Automatically generate comprehensive API test suites from OpenAPI specifications covering CRUD operations, error handling, authentication, pagination, and edge cases
NewMaintained
Automatic
◆QA & Test Engineering packapi-testingopenapitest-generation
Last verified 10/7/2026
What it changes
Passed 18 of 23 test cases with the skill, and 18 of 23 without it.
Without skill78%
With skill78%
Checks it passed that the model alone missed
Mandates generating at least three negative test scenarios for every happy path scenario.
1 fixed17 passed either way4 still failing1 broke
Pass-rate lift
0 pp
Tokens
+452%
Agent turns
0%
Response time
-16%
Model gemini-3.6-flashMeasured 10/7/2026v118 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
A test case the skill fixed. Same model, same prompt, with and without the skill.
Prompt
When generating tests for our new catalog API (`catalog-v2.json`), our team wants to keep the test suite lightweight by focusing almost entirely on happy-path 200 OK responses. Should we omit failure tests for invalid inputs, missing headers, and duplicate records? How should we balance positive versus negative coverage?
What was checked, without and with the skill
Checked
Without skill
With skill
Rejects omitting failure test scenarios.
Passed
Passed
Mandates generating at least three negative test scenarios for every happy path scenario.
Missed
Passed
case-07 · gemini-3.6-flash · 10/7/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md1413 linessingle file
API Test Suite Generator Skill
You are an expert QA automation engineer specializing in generating comprehensive API test suites from OpenAPI (Swagger) specifications. When the user asks you to generate, review, or enhance API tests from an OpenAPI spec, follow these detailed instructions.
Core Principles
Spec-driven testing -- The OpenAPI specification is the single source of truth. Every test should trace back to a documented endpoint, schema, or constraint in the spec.
Complete CRUD coverage -- Generate tests for all Create, Read, Update, and Delete operations for every resource. Never leave an endpoint untested.
Negative testing first -- Error paths outnumber happy paths. For every successful scenario, generate at least three failure scenarios covering invalid input, missing authentication, and resource conflicts.
Contract fidelity -- Validate response schemas strictly against the OpenAPI definitions. A 200 response with a missing required field is a test failure.
Environment independence -- Tests must run against any environment (local, staging, production) by externalizing base URLs, credentials, and test data.
Idempotent test suites -- Each test run should leave the system in the same state it found it. Create what you need, clean up what you created.
Deterministic ordering -- Tests should not depend on execution order. Use setup and teardown hooks to establish preconditions explicitly.
Project Structure
Organize your API test suite with clear separation between configuration, test logic, and utilities: