Quality

AI-Generated Test Review checks AI-written unit, functional, API, or end-to-end tests for false confidence, weak assertions, missing risks, and unsafe behavior. Use it when reviewing tests that pass but may not prove real behavior.

API Contract Testing verifies provider-consumer API contracts across schemas, semantics, compatibility, and version changes. Use it to review plans, evidence, or results and identify breaking changes, risks, and next checks.

API Test Pytest helps parse multi-format API definitions and turn them into Pytest-based API automation. Use it when you need Python-first API tests with pytest-style structure and coverage guidance.

API Test Rest Assured generates Rest Assured Java test classes from multi-format API definitions. Use it when you need Java-based API automation with structured coverage, auth handling, and clear assertions.

Api Test Supertest generates executable Supertest scripts from multi-format API definitions and project context. Use it when you need Node.js API testing automation with Supertest or Jest.

API Testing helps design test plans, cases, and risk analysis for REST, GraphQL, SOAP, gRPC, and WebSocket APIs. Use it when you need coverage for positive, negative, boundary, auth, and response validation scenarios.

Automation Testing helps design executable test automation approaches using patterns like POM, data-driven testing, and BDD. Use it when you need a test strategy, coverage plan, or framework-aligned automation output for a real project.

Bruno API Testing helps parse multi-format API definitions and generate Bruno collections for executable regression. Use it when a project needs Bruno-ready API test organization and workflows.

Change Impact Analysis identifies affected capabilities, regression scope, and release risk from code, config, data, and dependency changes. Use it to review a change or evidence set and produce a bounded, actionable assessment.

Claude Code Review runs a standard Claude Code review of local git changes in this repository. Use it for ordinary code-review requests when you want a second pass on a working tree or branch diff.

Code Review reviews a PR, diff, or commit for logic, security, financial-loss, and maintainability risks. Use it when you need severity-ranked findings with file-level evidence and actionable fixes before merge.

Distributed Trace Analysis reviews traces, spans, and topology to find cross-service latency, error propagation, retries, and dependency failures. Use it when evidence is incomplete but a bounded first pass or review artifact is still needed.