエージェント設計
サブエージェント化が必要と判定された場合、以下を設計する:
サブエージェント設計:
name: "{purpose}-agent"
type: "{research|feedback|ideation|validation|parallel-check}"
携帯Skills:
- "{関連skill-1}"
- "{関連skill-2}"
入力: "{何を受け取るか}"
出力: "{何を返すか}"
並列実行: "{可能/不可}"
Web検索: "{必要/不要}"
4. サブエージェント生成
設計に基づき、各サブエージェントを生成する:
output/{domain}_agent/.claude/agents/{agent-name}.md
サブエージェント定義フォーマット:
---
name: {agent-name}
description: "{説明}"
type: "{research|feedback|ideation|validation|parallel-check}"
tools: [Read, Grep, Glob, WebSearch, WebFetch] # 必要なツール
---
# {Agent Name}
{目的と役割の説明}
## 携帯Skills
このサブエージェントは以下のSkillsを参照して実行する:
- `.claude/skills/{skill-1}/`: {説明}
- `.claude/skills/{skill-2}/`: {説明}
## 実行手順
1. {ステップ1}
2. {ステップ2}
3. {ステップ3}
## 入力
- {入力パラメータ1}: {説明}
- {入力パラメータ2}: {説明}
## 出力
- {出力形式の説明}
- {レポートフォーマット等}
## 判定基準
- {成功条件1}
- {成功条件2}
5. サブエージェントタイプ別テンプレート
research-agent(調査系):
- Web検索で最新情報を収集
- 公式ドキュメント・ベストプラクティスを調査
- 携帯Skills: 対象ドメインの参照系Skills
feedback-agent(フィードバック系):
- 成果物に対する客観的レビュー
- 改善提案・代替案の提示
- 携帯Skills: 評価対象のSkills + evaluation基準
ideation-agent(アイデア出し系):
- 複数のアプローチを並列生成
- ブレインストーミング的発想
- 携帯Skills: ドメイン知識系Skills
validation-agent(検証系):
- 仮説の妥当性検証
- 実現可能性チェック
- 携帯Skills: 技術制約系Skills
parallel-check-agent(並列チェック系):
- 複数ファイルの同時チェック
- 独立した検証を並列実行
- 携帯Skills: チェック対象のSkills
6. QC(必須)
recommended_subagentsのQC Subagent(qa-skill-qc)に評価を委譲する。- Subagentは
./evaluation/subagent_criteria.mdをReadし、QCを実施する。 - チェック項目:
- サブエージェント化判定が適切か
- 携帯Skillsが適切に設定されているか
- 入出力定義が明確か
- 並列実行可能性が正しく判定されているか
- 指摘を最小差分で反映する(最大3回)。
7. バックログ反映
- 生成したサブエージェント一覧を記録する。
- CLAUDE.mdにサブエージェント索引を追加する。
- 次アクション(テスト実行等)を明示する。
subagent_policy:
- 品質ループ(QC/チェック/フィードバック)は必ずサブエージェントへ委譲する
- サブエージェントの指摘を反映し、反映結果(修正有無/理由)を成果物に残す
recommended_subagents:
- qa-skill-qc: サブエージェント化判定、携帯Skills設定、入出力定義を検査
Resources
- assets: ./assets/subagent_design_guide.md
- assets: ./assets/subagent_template.md
- assets: ./assets/subagent_types.md
- evaluation: ./evaluation/subagent_criteria.md
- triggers: ./triggers/next_action_triggers.md
Next Action
- triggers: ./triggers/next_action_triggers.md
起動条件に従い、条件を満たすSkillを自動実行する。
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/subagent-generator-mmbizkob/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/subagent-generator-mmbizkob' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/subagent-generator-mmbizkob/download' --output '.skill-downloads/subagent-generator-mmbizkob/SKILL.md.part' && mv '.skill-downloads/subagent-generator-mmbizkob/SKILL.md.part' '.skill-downloads/subagent-generator-mmbizkob/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/subagent-generator-mmbizkob/SKILL.md' && test -s '.skill-downloads/subagent-generator-mmbizkob/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/subagent-generate' && cp -R '.skill-downloads/subagent-generator-mmbizkob' '.claude/skills/subagent-generate'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/subagent-generator-mmbizkob'openskills read 'subagent-generator-mmbizkob'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/subagent-generator-mmbizkob/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.