Tessl • The management layer for AI agent skills

A lean, highly actionable skill body: exact executable commands backed by a real bundled script, a clear 5-step workflow with a validation step, and well-organized sections with appropriate use of a single script file for implementation detail. Remaining gaps are minor — a motivational slogan block, no failure-recovery guidance around the --force overwrite path, and some inline detail that could be delegated to the script.

Dimension	Reasoning	Score
Conciseness	The body is dominated by tight tables and lists (language support matrix, generated-content checklists) with copy-paste commands, but the "核心原则" slogan block ("无文档不成模块 / 文档是模块的身份证...") is motivational padding Claude does not need, and the "提取的信息" list partially repeats the language table. This matches 'efficient with minor instances that could be trimmed' rather than the fully lean 5 anchor.	4 / 5
Actionability	The usage section gives exact, copy-paste-ready commands — "node scripts/doc_generator.js <模块路径>" with "--force" and "--json" flags — and the referenced script (scripts/doc_generator.js, 435 lines) actually exists in the bundle and implements the described behavior. Combined with the concrete fill-in TODO workflow and per-file checklists, this fully matches the top anchor.	5 / 5
Workflow Clarity	The "使用流程" section lays out a clear 5-step sequence ending in an explicit validation step ("运行 /verify-module 校验完整性") and is reinforced by post-generation checklists, matching 'clear sequence with most checkpoints present'. It stops short of a 5 because there is no error-recovery feedback loop (what to do when verification fails) and the destructive "--force" overwrite path carries no caution or validation guidance.	4 / 5
Progressive Disclosure	The body acts as a proper overview: implementation lives in the single, correctly-signaled one-level-deep reference scripts/doc_generator.js (verified to exist), and sections are well-organized with clear headers. It sits at 4 rather than 5 because the detailed README/DESIGN skeleton contents are inlined in the body (arguably belonging in the script's output or a reference file), and the /verify-module dependency is referenced without any pointer to where that skill lives.	4 / 5
	Total	17 / 20 Passed

Description

78%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-formed, third-person description that clearly states what the skill does and when to use it, with explicit trigger phrases and auto-trigger timing. Its main weaknesses are limited action coverage (only two capabilities named despite the skill doing more) and one overly broad trigger term that creates minor conflict risk with general documentation skills.

Suggestions

Expand the 'what' portion to enumerate more of the concrete capabilities already implemented, e.g. "提取类与函数定义、检测语言与依赖、生成目录结构" (extract class/function definitions, detect language and dependencies, generate directory structure), to lift specificity from 2 actions to several.

Add missing natural trigger synonyms such as "写文档", "补文档", or "API 文档" so the trigger list covers the common variations users say, moving trigger term quality toward comprehensive.

Narrow the generic trigger "生成文档" to something like "生成模块文档" to reduce overlap with general document-writing skills.

Dimension	Reasoning	Score
Specificity	The description names the domain and exactly two concrete actions — "自动分析模块结构，生成 README.md 和 DESIGN.md 骨架" (auto-analyze module structure, generate README.md and DESIGN.md skeletons) — which matches the '1-2 concrete actions, not comprehensive' anchor. It does not list the several specific actions (dependency extraction, class/function listing, language detection) that would warrant a 4.	3 / 5
Completeness	It explicitly answers both questions: the 'what' is "自动分析模块结构，生成 README.md 和 DESIGN.md 骨架" and the 'when' is a concrete 'Use when...' clause listing trigger phrases plus "在新建模块开始时自动触发" for auto-trigger timing. This matches the top anchor with explicit what AND when with concrete trigger phrases, rather than the 4 anchor where the 'when' is less specific.	5 / 5
Trigger Term Quality	The trigger clause "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" provides five natural phrases users would actually say, giving good coverage. It falls short of a 5 because common synonyms and variations (e.g., 写文档, 补文档, documentation, docs) are missing.	4 / 5
Distinctiveness Conflict Risk	The niche (module README/DESIGN skeleton generation) is mostly distinct, with specific triggers like "创建README" and "文档骨架" giving clear differentiation. Minor overlap risk remains because the broad trigger "生成文档" could also match general document-writing or API-doc skills, keeping it below a 5.	4 / 5
	Total	16 / 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: templates/skills/tools/gen-docs/SKILL.md
Revision: 2f12cc5

Reviewed: 9 days ago

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.

gen-docs

Table of Contents

Is this your skill?