CtrlK
BlogDocsLog inGet started
Tessl Logo

api-documenter

Master API documentation with OpenAPI 3.1, AI-powered tools, and modern developer experience practices. Create interactive docs, generate SDKs, and build comprehensive developer portals.

25

Quality

16%

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 ./plugins/antigravity-awesome-skills/skills/api-documenter/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

0%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill reads as a persona description or capability catalog rather than actionable documentation. It lists dozens of topics Claude should know about (OpenAPI, OAuth, SDK generation, etc.) but provides zero concrete examples, code snippets, commands, or specific workflows. The content is almost entirely abstract bullet points that describe what an API documentation expert would do, rather than teaching Claude how to do it.

Suggestions

Replace the abstract 'Capabilities' bullet lists with concrete, executable examples—e.g., a minimal OpenAPI 3.1 spec template, a specific command to generate an SDK with openapi-generator, or a working curl example with authentication.

Add a clear multi-step workflow with validation checkpoints, such as: write spec → validate with `spectral lint` → generate docs with Redoc → test examples → publish. Include specific commands at each step.

Remove the 'Behavioral Traits', 'Knowledge Base', and 'Example Interactions' sections entirely—they consume tokens without adding actionable value. Claude doesn't need to be told to 'prioritize developer experience'.

If the skill is meant to cover many sub-topics, create bundle files (e.g., OPENAPI_TEMPLATE.md, SDK_GENERATION.md, AUTH_DOCS.md) with concrete content and reference them from a lean SKILL.md overview.

DimensionReasoningScore

Conciseness

Extremely verbose and padded with information Claude already knows. The massive 'Capabilities' section is essentially a taxonomy of API documentation topics that provides no actionable guidance—it reads like a resume or marketing brochure. 'Behavioral Traits' and 'Knowledge Base' sections restate obvious qualities. The entire document could be reduced by 80%+ without losing useful information.

1 / 3

Actionability

Despite being about API documentation, there is zero executable code, no concrete OpenAPI spec examples, no specific commands, no tool invocations, and no copy-paste-ready snippets. Everything is described at an abstract level ('OpenAPI 3.1+ specification authoring with advanced features') without showing how to actually do anything.

1 / 3

Workflow Clarity

The 'Instructions' section lists 4 extremely vague steps ('Create or validate specifications with examples and auth flows') with no concrete details, no validation checkpoints, and no error recovery. The 'Response Approach' section is similarly abstract. For a skill involving spec authoring and SDK generation, there are no verification steps whatsoever.

1 / 3

Progressive Disclosure

The content is a monolithic wall of bullet-pointed lists with no external references, no linked files, and no layered structure. Everything is dumped into a single file with no navigation aids. There are no bundle files to reference, yet the content doesn't compensate by being well-organized—it's just flat lists of topics.

1 / 3

Total

4

/

12

Passed

Description

32%Scale 1-3

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 identifies a reasonable domain (API documentation with OpenAPI) and lists some concrete outputs, but relies heavily on buzzwords like 'AI-powered tools' and 'modern developer experience practices' without specificity. The complete absence of a 'Use when...' clause significantly weakens its utility for skill selection, and the trigger terms miss common user vocabulary like 'Swagger' or 'API spec'.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about API documentation, OpenAPI specs, Swagger files, SDK generation, or building developer portals.'

Replace vague phrases like 'AI-powered tools' and 'modern developer experience practices' with concrete actions such as 'validate OpenAPI specs, generate client libraries, create API reference pages'.

Include common trigger term variations users would naturally say: 'Swagger', 'API spec', 'REST docs', '.yaml', '.json', 'API reference'.

DimensionReasoningScore

Specificity

Names the domain (API documentation) and lists some actions like 'Create interactive docs, generate SDKs, and build comprehensive developer portals,' but also includes vague phrases like 'AI-powered tools' and 'modern developer experience practices' that are more buzzwords than concrete actions.

2 / 3

Completeness

Describes what the skill does (create docs, generate SDKs, build portals) but completely lacks any 'Use when...' clause or explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' portion is also somewhat vague, placing this at 1.

1 / 3

Trigger Term Quality

Includes some relevant keywords like 'OpenAPI 3.1', 'API documentation', 'SDKs', and 'developer portals', but misses common user variations like 'Swagger', 'REST API docs', 'API spec', 'API reference', or file extensions like '.yaml'/'.json'. The term 'AI-powered tools' is vague and unlikely to be a natural trigger.

2 / 3

Distinctiveness Conflict Risk

The mention of OpenAPI 3.1 and SDK generation provides some distinctiveness, but 'API documentation' and 'developer portals' are broad enough to overlap with general documentation skills or web development skills. The buzzword 'AI-powered tools' further muddies the niche.

2 / 3

Total

7

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
popey/claude-code-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.