CtrlK
BlogDocsLog inGet started
Tessl Logo

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)。

72

Quality

88%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

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 well-structured, highly actionable meta-skill for creating Claude Code skills. Its greatest strengths are the concrete description design checklist, the clear 12-step creation workflow, and the comprehensive anti-patterns table. However, it's somewhat ironic that a skill teaching progressive disclosure and the 5,000-word limit doesn't itself split its detailed reference material (frontmatter fields, design patterns) into separate files, and it includes some explanatory content that Claude wouldn't need.

Suggestions

Practice your own progressive disclosure: move the full frontmatter field reference and the 5 design patterns into references/ files, keeping only summaries in SKILL.md

Trim explanations of concepts Claude already knows (e.g., what kebab-case means, that YAML uses key-value pairs) to improve token efficiency

DimensionReasoningScore

Conciseness

The skill is comprehensive but includes some content Claude already knows (e.g., explaining what kebab-case is, basic YAML syntax). The frontmatter reference section is thorough but could be more concise—many fields have obvious meanings. The '将軍システム固有ルール' section adds domain-specific value, but overall the skill is quite long (~400+ lines) and could be tightened by moving the full frontmatter reference and design patterns to references/ files.

2 / 3

Actionability

The skill provides highly concrete, actionable guidance: the 7-item description checklist with good/bad examples, the 12-step creation workflow, executable validation script examples, specific file paths, naming conventions, and trigger test templates. The description debugging technique ('When would you use the [skill-name] skill?') is a particularly actionable tip.

3 / 3

Workflow Clarity

The 12-step Creation Workflow is clearly sequenced with logical dependencies. The testing strategy covers 3 distinct areas with explicit examples. The validation script recommendation serves as a verification checkpoint. The anti-patterns table provides clear guardrails against common failure modes, and the description design section includes a structured checklist for quality validation.

3 / 3

Progressive Disclosure

The skill describes a 3-layer progressive disclosure model (L1/L2/L3) and recommends references/ for detailed content, but ironically doesn't practice what it preaches—the full frontmatter reference, all 5 design patterns, and the complete anti-patterns table are all inline rather than split into reference files. No bundle files are provided, so there are no actual references/ to point to. The skill would benefit from its own progressive disclosure structure.

2 / 3

Total

10

/

12

Passed

Description

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 designing/reviewing SKILL.md files), provides explicit trigger terms in Japanese, and includes a helpful exclusion clause. It covers all four dimensions strongly with concrete actions, natural keywords, complete what/when guidance, and a distinct niche that minimizes conflict with other skills.

DimensionReasoningScore

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). Both dimensions are explicitly addressed.

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

Highly distinctive niche: specifically about creating and reviewing SKILL.md files for Claude Code, not about executing skills or general coding. The 'Do NOT use for' clause further reduces conflict risk by explicitly excluding skill execution/invocation.

3 / 3

Total

12

/

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.