codebase-design

用于设计深模块的共享词汇。适用于用户想设计或改进模块接口、寻找深化机会、决定 seam 放在哪里、让代码更容易测试或更适合 AI 导航，或其他技能需要深模块词汇时。

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/engineering/codebase-design/SKILL.md

Quality

Content

76%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, well-written conceptual skill that establishes a precise deep-modules vocabulary with executable testability examples and clear diagrams. It is highly token-efficient and actionable as design guidance, but the 'Going deeper' references to DEEPENING.md and DESIGN-IT-TWICE.md point to bundle files that are not present, which weakens progressive disclosure, and it offers principles rather than a sequenced workflow.

Suggestions

Provide the referenced DEEPENING.md and DESIGN-IT-TWICE.md files (or remove/replace the links), since the 'Going deeper' section currently points to non-existent bundle files.

Add a short concrete design procedure (e.g., a numbered sequence: identify interface → apply deletion test → place seam → verify via interface) to lift workflow clarity beyond principles and heuristics.

Confirm the referenced file paths match the actual bundle layout so progressive disclosure can be scored against the real structure.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence: it defines a precise shared vocabulary and principles without explaining basic programming concepts Claude already knows, and every section earns its tokens.	5 / 5
Actionability	Concrete executable TypeScript snippets illustrate testable vs hard-to-test patterns and ASCII diagrams make deep/shallow tangible, but the bulk is conceptual guidance and design questions rather than copy-paste-ready commands across common cases.	4 / 5
Workflow Clarity	No multi-step destructive or batch workflow is presented, so the simple-skill exception applies; however the guidance is principles + heuristics (e.g., the 'deletion test', 'interface is the test surface') without an explicit sequenced procedure, which sits at the midpoint.	3 / 5
Progressive Disclosure	The body signals one-level-deep references to DEEPENING.md and DESIGN-IT-TWICE.md under 'Going deeper', but those bundle files are absent, so the references are not actually resolvable and the structure cannot be verified as well-organized.	3 / 5
	Total	15 / 20 Passed

Description

75%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-constructed Chinese-language description that clearly states both what the skill provides (a shared vocabulary for designing deep modules) and when to use it (via an explicit '适用于…' clause listing concrete scenarios). It is specific, uses natural trigger terms, and is largely distinct from other skills, though the 'when' clause is scenario-listed rather than the canonical 'Use when…' form.

Dimension	Reasoning	Score
Specificity	The description lists several concrete capabilities — '设计或改进模块接口', '寻找深化机会', '决定 seam 放在哪里', '让代码更容易测试或更适合 AI 导航' — which are specific actions rather than vague fluff, though they describe application scenarios more than discrete operations.	4 / 5
Completeness	Both 'what' (a shared vocabulary for designing deep modules) and 'when' (the '适用于…' clause enumerating scenarios) are present; the 'when' is explicit and multi-scenario but phrased as a list of situations rather than the crisp 'Use when…' anchor form.	4 / 5
Trigger Term Quality	It includes natural trigger phrases a user might say like '设计或改进模块接口' and '决定 seam 放在哪里', with good coverage of design/refactoring scenarios; a few common synonyms (e.g., '重构', '接口设计') are implied but not all explicitly stated.	4 / 5
Distinctiveness Conflict Risk	The deep-modules / seam / interface vocabulary carves a clear niche distinct from general coding skills, with minimal overlap risk; it could still brush against generic refactoring or architecture skills, so not a 5.	4 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: vinvcn/mattpocock-skills-zh-CN
Path: skills/engineering/codebase-design/SKILL.md
Commit: 9fe7e7a

Reviewed: 11 days ago

Table of Contents

Discovery Implementation Validation

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.