api-test-suite-builder

Use when the user asks to generate API tests, create integration test suites, test REST endpoints, or build contract tests.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./engineering/skills/api-test-suite-builder/SKILL.md

Quality

Content

80%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 highly actionable with executable route-detection commands and concrete test matrices, and it uses progressive disclosure well by offloading full templates to a single well-signaled reference. Its main weakness is the generation workflow, which lacks a validation/verification step for the batch operation of producing test suites.

Suggestions

Add an explicit validation step to the generation workflow (e.g., "Run the generated suite; fix any failing assertions or misdetected routes before considering the task complete") to introduce a feedback loop.

Trim advisory color in Common Pitfalls and Best Practices to one-line, non-editorial guidance to improve token efficiency.

Consider moving the per-framework route-detection command blocks into the reference file to keep the overview leaner, since they are reference-style material.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no concept explanations of JWTs, auth, or pagination) and leads with executable commands and matrices; minor advisory color in Common Pitfalls and Best Practices (e.g., "80% of bugs live in error paths") could be trimmed, fitting anchor 4 rather than the fully lean anchor 5.	4 / 5
Actionability	Copy-paste-ready route-detection bash commands cover four frameworks, and the auth/input-validation matrices give concrete test cases with expected status codes, fully covering the common cases per anchor 5 rather than the "mostly executable" anchor 4.	5 / 5
Workflow Clarity	The "Generating Tests from Route Scan" section gives a clear numbered sequence (Scan → Read handler → Generate → Name → Factories → Assert), but there is no validation/verification checkpoint such as running the generated tests and fixing failures; for batch test generation the missing feedback loop caps this at anchor 3.	3 / 5
Progressive Disclosure	A clear overview is supported by well-organized sections, and the heavy test-file templates are split into a single clearly-signaled one-level reference ("→ See references/example-test-files.md"), which is real and non-nested, matching anchor 5.	5 / 5
	Total	17 / 20 Passed

Description

75%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 uses an explicit "Use when" trigger structure with several natural, concrete trigger terms, but it front-loads the "when" and leaves the "what" implied through those triggers rather than a clean declarative capability statement. It is specific and distinct but not comprehensive.

Suggestions

Lead with a declarative capability statement (e.g., "Scans API route definitions and generates ready-to-run test suites") before the "Use when" clause so the "what" is explicit rather than embedded in triggers.

Add distinguishing detail such as supported frameworks (Next.js, Express, FastAPI, Django) or output targets (Vitest/Pytest) to sharpen distinctiveness and specificity.

Include a synonym or two users might say (e.g., "endpoint tests", "API regression tests") to push trigger-term coverage toward comprehensive.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ("generate API tests", "create integration test suites", "test REST endpoints", "build contract tests"), but they are overlapping variants of test-making with minor coverage gaps (no frameworks or output formats), matching anchor 4 rather than the comprehensive anchor 5.	4 / 5
Completeness	The "when" is explicit with concrete trigger phrases ("Use when the user asks to..."), and the "what" is conveyed through those same actions, but the what is embedded in triggers rather than a standalone declarative statement, fitting anchor 4 instead of anchor 5.	4 / 5
Trigger Term Quality	Natural user-facing terms like "API tests", "integration test suites", "REST endpoints", and "contract tests" are present, giving good keyword coverage; it stops short of anchor 5 because synonyms and extension-style variations are missing.	4 / 5
Distinctiveness Conflict Risk	The API/REST/contract-testing niche is mostly distinct with low conflict risk, but it could overlap with general test-generation skills and omits the route-scanning feature that would make it fully distinctive, so anchor 4 fits better than 5.	4 / 5
	Total	16 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: alirezarezvani/claude-skills
Path: engineering/skills/api-test-suite-builder/SKILL.md
Commit: 19392f7

Reviewed: ~5 hours ago

Table of Contents

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.