codegen-doc

基于当前项目/代码生成各类文档，支持论文章节、项目梳理、重点问题、简历项目描述四种类型。当用户提到生成论文章节、项目梳理、技术难点、简历项目描述时使用。要给新同事看的上手文档（新人文档、架构文档、代码导读、onboarding）用 project-docs。

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 ./skills/codegen-doc/SKILL.md

Quality

Content

71%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-organized, concise, and gives concrete reading guidance with implicit verification principles. Its main weakness is progressive disclosure: the four signaled reference files are missing from the bundle and the path is non-conventional, so the disclosure links do not resolve.

Suggestions

Add the referenced reference/thesis-chapter.md, reference/overview.md, reference/key-issues.md, and reference/resume-format.md files (or correct the path to references/) so the signaled links resolve instead of 404.

Promote the verification principles into an explicit sequenced checkpoint in the workflow, e.g. "generate → cross-check names/claims against code → fix → re-verify", rather than leaving them only in 通用原则.

Align the reference directory name: the body uses "reference/" (singular) but the bundle convention is "references/" — pick one and use it consistently.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence (no library tutorials or concept explanations), e.g. "看轮廓…看骨架…按类型补读"; only minor phrasing could be trimmed, so it sits above the mostly-efficient anchor of 3 but short of the every-token-earns-its-place anchor of 5.	4 / 5
Actionability	Concrete reading guidance (exclude "node_modules / build / dist / vendor", inspect "package.json / pom.xml…", grep "TODO / FIXME") is specific and executable; as an instruction-only skill the absence of code is not penalized, but it stops short of copy-paste-ready examples so it does not reach 5.	4 / 5
Workflow Clarity	A clear sequence exists (Step 0 task table → 3-step "怎么读项目" → 通用原则) with verification guidance such as "技术栈、模块名、接口名要和代码逐字一致"; it lacks an explicit generate→verify→fix→re-verify feedback loop, so it does not reach 5.	4 / 5
Progressive Disclosure	The task table signals one-level-deep references (reference/thesis-chapter.md, overview.md, key-issues.md, resume-format.md), but none of these files exist in the bundle and the path uses "reference/" while the convention is "references/", so navigation is broken and disclosure is incomplete.	3 / 5
	Total	15 / 20 Passed

Description

87%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 strong description: it concisely names the domain and four concrete output types, gives explicit natural-language triggers, and carves out a clear boundary against the related project-docs skill. The only weakness is generic verb phrasing and lack of synonym/extension variants in the triggers.

Dimension	Reasoning	Score
Specificity	"生成各类文档，支持论文章节、项目梳理、重点问题、简历项目描述四种类型" lists four concrete document output types, matching the anchor for several specific actions; the generating verb itself stays generic, so it does not reach the comprehensive anchor of 5.	4 / 5
Completeness	It explicitly states both what it does (generates the four document types from the current project/code) and when to use it ("当用户提到…时使用") with concrete trigger phrases, matching the top anchor; it is not capped at 3 because an explicit 'Use when...' equivalent is present.	5 / 5
Trigger Term Quality	"当用户提到生成论文章节、项目梳理、技术难点、简历项目描述时使用" supplies natural trigger phrases a user would say; it lacks synonyms and file-extension-style variants, so it falls short of the comprehensive anchor of 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche (evaluator-facing docs from code) with distinct triggers, plus explicit boundary guidance ("要给新同事看的上手文档…用 project-docs") that actively routes the overlapping onboarding case elsewhere, minimizing conflict risk.	5 / 5
	Total	18 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: xstongxue/best-skills
Path: skills/codegen-doc/SKILL.md
Commit: 88a38bb

Reviewed: ~1 hour 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.