code-documentation-doc-generate

You are a documentation expert specializing in creating comprehensive, maintainable documentation from code. Generate API docs, architecture diagrams, user guides, and technical references using AI-powered analysis and industry best practices.

Quality

42%

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/code-documentation-doc-generate/SKILL.md

Quality

Content

35%

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 and concise-ish, but its guidance is abstract rather than actionable, and its only progressive-disclosure reference points to a missing file. The skill tells Claude what to think about more than exactly what to do.

Suggestions

Replace abstract directives with concrete, executable guidance: name specific tools/commands (e.g., a doc-gen CLI, a linter like markdownlint, a CI snippet) and a minimal worked example.

Add an explicit validation checkpoint with a feedback loop (e.g., 'lint generated docs, fix errors, re-lint, only commit when clean') rather than a bare 'validate accuracy' bullet.

Either create 'resources/implementation-playbook.md' or remove the dangling references in the Instructions and Resources sections so progressive disclosure points to real content.

Dimension	Reasoning	Score
Conciseness	The body uses lean bullets and clear sections, but it repeats the frontmatter description verbatim and the Context section restates the skill's intent, adding tokens that do not earn their place.	2 / 3
Actionability	Instructions are abstract ('Extract information from code, configs, and comments', 'Add automation (linting, CI)') with no concrete commands, tools, code, or copy-paste-ready guidance; it describes rather than instructs.	1 / 3
Workflow Clarity	The Instructions are sequenced, but validation is only vaguely mentioned ('validate accuracy') with no explicit checkpoints or error-recovery feedback loop.	2 / 3
Progressive Disclosure	Sections are well organized and the single detail reference is clearly signaled, but the referenced file 'resources/implementation-playbook.md' does not exist, so the one-level-deep navigation is broken.	2 / 3
	Total	7 / 12 Passed

Description

50%

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 conveys the skill's purpose and lists concrete artifact types, but its second-person voice and missing 'Use when...' trigger guidance limit it across all dimensions. It reads as capable but not yet optimized for skill-discovery triggering.

Suggestions

Rewrite in third person (e.g., 'Generates API docs, architecture diagrams, user guides, and technical references from code') and add an explicit 'Use when...' clause naming natural trigger terms like 'write API docs', 'generate documentation', or 'create user guides'.

Add common user phrasings ('write docs', 'document my code', 'README generation') to broaden trigger-term coverage and reduce overlap with generic documentation skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Generate API docs, architecture diagrams, user guides, and technical references'), which would score 3, but opens with second-person voice ('You are a documentation expert'), triggering the rubric's -1 specificity penalty.	2 / 3
Completeness	Clearly states what the skill does, but provides no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Contains relevant terms like 'documentation', 'API docs', and 'user guides', but lacks an explicit 'Use when...' trigger and omits common phrasings users would naturally say, so it only partially covers natural trigger terms.	2 / 3
Distinctiveness Conflict Risk	The code-to-documentation niche is somewhat specific, but the absence of distinct triggers means it could still overlap with other documentation or code-analysis skills.	2 / 3
	Total	8 / 12 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: rmyndharis/antigravity-skills
Path: skills/code-documentation-doc-generate/SKILL.md
Commit: e63f7dd

Reviewed: about 5 hours 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.