verify-quality

代码质量校验关卡。检测复杂度、重复代码、命名规范、函数长度等质量指标。当用户提到代码质量、复杂度检查、代码异味、重构建议、lint检查、代码规范时使用。在复杂模块、重构完成时自动触发。

Quality

76%

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-quality/SKILL.md

Quality

Content

68%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 well-structured, actionable, and token-efficient, delegating computation to a real bundled script. Its main weakness is workflow_clarity: the documented process lists steps but lacks validation/feedback checkpoints for a batch scanning operation, capping that dimension.

Suggestions

Add an explicit validation/feedback checkpoint to the 校验流程, e.g. after running the checker: review failures, fix high-severity issues, then re-run "node scripts/quality_checker.js <路径> --json" to confirm the pass count improves.

Trim the motivational aphorisms in 核心原则 and the 道基/异端/正道 commentary in the refactoring examples to reduce padding that Claude does not need.

Make the refactoring examples more concrete by replacing placeholder conditions (condition1/2/3) with a realistic data-processing example so the pattern is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Mostly lean with token-efficient tables and a real script invocation, but the boxed "核心原则" aphorisms ("劣质代码是技术债，技术债是道基裂痕") and the 道基/异端/正道 flavorings in examples are minor motivational padding that could be trimmed.	4 / 5
Actionability	Gives a concrete, executable command ("node scripts/quality_checker.js <扫描路径>") backed by a real bundle script, plus specific threshold tables and a report template; the Python refactoring snippets use placeholder conditions, which is a minor gap.	4 / 5
Workflow Clarity	The 5-step "校验流程" lists a sequence but has no validation checkpoint or fix-and-retry feedback loop, and code scanning is a batch operation, which per the rubric caps this dimension at 3.	3 / 5
Progressive Disclosure	Well-organized into clear headed sections with the heavy logic offloaded to a one-level-deep, clearly signaled bundle script (scripts/quality_checker.js) that exists on disk; minor organization gaps from the inlined report-format and refactoring blocks.	4 / 5
	Total	15 / 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 strong: it states concrete detection capabilities and gives explicit, natural trigger terms covering both user-invoked and auto-trigger cases. The only weakness is mild overlap risk with adjacent lint/review skills and homogeneous detection-only action verbs.

Dimension	Reasoning	Score
Specificity	Lists several concrete detection actions ("检测复杂度、重复代码、命名规范、函数长度") with the open-ended "等质量指标" for breadth, but all actions are variations of detection with no mention of what is done with results.	4 / 5
Completeness	Explicitly answers both what ("检测...质量指标") and when ("当用户提到...时使用。在复杂模块、重构完成时自动触发") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Provides six natural user-facing triggers ("代码质量、复杂度检查、代码异味、重构建议、lint检查、代码规范") that users would actually say, missing only a few synonyms like code review or test coverage.	4 / 5
Distinctiveness Conflict Risk	Targets a clear code-quality/lint niche with distinct triggers, but has minor overlap risk with general linting or code-review 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-quality/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.