agentleFS
morodomimorodomi/dev-crew/skills/skill-maker/SKILL.md

skill-maker

Skill1 starsChanged 26 days agoMITView on GitHub

Anthropic公式ガイド準拠の対話型スキル作成・レビュー支援。Use when user says "create skill", "make skill", "skill review", "スキルを作りたい", "スキルレビュー"。新規作成とdescription品質チェックの2モードで起動。

21 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Skill Maker

Anthropic公式ガイドに基づき、高品質なスキルを対話的に作成・レビューする。

Progress Checklist

Skill Maker Progress:
- [ ] モード判定(Create / Review)
- [ ] ワークフロー実行
- [ ] バリデーション
- [ ] 出力

Mode Selection

ユーザー入力からモードを判定:

キーワードモード
create, make, 作りたい, 新規Create
review, check, レビュー, 品質Review
両方検出(create+review)AskUserQuestion で優先モード確認
不明AskUserQuestion でモード選択

Create Mode: 新規スキル作成

Step 1/6: Use Case Definition

AskUserQuestion で確認:

  • 何を実現するスキルか(目的)
  • 誰が使うか(対象ユーザー)
  • 2-3個の具体的なユースケース

Step 2/6: Category Selection

AskUserQuestion でカテゴリ選択:

  • Document & Asset Creation(ドキュメント生成)
  • Workflow Automation(ワークフロー自動化)
  • MCP Enhancement(MCP連携強化)

Step 3/6: YAML Frontmatter生成

name + description を生成。ユーザーが拒否した場合は再生成(リトライ可)。description基準: reference.md

Step 4/6: SKILL.md Body作成

ステップ形式のワークフロー + Progressive Disclosure。詳細: reference.md

Step 5/6: Validation

チェックリスト実行: reference.md

Step 6/6: Output

生成したSKILL.mdを出力。reference.md が必要なら併せて生成。

Review Mode: 既存スキル品質チェック

Step 1/4: Target Selection

レビュー対象のSKILL.mdパスをAskUserQuestion で確認。

Step 2/4: Quality Check

公式基準でチェック:

  • description品質(WHAT+WHEN+triggers): reference.md
  • 構造(< 100行、Progressive Disclosure): reference.md
  • セキュリティ(XML禁止、予約名): reference.md

Step 3/4: Issue Report

検出された問題をリスト。severity: critical / important / minor。

Step 4/4: Fix Suggestions

各問題に対する修正案を提示。ユーザー承認後に適用。

Reference

詳細: reference.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.