verify-module

模块完整性校验关卡。扫描目录结构、检测缺失文档、验证代码与文档同步。当用户提到模块校验、文档检查、结构完整性、README检查、DESIGN检查时使用。在新建模块完成时自动触发。

Quality

79%

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 ./dsh-ccg/skills/verify-module/SKILL.md

Quality

Content

75%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.

The body is a tight, actionable verification skill with a real, referenced scanner script, clear sequencing, and useful checklists. Its main weakness is mild redundancy — required files and the report format are restated in multiple places.

Suggestions

Consolidate the required-file definition so '校验标准', '检测项', and the README/DESIGN checklists do not each re-list the same README.md/DESIGN.md requirement.

Replace the static '校验报告格式' template with a note that the scanner emits the report (or show one real `--json` example), since the script already generates it.

Make the consistency-check feedback loop explicit in 校验流程, e.g. '6. 若未通过，运行 /gen-docs 补充文档后重新执行 step 1'.

Dimension	Reasoning	Score
Conciseness	Content is mostly efficient — tables, checklists, and code blocks with no over-explanation of concepts Claude already knows — but the required-file list is restated across '校验标准', '检测项', and the README/DESIGN checklists, and the report-format template duplicates output the script already generates.	4 / 5
Actionability	Provides copy-paste-ready commands ('node scripts/module_scanner.js <模块路径>' with -v/--json flags, plus '/gen-docs <模块路径>') and concrete content checklists; not a 5 because the consistency check (step 5) lacks an executable method.	4 / 5
Workflow Clarity	The 6-step '校验流程' is clearly sequenced and the skill is itself a validation checkpoint with checklists; not a 5 because the fix-then-re-verify feedback loop is only implied via the 快速修复 section rather than an explicit re-scan step.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with a single one-level-deep, clearly signaled bundle reference (scripts/module_scanner.js, which exists); not a 5 because the inline report-format template is content the script already produces and could be deferred.	4 / 5
	Total	16 / 20 Passed

Description

83%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.

The description is well-constructed: it states concrete capabilities, gives explicit 'use when' triggers, and defines a fairly distinct niche. It uses correct third-person voice and avoids vague fluff.

Dimension	Reasoning	Score
Specificity	Names the domain and three concrete actions — '扫描目录结构', '检测缺失文档', '验证代码与文档同步' — giving broad coverage with only minor gaps, matching the 'lists several specific actions' anchor; not a 5 because the actions are not exhaustively enumerated.	4 / 5
Completeness	Explicitly answers both 'what' (scans structure, detects missing docs, verifies code-doc sync) and 'when' ('当用户提到...时使用' plus '在新建模块完成时自动触发') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Lists several natural phrases a user would say — '模块校验', '文档检查', '结构完整性', 'README检查', 'DESIGN检查' — giving good keyword coverage; not a 5 because it omits synonyms and file-extension variants.	4 / 5
Distinctiveness Conflict Risk	The README.md+DESIGN.md module-integrity niche is mostly distinct with specific triggers; not a 5 because broad terms like '文档检查' and '结构完整性' carry some overlap risk with generic documentation skills.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: fengshao1227/ccg-workflow
Path: dsh-ccg/skills/verify-module/SKILL.md
Commit: fba314b

Reviewed: 2 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.