Find the perfect skill

Testing

Analyze code coverage gaps and generate targeted tests for uncovered branches, functions, and edge cases.

Testing

Generates test suites derived from Eiffel contracts and runs them. Helps verify postconditions and edge cases by automatically translating contracts into executable tests. Includes AI-driven coverage gap analysis to identify untested contracts.

Testing

Create load testing and performance benchmarking suites with k6, Artillery, or custom scripts.

Testing

Automate accessibility testing with axe-core, pa11y, and custom WCAG compliance checks.

Testing

Generates end-to-end tests with Playwright for web applications. Analyzes page structure and user interactions to create automated browser tests covering user flows, UI, and integration. Includes test templates, best practices for selectors and assertions, and configuration for running tests.

Testing

Prioritizes visual stability over perfection. Flags only issues that could cause embarrassment during a live demo. Use when preparing for demos, final pre-deploy review, or verifying demo-critical paths.

Testing

Conducts a comprehensive usability and accessibility review of interfaces using Nielsen's 10 heuristics, WCAG 2.1 AA/AAA guidelines, keyboard and screen reader testing, user flow analysis, and cognitive load assessment. Ideal for identifying usability issues before release, evaluating form design, and ensuring accessibility compliance. Provides severity-rated findings and actionable recommendations.

Testing

Inspect captured HTTP traffic from the MITM proxy. Use to list, filter, and view request/response details of intercepted requests. Helps analyze network activity, debug API calls, or export traffic as HAR for external tools.

Testing

Implement chaos engineering practices to test system resilience under failure conditions.

Testing

Run pytest tests (fast/slow/full) in mflux while preserving image outputs and safely handling golden image diffs without unintended updates.

Testing

Takes screenshots of all pages across desktop and mobile viewports and light/dark modes, then analyzes design quality to identify issues and propose creative improvements. Use this when reviewing a design, checking dark mode consistency, or auditing UI quality before shipping.

Testing

Performs an independent audit of code changes against a provided change log, with no prior session context. It verifies data flow, API consistency, cross-file integrity, performance, and test strategy, outputting structured discrepancy and defense analysis. Essential for catching hidden side effects, undocumented deviations, and ensuring change log accuracy in critical code reviews.