CtrlK
BlogDocsLog inGet started
Tessl Logo

code-documentation

Writing effective code documentation - API docs, README files, inline comments, and technical guides. Use for documenting codebases, APIs, or writing developer guides.

61

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/code-documentation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 delivers concrete, well-organized documentation templates that are mostly copy-paste ready, but it spends significant tokens on boilerplate Claude already knows and offers no workflow for deciding what to document or keeping docs current. Structure and navigation are good for a single-file skill, though bulky templates would be better split into reference files.

Suggestions

Trim or drop templates that restate common knowledge (generic README skeleton, standard JSDoc syntax, stock OpenAPI 3.0 schema) and keep only the project's preferred conventions and deviations.

Add a short workflow for producing documentation — e.g., identify the audience, pick the doc type, draft from the template, then check for staleness against the code — so the skill instructs as well as templates.

Move bulky full-length templates (OpenAPI example, ADR format) into a references/ file and keep SKILL.md as a concise overview with clearly signaled links.

DimensionReasoningScore

Conciseness

The body is template-driven rather than padded prose, but substantial portions restate knowledge Claude already has — a stock README skeleton, standard JSDoc/TSDoc syntax, a generic OpenAPI 3.0 schema, and basics like "BAD: Increment counter by 1". This fits the anchor for mostly efficient content with some unnecessary material that could be tightened; it is not verbose enough for 2, but too much boilerplate for 4.

3 / 5

Actionability

Concrete, mostly copy-paste-ready material dominates: the README template, full JSDoc example, OpenAPI YAML, and ADR template. Minor gaps remain — "if (user.role === 'admin') { ... }" and placeholder lines like "Detailed installation instructions..." and "How to contribute..." keep it below fully executable.

4 / 5

Workflow Clarity

No multi-step process is presented at all — the body is a static template collection with no sequence for producing documentation (e.g., audit the code, choose doc types, draft, verify freshness), and the closing "Documentation Principles" are abstract rather than procedural. Non-destructive so no validation cap applies, but the under-50-line simple-skill exception does not cover a 256-line reference, so it sits at organized-but-no-workflow rather than higher.

3 / 5

Progressive Disclosure

The single-file body is well organized with clean sections (README Structure, API Documentation, Inline Comments, Architecture Documentation, Principles) and no nested or buried references since no bundle files exist. Bulky templates like the full OpenAPI example and ADR are inlined where a separate reference file would better serve a quick-start-first pattern, matching the anchor for good structure with minor organization gaps rather than an ideal overview-plus-references split.

4 / 5

Total

14

/

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 names four concrete documentation deliverables and pairs them with an explicit, concrete "Use for..." trigger clause covering both what and when. Keyword coverage is good though not exhaustive, and the niche is mostly distinct from related skills.

Suggestions

Add the trigger synonyms users naturally say — "docstrings", "JSDoc", "changelog", "write a README" — to lift trigger term coverage toward comprehensive.

Mention architecture decision records (ADRs) or changelogs in the description, since the body covers them, to close the specificity gap and sharpen distinctiveness.

DimensionReasoningScore

Specificity

"API docs, README files, inline comments, and technical guides" names four concrete deliverables, matching the anchor for several specific actions with minor gaps (architecture docs/ADRs and changelogs, which the body covers, are omitted). Not 3 since more than 1-2 concrete actions are named; not 5 since everything hangs off the single verb "Writing" with coverage gaps.

4 / 5

Completeness

"Writing effective code documentation - API docs, README files, inline comments, and technical guides" explicitly answers what, and "Use for documenting codebases, APIs, or writing developer guides" explicitly answers when with concrete trigger domains. Anti-drift check against score 4 (when "could be more explicit") confirms the when-clause is explicit and enumerates specific triggers rather than vaguely restating the what.

5 / 5

Trigger Term Quality

Natural phrases users would say are present — "documenting codebases", "APIs", "developer guides", "README", "inline comments" — but common variations like "docstrings", "JSDoc", "changelog", or "write a README" are missing. This matches the anchor for good keyword coverage with a few natural terms missing rather than comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

"Writing effective code documentation" carves a clear niche with distinct triggers (README, API docs, inline comments, developer guides), with only minor overlap risk against general technical-writing or code-review skills. Not 5 because "technical guides" and "developer guides" are broad enough to brush against adjacent writing skills.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
MoizIbnYousaf/ai-agent-skills
Reviewed

Table of Contents

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.