CtrlK
BlogDocsLog inGet started
Tessl Logo

701-technologies-openapi

Use when you need framework-agnostic OpenAPI 3.x guidance — spec structure, metadata and versioning, paths and operations, reusable schemas, security schemes, examples, documentation quality, contract validation (e.g. Spectral), breaking-change awareness, and handoffs to codegen — without choosing Spring Boot, Quarkus, or Micronaut. This should trigger for requests such as Review an OpenAPI; Improve an OpenAPI; Improve API contract; Improve API schema design. Part of Plinth Toolkit

64

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

65%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 a well-structured overview with excellent progressive disclosure — it delegates all detail to a single real reference file and links to it cleanly. Weaknesses are concentrated in the workflow: verification and change steps are described generically without concrete commands, and the body carries some inherited toolkit boilerplate (Maven/fuzzing constraints, duplicated trigger list) that adds tokens without OpenAPI-specific value.

Suggestions

Make the workflow's verification step concrete by naming the actual checks, e.g. 'validate the spec (spectral lint api.yaml) and re-run the project's contract gate before summarizing results'.

Remove or gate the Maven compile/verify and fuzzing constraints that appear inherited from the parent toolkit and are not relevant to OpenAPI contract review, keeping only constraints the user could act on.

Drop the 'When to use this skill' section that duplicates the frontmatter description verbatim, or replace it with a one-line pointer to save tokens.

DimensionReasoningScore

Conciseness

The body is mostly lean overview material, but 'When to use this skill' duplicates the frontmatter description nearly verbatim, and the Constraints section carries inherited boilerplate ('FUZZING: keep fuzzing guidance high-level...' generic rule, Maven compile/verify commands), Maven compile/verify commands) that is tangential to OpenAPI contract guidance — minor trimmable instances rather than severe padding.

4 / 5

Actionability

Step 1 gives a concrete pointer ('Read references/701-technologies-openapi.md and inspect current API/context artifacts') and the reference file genuinely contains executable YAML examples, but the body's own steps are generic direction — 'Execute appropriate checks', 'Implement or refactor artifacts following the reference patterns' — with no concrete commands or lint/validation specifics, matching 'some concrete guidance but incomplete'.

3 / 5

Workflow Clarity

The 4-step sequence (assess context, gather scope, apply changes, run verification and report) is clearly ordered and ends in a verification step, but the validation checkpoint is implicit and generic ('Execute appropriate checks') with no concrete validation command in the workflow — the same pattern as the anchor-3 example ending in 'Test the output', below anchor 4 which shows explicit commands per step.

3 / 5

Progressive Disclosure

The body is a genuine overview: scope summary, constraints, workflow, and a single well-signaled one-level-deep reference ('For detailed guidance, examples, and constraints, see references/701-technologies-openapi.md') that exists on disk and holds the 591 lines of concrete examples — clear split, easy navigation, no nesting.

5 / 5

Total

15

/

20

Passed

Description

87%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.

A strong description: it clearly states what the skill covers across the full OpenAPI contract lifecycle, gives explicit natural-language trigger phrases, and proactively disambiguates against framework-specific alternatives. The only gaps are a few common synonyms (notably 'Swagger') and the absence of spec file extensions in the trigger vocabulary.

Suggestions

Add common synonyms users would naturally say, e.g. 'Swagger/OpenAPI spec' and spec file extensions like .yaml/.json, to the trigger vocabulary.

Lead with a compact action statement (e.g. 'Reviews and improves OpenAPI 3.x contracts...') before the topic list so capabilities read as actions rather than topic areas.

DimensionReasoningScore

Specificity

The description comprehensively enumerates capability areas ('spec structure, metadata and versioning, paths and operations, reusable schemas, security schemes, examples, documentation quality, contract validation (e.g. Spectral), breaking-change awareness, and handoffs to codegen') with named tools, but it lists topics rather than distinct concrete actions, so it sits at 'several specific actions; minor gaps' rather than fully action-based comprehensive coverage.

4 / 5

Completeness

It explicitly answers both 'what' (framework-agnostic OpenAPI 3.x guidance with a concrete capability list) and 'when' ('Use when you need framework-agnostic OpenAPI 3.x guidance... This should trigger for requests such as Review an OpenAPI...') with concrete trigger phrases, matching the top anchor; a 4 would require the 'when' to be weaker or less explicit than it is here.

5 / 5

Trigger Term Quality

Natural trigger phrases are explicit ('Review an OpenAPI; Improve an OpenAPI; Improve API contract; Improve API schema design') alongside terms like Spectral and codegen, but common synonyms users would say — 'Swagger', 'OpenAPI spec', 'API definition' — and file extensions (.yaml/.json) are missing, so keyword coverage is good but not comprehensive.

4 / 5

Distinctiveness Conflict Risk

The exclusion clause 'without choosing Spring Boot, Quarkus, or Micronaut' explicitly disambiguates this skill from framework-specific siblings, and 'Part of Plinth Toolkit' plus OpenAPI-specific triggers give it a clear niche with minimal overlap risk — it is not merely 'mostly distinct' (4) but fully distinct.

5 / 5

Total

18

/

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
jabrena/plinth
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.