Everything Claude Code のインタラクティブなインストーラー — スキルとルールの選択とインストールをユーザーレベルまたはプロジェクトレベルのディレクトリへガイドし、パスを検証し、必要に応じてインストールされたファイルを最適化します。
60
68%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./docs/ja-JP/skills/configure-ecc/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description clearly communicates a specific, well-scoped capability (interactive installer for Claude Code skills/rules) with concrete actions like path validation and file optimization. Its main weaknesses are the lack of an explicit 'Use when...' trigger clause and limited natural keyword coverage, particularly missing English equivalents that users might naturally use.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to install, set up, or configure Claude Code skills and rules.'
Include natural trigger terms in both Japanese and English, such as 'setup', 'configure', 'install skills', 'セットアップ', 'CLAUDE.md' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: guides skill/rule selection and installation, validates paths, and optimizes installed files. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (interactive installer for skills and rules, path validation, optimization), but lacks an explicit 'Use when...' clause or equivalent trigger guidance for when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Contains relevant terms like 'インストーラー' (installer), 'スキル' (skills), 'ルール' (rules), 'インストール' (install), but is in Japanese which limits natural trigger matching. Missing common English variations like 'setup', 'configure', 'CLAUDE.md' that users might say. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche — an interactive installer for 'Everything Claude Code' skills and rules with user-level vs project-level directory targeting. This is unlikely to conflict with other skills due to its unique, well-defined scope. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
70%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 installer wizard with excellent workflow clarity and validation checkpoints. Its main weakness is that it's monolithic — the full 31-skill catalog, optimization procedures, and troubleshooting are all inline, making it very long (~300 lines) when much of this reference data could be externalized. The actionability is excellent with concrete commands, specific AskUserQuestion prompts, and edge-case handling.
Suggestions
Extract the skill catalog tables (Framework & Language, Database, Workflow & Quality) into a separate CATALOG.md file and reference it from the main SKILL.md to significantly reduce token usage
Move the optimization procedures (Step 5) and troubleshooting section into separate referenced files (e.g., OPTIMIZE.md, TROUBLESHOOTING.md) since they are optional/conditional flows
Consider condensing the AskUserQuestion examples to show the pattern once and then use shorthand for subsequent prompts, rather than fully spelling out each prompt block
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~300 lines) with extensive tables listing all 31 skills and their descriptions. While the step-by-step structure is necessary for an installer wizard, the full skill catalog tables could be externalized. Some sections like the troubleshooting tips are useful but add bulk. The content mostly avoids explaining things Claude already knows, but the sheer volume of inline reference data (skill tables, rule descriptions) reduces token efficiency. | 2 / 3 |
Actionability | The skill provides fully executable bash commands for every step (git clone, cp -R, mkdir -p, grep, ls -la), specific AskUserQuestion prompts with exact options, concrete path patterns, and clear variable naming ($ECC_ROOT, $TARGET). The trailing-slash handling tip and the cp command patterns are copy-paste ready and address real edge cases. | 3 / 3 |
Workflow Clarity | The 7-step workflow (Steps 0-6) is clearly sequenced with explicit validation in Step 4 (file existence, path references, cross-references, issue reporting with file/line/problem/fix structure). There are feedback loops: clone failure triggers AskUserQuestion fallback, validation issues get reported with recommended fixes, and the optimization step offers to fix issues found in validation. The dependency warning for common rules is a good checkpoint. | 3 / 3 |
Progressive Disclosure | The entire skill is a monolithic document with no references to external files. The 31-skill catalog with descriptions, all rule sets, troubleshooting, and optimization logic are all inline. The skill tables alone consume significant space and could be in a separate CATALOG.md. No bundle files are provided to support splitting, but the content clearly warrants decomposition — the skill catalog, optimization procedures, and troubleshooting could each be separate referenced files. | 1 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
928076c
Table of Contents
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.