Find the perfect skill

Testing

Runs a thorough code review applying all 30 predefined checklists covering correctness, security, architecture, infrastructure, quality, and UX. The senior-review-specialist agent analyzes every changed file, cross-references dependencies, and outputs a structured report with critical issues, warnings, and suggestions. Best used before merging pull requests to catch a wide range of issues.

Testing

Expert in creating realistic mock APIs for development, testing, and demos. Enables parallel development and API contract validation.

Testing

Runs a brepjs-cad skill eval in this session (no API key): re-author playground examples, blind-judge them, or verify precision/recall. Proposes SKILL.md fixes.

Testing

Starts the dev server and a real browser session, writes a checklist from the requirements and the diff, executes each item with evidence, then hunts for regressions and adjacent issues.

Testing

Reviews code changes and generates both a code quality report and a manual QA test plan. Use it to validate a pull request, commit, or branch in two phases: first a code review covering architecture, tests, and security, then a set of test cases for happy path, negative, edge, and error recovery scenarios.

Testing

Adversarial, read-only review of any artifact (spec, plan, PR, prose): assumes it is wrong, tries to prove it, and reports only findings that survive its own refutation.

Testing

Browser automation CLI for AI agents: navigate pages, fill forms, screenshots, scrape data, and test web apps and Electron apps via accessibility snapshots.

Testing

Run the E2E QA test suite against the live app using Playwright MCP and nREPL.

Testing

Delta audit — check only recently changed code for regressions and new bugs.

Testing

Turn settled intent into the cheapest discriminating executable proof before implementation or candidate promotion.

Testing

Automated assistance for testing keyboard navigation in frontend applications. Provides step-by-step guidance and generates configurations.

Testing

Battle-tested Playwright patterns for writing, debugging, and scaling reliable test suites. Covers E2E, API, component, visual, accessibility, and security testing.