swiftui-accessibility-auditor
Audit SwiftUI views for accessibility (iOS + macOS) with patch-ready fixes
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 10-31 00:15
Testing & quality
12,971 results
fast-track-ai-assess
Produce an evidence-backed internal assessment of a project, feature, or idea. Use when the user asks to assess, evaluate, audit, or review project…
cypress-skill
Flagship Cypress skill pack for planning, authoring, debugging, documenting, and operationalizing Cypress. Routes E2E, API, component, visual, accessibility,…
bug-fix-lifecycle
Use when Codex must report a newly discovered defect, implement an approved bug fix, or harden regression coverage and documentation around a known bug. This…
playwright-analysis-requirements
Requirements-analysis skill for Playwright planning and implementation. Use when the agent needs to extract testable behaviors, acceptance criteria, risks,…
playwright-ci
CI and delivery skill for Playwright automation. Use when Codex needs to design, debug, or optimize Playwright execution in GitHub Actions, GitLab CI,…
playwright-cli
Browser-automation skill for terminal-driven Playwright work. Use when the agent needs to navigate websites, inspect pages, interact with forms, capture…
playwright-orchestrator
Central entrypoint for broad or ambiguous Playwright requests. Use when the agent needs to classify the user's testing goal, choose the right Playwright…
test-lifecycle-skill
Use when the user wants end-to-end testing for a change — running a requirement, feature, webapp, UI, batch job, API, or release through the full 13-phase…
test-strategy-skill
Use when designing a test strategy or test plan for a requirement, feature, webapp, UI, batch job, API, or release. Produces a structured strategy doc that…
receiving-code-review
Resolve code-review reports, PR feedback, or equivalent comments. Verify current execution chains and product intent, challenge incorrect or stale claims, and…
review-harness
Review an existing LLM harness for correctness and gameplay-impacting bugs. Use when the user asks to "review", "audit", "check", "look over", or "find bugs…
qc-skill
Deterministic media quality control / validation. Measures and checks video, audio, subtitle, and delivery artifacts - a single file, or…
codex-code-avengers
Assemble six named Codex roles for an evidence-backed, read-only code review of a pull request, branch, working-tree diff, selected files, release candidate,…
qa
Establish or harden a test cage for a codebase — the automated suite and conventions that lock behavior so change is safe. Use when surveying test health,…
play-store-review-aso
Google Play submission hardening + ASO workflow for Android apps. Optimized for policy compliance, listing quality, and conversion.
frappe-doctype-tests
Expert guidance for writing DocType controller Python tests in custom Frappe apps. Covers the mandatory workflow (read controller, read schema, write test,…
vitest
Vitest fast unit testing framework powered by Vite with Jest-compatible API. Use when writing tests, mocking, configuring coverage, or working with test…
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
check-side-effects
Sweep a finished change for what it makes possible that nobody intended: security holes, breaking changes, slow paths, weakened checks.
prune-tests
Cut the low-signal tests from a suite so CI runs faster and flakes less, keeping every test that guards real behaviour.
try-every-surface
Run a finished change on every surface it touches and report what it actually does.
dev-browser
Drive a real browser (navigate, click, fill, screenshot, full Playwright API) via sandboxed JS using the open-source dev-browser CLI. For scripted…