Find the perfect skill

Testing

Sample plugin fixture for testing SKILL backwards compatibility without open-design.json sidecar.

Testing

Live UAT from the user's perspective: runs functional and visual checks using Playwright and Claude in Chrome.

Testing

Run a brepjs-cad skill eval in this Claude session and propose fixes without API key. Implements or verifies playground examples with a blind judge scorecard.

Testing

Drive the Silo dev app via its RPC bridge to execute commands, evaluate DOM, capture screenshots, and manage workspaces for runtime verification.

Testing

Deep audit of ByroRedux readiness for The Elder Scrolls IV: Oblivion content, covering NIF v20.0.0.5 and v10.x NetImmerse, BSA v103, and live ESM parsing.

Testing

Validates ADLC artifacts (requirements, architecture, tasks) before phase advancement. Ensures quality and compliance with standards.

Testing

Measure BS3D's frame rate under pinned, repeatable conditions and compare machines or settings. Use before deciding a quality tier or checking rendering changes.

Testing

Systematically QA test a web app, fix bugs with atomic commits, and re-verify. Produces before/after health scores and a ship-readiness summary.

Testing

Captures before/after screenshots of web pages or elements to document and compare UI changes, with PR markdown integration.

Testing

Read-oriented inspection for drift, inconsistency, and omissions in artifacts.

Testing

Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships. Use when output must clear two independent adversarial reviewers before it ships.

Testing

Shortcut to create unit/integration/e2e tests directly, each traced to an acceptance criterion, using a shared engine that scaffolds, grades, and halts for approval.