CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

source-command-generate-api-docs

Create comprehensive API documentation from source code

Quality

68%

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 ./.agents/skills/source-command-generate-api-docs/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 admirably lean and well-organized for a simple single-purpose skill, with concrete paths and output specifications. Its weaknesses are the lack of any executable guidance (no commands or code for scanning/extracting) and the absence of validation checkpoints in what is a batch operation over all files in /src/api/.

Suggestions

Add concrete executable guidance for the scan/extract steps, e.g. a ripgrep or find command for /src/api/ and how function signatures and JSDoc comments should be extracted, instead of only naming the actions.

Add a validation step after generation, e.g. verify every exported endpoint in /src/api/ appears in /docs/api.md and that curl examples are syntactically valid.

Clarify ambiguous steps like 'Organizing by endpoint/module' by specifying the grouping rule (by file, by router, or by HTTP method).

DimensionReasoningScore

Conciseness

The body is lean and efficient with zero padding: it assumes Claude's competence, contains no explanations of known concepts, and every line (paths, output format, deliverables) earns its place. This matches the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

There are concrete specifics ("Scanning all files in /src/api/", "Markdown file in /docs/api.md", curl examples, TypeScript types) but no executable commands, code, or method for scanning/extracting — the numbered list is essentially a pseudocode-level spec. Not level 4 because no concrete code or commands are provided; better than level 2 because specific paths, formats, and deliverables are stated.

3 / 5

Workflow Clarity

Steps 1-6 form a clear sequence with a defined output format, but there are no validation or verification checkpoints (e.g., confirming every endpoint is documented or the output file is well-formed), and the scan of all files in /src/api/ is a batch operation, capping workflow clarity at 3. Not level 2 because the sequence itself is complete and well-ordered.

3 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, has no bundle files, and consists of well-organized sections (intro, command template steps, output format), so the simple-skill exception applies and progressive disclosure scores 5. Navigation is trivial and nothing that belongs in a separate file is inlined.

5 / 5

Total

16

/

20

Passed

Description

48%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 communicates the skill's domain and output but is thin: it relies on a single generic verb, omits any 'Use when...' trigger guidance, and provides few natural trigger terms. Its strongest quality is that the API-documentation-from-source-code niche is reasonably distinct from other skills.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to run generate-api-docs, or wants API docs, endpoint reference, or documentation generated from source code.'

Enumerate the concrete actions already present in the body (extract function signatures and JSDoc comments, generate curl examples and TypeScript types, write /docs/api.md) instead of the generic 'Create comprehensive API documentation'.

Include natural synonyms users would say — 'API docs', 'document the API', 'endpoint reference', 'JSDoc' — to improve trigger term coverage.

DimensionReasoningScore

Specificity

The description names the domain ("API documentation from source code") but offers only a single generic action ("Create"), with "comprehensive" serving as fluff rather than a concrete capability. This matches the anchor 'Names the domain but actions are minimal or generic' rather than the level-3 anchor, which expects 1-2 concrete actions like 'extracts content'.

2 / 5

Completeness

The 'what' is clearly stated (create API documentation from source code), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not level 2 because the 'what' is concrete, not vague.

3 / 5

Trigger Term Quality

"API documentation" and "source code" are relevant keywords a user might say, but common variations and synonyms ("API docs", "document the API", "endpoints", "JSDoc", "reference docs") are missing. This is 'some relevant keywords but missing common variations', not level 4's good coverage.

3 / 5

Distinctiveness Conflict Risk

"API documentation from source code" carves out a mostly distinct niche with only minor overlap risk against general documentation or README-generation skills, matching 'mostly distinct; minor overlap risk'. It is not level 5 because the absence of explicit trigger phrases leaves it less distinguishable from closely related docs skills.

4 / 5

Total

12

/

20

Passed

Validation

100%

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

tonykay/transcriber

Path

.agents/skills/source-command-generate-api-docs/SKILL.md

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.