build-inspector

分析构建系统拓扑，识别独立构建单元、多产物风险和版本漂移隐患。

1.17x

Quality

47%

Does it follow best practices?

Impact

94%

1.17x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.trae/skills/build-inspector/SKILL.md

Quality

Discovery

32%

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 identifies a specific technical domain (build system analysis) with some concrete capabilities, but suffers from missing explicit trigger guidance ('Use when...') and relies heavily on technical jargon that users may not naturally use. The Chinese language description is functional but would benefit from more user-facing keywords and clear activation conditions.

Suggestions

Add a 'Use when...' clause with trigger terms like 'build system', 'monorepo', 'dependency analysis', 'build configuration', or specific file types like 'BUILD', 'pom.xml', 'package.json'

Include more natural user-facing keywords alongside technical terms - e.g., 'build errors', 'dependency conflicts', 'build optimization'

Specify concrete outputs or actions - e.g., 'generates dependency graphs', 'produces build order recommendations', 'outputs risk reports'

Dimension	Reasoning	Score
Specificity	Names the domain (build systems) and lists some actions (analyze topology, identify independent build units, multi-artifact risks, version drift risks), but the actions are somewhat abstract and could be more concrete about what specific outputs or operations are performed.	2 / 3
Completeness	Describes what the skill does (analyze build system topology and identify risks) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Contains technical terms like '构建系统' (build system), '拓扑' (topology), '版本漂移' (version drift), but these are specialized jargon. Missing common user-facing terms like 'build', 'dependencies', 'monorepo', 'CI/CD', or file types users might mention.	2 / 3
Distinctiveness Conflict Risk	The focus on build system topology and version drift is fairly specific, but could overlap with general code analysis, dependency management, or CI/CD skills. The lack of explicit triggers increases conflict risk.	2 / 3
	Total	7 / 12 Passed

Implementation

62%

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

This skill provides a solid conceptual framework for analyzing build system topology with clear workflows and decision criteria. However, it relies heavily on stylistic flourishes ('老师傅', metaphors) that consume tokens without adding value, and lacks executable code examples that would make it immediately actionable. The workflow structure is strong but the actionability suffers from pseudocode rather than real tool invocations.

Suggestions

Replace the pseudocode `find_by_name(pattern=...)` with actual executable commands (e.g., `find . -name 'Cargo.toml' -o -name 'package.json'` or specific tool invocations)

Remove or minimize the stylistic elements ('老师傅箴言', emojis, metaphors) to improve token efficiency while keeping the technical content

Add concrete code examples for checking workspace configuration (e.g., parsing Cargo.toml for [workspace] section)

Consider splitting the ecosystem-specific checks (Rust/Node/Go) into a separate reference file for progressive disclosure

Dimension	Reasoning	Score
Conciseness	The skill has some unnecessary stylistic elements (quotes, emojis, 'old master' metaphors) that add tokens without value. However, the core technical content is reasonably efficient and the tables are well-structured.	2 / 3
Actionability	Provides concrete file patterns and decision tables, but lacks executable code examples. The find_by_name command is pseudocode-like rather than a real tool invocation, and there are no actual code snippets for validation or analysis.	2 / 3
Workflow Clarity	Clear three-step workflow (Locate -> Check -> Identify) with explicit decision points. The tables provide clear criteria for judgment, and the output checklist defines exactly what should be produced.	3 / 3
Progressive Disclosure	Content is well-organized with clear sections, but everything is in a single file. For a skill of this complexity, some content (like the risk label system or ecosystem-specific checks) could be split into reference files.	2 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: Lingjie-chen/MT5
Commit: 3069d33

Reviewed: 26 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.