gen-docs

文档生成器。自动分析模块结构，生成 README.md 和 DESIGN.md 骨架。当用户提到生成文档、创建README、创建DESIGN、文档骨架、文档模板时使用。在新建模块开始时自动触发。

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/gen-docs/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 content is well-structured and actionable with concrete generator commands, but loses points on workflow clarity because the destructive --force overwrite path lacks an explicit validation/confirmation checkpoint. Conciseness and progressive disclosure are good with only minor organization gaps.

Suggestions

Add an explicit validation/confirmation step before '--force' overwrites existing README.md/DESIGN.md (e.g., list files to be overwritten and require confirmation), so the destructive path has a real checkpoint.

Trim the metaphorical '核心原则' block or replace it with a one-line actionable rule to improve token efficiency.

Consider splitting the large README.md/DESIGN.md field-spec tables and the supported-languages table into a one-level-deep reference file (e.g. references/fields.md) to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and well-structured with tables and bullet lists and no over-explanation of known concepts; the '核心原则' metaphorical block ('文档是模块的身份证…') is minor padding that could be trimmed, keeping it just below a 5.	4 / 5
Actionability	Provides concrete, copy-pasteable commands ('node scripts/doc_generator.js <模块路径> [--force\|--json]') and a clear generated-content spec; not a 5 because the per-field generation descriptions are stated rather than shown as executable examples.	4 / 5
Workflow Clarity	A usage flow with a terminal '/verify-module' step and post-generation checklists exists, but the '--force' flag overwrites existing documents (a destructive operation) with no explicit pre-overwrite validation/confirmation checkpoint, so the rubric's destructive-operation cap holds it at 3.	3 / 5
Progressive Disclosure	Content is organized into clear sections and references one real bundle file (scripts/doc_generator.js, verified present); not a 5 because all guidance is inlined in SKILL.md with no one-level-deep reference split for the larger spec tables.	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 capabilities, provides explicit natural-language trigger phrases, and clearly covers both what the skill does and when to use it. Minor gaps are limited trigger synonyms/extensions and slight breadth on the generic '生成文档' phrase.

Dimension	Reasoning	Score
Specificity	Names the domain (文档生成器) and several concrete actions — '自动分析模块结构' and '生成 README.md 和 DESIGN.md 骨架' — which matches the anchor listing several specific actions with minor coverage gaps; not a 5 because coverage is limited to two doc types.	4 / 5
Completeness	Explicitly answers both 'what' (analyzes module structure, generates README.md/DESIGN.md skeletons) and 'when' (当用户提到…时使用, plus auto-trigger 在新建模块开始时) with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes good natural trigger phrases ('生成文档、创建README、创建DESIGN、文档骨架、文档模板') that users would say; not a 5 because file extensions (.md) and common English variations are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (module documentation skeleton generation) with distinct triggers; not a 5 because '生成文档' is broad enough to lightly overlap with general 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/gen-docs/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.