Deft
Ask AI

Search

Search skills, authors and topics

Testing

Reliability checks, QA flows, and regression prevention.

  • browser-testing-with-devtools

    Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.

  • break-ui

    Stress-test UI with worst-case data behind a demo toggle, then report what broke and how to fix each edge case.

  • dev

    Development workflows for the playwright-cli repository, including rolling Playwright dependencies and preparing releases.

  • state-machine

    Renders every state of a component you choose on a throwaway page, with mock data and a switcher, so you can work on each state.

  • accessibility-scan

    Run the AccessLint rule engine against a live page and return a worklist of WCAG 2.2 violations grounded to DOM selectors and source locations.

  • accessibility-diff

    Regression check that diffs a live page's accessibility violations against a baseline from uncommitted changes or a branch.

  • design-review

    Run a sharp, prioritized design critique of a UI — a URL, a screenshot/image, or a component file — covering visual hierarchy, typography, spacing, color & contrast, motion, component states, responsiveness, accessibility, and brand consistency. Returns findings ranked from blocking to polish, each with a specific fix; can optionally apply the fixes to code. Use when the user asks to review/critique a design, page, screen, component, or screenshot, or to check craft/accessibility before shipping.

  • interface-review

    Interface review of a change rather than a screen: uncommitted work, the current branch, or a pull request. Covers interface quality, not correctness, tests, or security.

  • linear-monitor

    Health-check Linear projects for slipping dates, stale in-progress work, orphan issues, and tracking anti-patterns.

  • effect

    Opinionated guidance for building production TypeScript applications with Effect v4, including workflows, services, layers, schemas, configuration, scheduling, caching, streams, HTTP clients, and tests.

  • improve

    Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or take the project next, or generate handoff plans for another agent to implement.

  • tdd

    Red-green-refactor workflow for building features and fixes one slice at a time.

  • engineering

    Routing bundle for code work covering planning, debugging, TDD, architecture, and execution flows.

  • build-primitive

    Build foundational UI primitives from scratch with strong ARIA, keyboard, focus, and state handling.

  • optimize

    Diagnose and improve interface performance across rendering, motion smoothness, assets, and load speed.

  • harden

    Make interfaces production-ready with robust empty states, edge cases, errors, onboarding, and i18n resilience.

  • critique

    Evaluate design quality with structured UX scoring, persona checks, and actionable remediation guidance.

  • audit

    Run technical UI quality audits across accessibility, performance, theming, responsive behavior, and anti-patterns.

  • improve-animations

    Survey a codebase's animation and motion code as a senior motion advisor, then produce prioritized audit and self-contained implementation plans. Read-only on source code - it plans improvements, it does not apply them. Use when the user asks to improve animations, audit motion, make an app feel better, or wants a roadmap of animation fixes rather than a review of a single diff.

  • refactor

    Compatibility listing for refactor installs from AccessLint's marketplace skill set.

  • accessibility-inspect

    Manual accessibility pass on a live page: keyboard operation and focus order, screen-reader names and roles, reflow and zoom, reduced motion, form errors, and target size. Use for the checks a rule engine can't decide; it grades findings by evidence and severity but does not fix them.

  • audit-and-fix

    Accessibility auditing and remediation workflow that combines detection, prioritization, and practical fixes for WCAG issues.

  • react-doctor

    Run React Doctor to detect regressions in security, performance, correctness, and architecture, with score-based quality checks.

  • vitest

    Vitest testing best practices for unit tests, mocking, coverage, fixtures, and test filtering.

  • wcag-audit-patterns

    Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance. Use when auditing websites for accessibility, fixing WCAG violations, or implementing accessible design patterns.

  • web-quality-audit

    Web quality auditing skill for Lighthouse-style analysis across performance, accessibility, best practices, and SEO signals.

  • playwright-cli

    Official Playwright CLI skill for browser automation, test generation, tracing, and session-driven end-to-end testing workflows.

  • agent-browser

    Browser automation CLI for AI agents for navigation, form actions, extraction, screenshots, QA, and app testing.

  • vue-debug-guides

    Practical debugging workflows for diagnosing and fixing Vue reactivity, rendering, and state issues.

  • fixing-accessibility

    Audit and fix HTML accessibility issues including ARIA labels, keyboard navigation, focus management, color contrast, and form errors. Use when adding interactive controls, forms, dialogs, or reviewing WCAG compliance.