skill-creator
Claude Codeスキル（SKILL.md）の設計・作成・バリデーション・レビュー。 Anthropic公式ガイド(2026-03)準拠。新規スキル作成、既存スキルの改善、 description品質チェック、トリガーテスト設計に使用。 「スキル作って」「スキル設計」「SKILL.md作成」「スキルレビュー」で起動。 Do NOT use for: スキルの実行・呼び出し（それは各スキル自体が行う）。
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that clearly defines its scope (meta-skill for creating and reviewing SKILL.md files), provides explicit trigger terms in natural Japanese, and includes a helpful exclusion clause. The description is concise yet comprehensive, listing specific capabilities and when to activate. The only minor note is that it's primarily in Japanese, which is appropriate if the target user base is Japanese-speaking.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 設計(design), 作成(creation), バリデーション(validation), レビュー(review) of SKILL.md files, plus sub-actions like 新規スキル作成, 既存スキルの改善, description品質チェック, トリガーテスト設計. | 3 / 3 |
Completeness | Clearly answers 'what' (SKILL.md設計・作成・バリデーション・レビュー with specific sub-tasks) and 'when' (explicit trigger phrases listed, plus a 'Do NOT use for' exclusion clause that further clarifies scope). The trigger guidance is explicit and well-defined. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say in Japanese: 「スキル作って」「スキル設計」「SKILL.md作成」「スキルレビュー」. Also includes key terms like SKILL.md, スキル, description品質チェック which cover common variations of how users would request this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche focused specifically on SKILL.md meta-skill creation and review, distinct from actual skill execution. The 'Do NOT use for' clause further reduces conflict risk by explicitly excluding skill invocation/execution. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive, well-structured skill creation guide with strong actionability—concrete examples, checklists, and a clear 12-step workflow make it immediately usable. Its main weakness is that it doesn't follow its own progressive disclosure advice: at 400+ lines it's a dense monolith that could benefit from splitting detailed references (frontmatter spec, design patterns, anti-patterns) into separate files. Some verbosity could be trimmed where Claude's existing knowledge is assumed.
Suggestions
Practice progressive disclosure: move the full frontmatter reference, 5 design patterns, and anti-patterns table into references/ files, keeping only summaries and links in SKILL.md
Trim explanatory text that Claude already knows (e.g., what kebab-case means, basic YAML structure) to improve token efficiency
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some explanatory content that Claude already knows (e.g., explaining what kebab-case is, basic YAML concepts). The tables and structured format help, but at ~400+ lines this could be tightened—some sections like 'Dynamic Features' and 'Execution Patterns' contain explanations that could be more telegraphic. The '将軍システム固有ルール' section mixes domain-specific context that may not belong in a general skill creator guide. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: complete YAML frontmatter with field-by-field documentation, a 7-item checklist for description quality, executable bash validation script examples, specific file structure paths, a 12-step creation workflow, and concrete good/bad examples for descriptions. The triggering test examples are copy-paste ready. | 3 / 3 |
Workflow Clarity | The 12-step Creation Workflow is clearly sequenced with logical dependencies (identify use case → categorize → design description → check duplicates → write → validate → test → deploy). Validation is explicitly called out as step 10 with script examples, and the 3-domain testing strategy provides clear verification checkpoints. The anti-patterns table serves as an additional validation checklist. | 3 / 3 |
Progressive Disclosure | The skill documents the concept of progressive disclosure (L1/L2/L3 layers) and recommends references/ for detailed content, but the SKILL.md itself is a monolithic document that doesn't practice what it preaches. The frontmatter reference, design patterns, and anti-patterns could be split into separate reference files. No external file references are provided for deeper dives on any topic. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- yohey-w/multi-agent-shogun
- Commit
3dafe0a
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.