Tessl • The package manager for agent skills

SkillPublic

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

60%

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

42%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-sectioned and short, but its guidance is abstract (no concrete tools, commands, or examples), validation is only implicit, and it twice points to a playbook file that is missing from the bundle. It reads more like an outline of intent than an executable procedure.

Suggestions

Ship the referenced file or remove both references — "resources/implementation-playbook.md" currently dead-ends; if the file is intentional, include it in the bundle.

Add one concrete worked element to Instructions, e.g. a specific command (mkdocs/docstring generation) or an output doc skeleton showing section structure.

Make validation an explicit checkpoint with a feedback loop, e.g. "Cross-check every generated claim against the source file; fix mismatches before writing output".

Delete the duplicated persona paragraph (it repeats the description verbatim) and fold the Context section into Use/Do-not-use to reclaim tokens.

Dimension	Reasoning	Score
Conciseness	The opening paragraph "You are a documentation expert specializing in..." duplicates the frontmatter description verbatim and the Context section restates the Use/Do-not-use bullets, so the body is mostly efficient but carries noticeable redundant padding (anchor 3 rather than 4, since verbatim duplication is more than minor over-explanation).	3 / 5
Actionability	The instructions are high-level hints — "Identify required doc types and target audiences", "Extract information from code, configs, and comments", "Add automation (linting, CI) and validate accuracy" — with no tools, commands, templates, or doc-structure examples, matching anchor 2 (minimal concrete guidance, missing the specific steps to execute) rather than 3 (some concrete guidance present).	2 / 5
Workflow Clarity	The instruction bullets form a rough sequence (identify types → extract info → generate docs → add automation → validate) but "validate accuracy" is a single implicit step with no checkpoint, error-recovery loop, or feedback mechanism, matching anchor 3 (sequence present, checkpoints missing or implicit).	3 / 5
Progressive Disclosure	Section organization is clean and detail is pushed to a single reference, but "resources/implementation-playbook.md" is referenced twice (Instructions and Resources) and does not exist anywhere in the bundle, so navigation dead-ends — a broken reference is more than the "minor organization gaps" of anchor 4, while the structure itself is better than anchor 2's inlined-wall-of-text.	3 / 5
	Total	11 / 20 Passed

Description

61%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 clearly states what the skill produces (API docs, architecture diagrams, user guides, technical references from code) but never says when to use it, and it opens with a second-person persona statement instead of third-person action phrasing. Keywords are decent, with some natural synonyms missing.

Suggestions

Rewrite in third person and lead with actions, e.g. "Generates API docs, architecture diagrams, user guides, and technical references from code" instead of "You are a documentation expert...".

Append an explicit trigger clause, e.g. "Use when generating or standardizing documentation from a codebase, or when the user mentions API docs, user guides, READMEs, or doc pipelines.".

Replace the buzzword tail "using AI-powered analysis and industry best practices" with concrete capability words such as "adds doc linting and CI validation".

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("Generate API docs, architecture diagrams, user guides, and technical references") which sits at anchor 4, but the second-person opening "You are a documentation expert..." triggers the third-person voice penalty (-1), and "using AI-powered analysis and industry best practices" is buzzword padding rather than a concrete action.	3 / 5
Completeness	The "what" is clear (generate documentation artifacts from code) but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines; it is not a 4 because "when" is entirely absent rather than merely under-specified.	3 / 5
Trigger Term Quality	"API docs", "architecture diagrams", "user guides", and "technical references" are phrases users naturally say, giving good keyword coverage; common variations like "document code", "README", or "docstrings" are missing, so it falls short of anchor 5.	4 / 5
Distinctiveness Conflict Risk	"documentation ... from code" combined with the specific artifact types carves a recognizable niche with only minor overlap risk against closely related skills (README generators, general writing skills); it is not a 5 because the broad "documentation expert" framing could still collide with generic doc-writing requests.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/code-documentation-doc-generate/SKILL.md
Revision: 64adc55

Reviewed: 19 hours 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.

code-documentation-doc-generate

Table of Contents

Is this your skill?