Testing plugins

AI-assisted interfaces-first pre-review, code and logic audit, process simulation, visual E2E review, mission guardrails, and optional dialogue checks.

20 skills · hooks

A suspicious, curious QA engineer that continuously probes your project for bugs, silent failures, and visual inconsistencies using 6 specialist agents.

4 commands · 7 agents · hooks

Code quality: TDD discipline, E2E testing patterns, AI regression testing, click-path audit, santa-method adversarial verification, security review checklist, .claude config scan, Plankton write-time enforcement

8 skills

Multi-language code review: /code-review dispatches to language-specific reviewer (Python, TypeScript, Swift) plus mandatory security-reviewer. General code-reviewer fallback.

1 command · 5 agents

Invoke Codex (read-only codex exec via ~/.local/bin/codex-run) for code review and design challenge.

2 skills · 2 commands

Observe and interact with live web pages via WebEngine MCP (Selenium): snapshot, click/type/select, then generate UI code in any stack.

2 skills · 1 MCP server

Observe and interact with live Android/iOS apps via WebEngine MCP (Appium): snapshot, tap/type/swipe, then generate mobile UI code.

2 skills · 1 MCP server

Browser testing and automation plugin with Playwright MCP integration for end-to-end testing.

1 MCP server

Scaffolds comprehensive testing setup for Next.js applications including Vitest unit tests, React Testing Library component tests, and Playwright E2E flows with accessibility testing via axe-core. This skill should be used when setting up test infrastructure, generating test files, creating test utilities, adding accessibility checks, or configuring testing frameworks for Next.js projects. Trigger terms include setup testing, scaffold tests, vitest, RTL, playwright, e2e tests, component tests, u

1 skill

Creates Playwright test scripts from natural language user flow descriptions. This skill should be used when generating E2E tests from scenarios, converting user stories to test code, recording user flows, creating test scripts from descriptions like "user signs up and creates project", or translating acceptance criteria into executable tests. Trigger terms include playwright test, e2e flow, user scenario, test from description, record flow, user journey, test script generation, acceptance test,

1 skill

Adds comprehensive accessibility testing to CI/CD pipelines using axe-core Playwright integration or pa11y-ci. Automatically generates markdown reports for pull requests showing WCAG violations with severity levels, affected elements, and remediation guidance. This skill should be used when implementing accessibility CI checks, adding a11y tests to pipelines, generating accessibility reports, enforcing WCAG compliance, automating accessibility scans, or setting up PR accessibility gates. Trigger

1 skill

JSON-driven E2E browser test runner — no JavaScript test files needed. Parallel execution against a Chrome pool (browserless, CDP, Lightpanda, Obscura, Steel), 28+ built-in actions, visual verification, network debugging, flaky test detection, reusable modules, and a real-time dashboard. Includes 3 specialized agents (test-creator, test-analyzer, test-improver), 4 slash commands, and 17 MCP tools.

Skills and an MCP server for writing, running and debugging axx acceptance tests (Gherkin).

5 skills · 1 MCP server

Unit and integration test automation for Python and JavaScript with debugging support

1 command · 2 agents

Reviews existing tests for efficacy, correctness, and coverage gaps, prioritizing real interactions over mocking

1 skill

Analyze a GitHub pull request for risk level and generate concrete QA recommendations using a multi-dimensional scoring framework

1 skill

QA workflows on any provider: Playwright-BDD UI E2E, API & API integration tests, bug filing, fix verification, MR/PR test impact, flaky triage, test healing, exploratory testing, release readiness, load tests.

31 skills · 2 MCP servers · hooks

A QA test-session engine: a manager plus the qa-analyst/qa-manual/qa-automator subagents, a session file scheme, reports and a mandatory retro. One flow for many projects — everything project-specific (tracker, test management, environments, autotests) lives in the project's own profile.

3 skills · 3 agents · hooks

Audit testing in vllm to enforce contracts of correctness.

2 skills · 3 agents · hooks

Quality assurance agents for test planning, automated validation, quality gate enforcement, and coverage analysis

1 skill · 1 command · 2 agents · hooks

Test-driven development commands and skills enforcing red-green-refactor methodology with comprehensive test generation and quality validation

2 skills · 2 commands

Testing toolkit: browser-based end-to-end verification with Playwright and a /write-tests command that generates a suite matching project conventions.

2 skills · 1 command

Demo plugin for validating Claude Code plugin infrastructure in CI. Tests hook execution, script invocation, and skill loading.

1 skill · hooks

Refactor PyTorch test files to be device-agnostic with hardware classification (GENERIC/DEVICE_GENERIC/DEVICE_SPECIFIC/MULTI_DEVICE). Guides analysis, classification, class splitting, and verification.

1 skill · 1 agent

Agent-native mobile UI automation and verification for Expo, React Native, Flutter, and native Android/iOS apps.

1 skill · 1 MCP server

Check whether one change to Claude Code's instructions (CLAUDE.md, .claude/rules, referenced docs, skills) actually changes behavior. Runs the same prompts before and after the uncommitted change and builds a report for a person to compare the runs side by side.

1 skill

Adversarial test generation that finds real bugs by inverting the reward structure

2 skills · 3 agents

Apptension E2E testing — generates Playwright end-to-end test specs from a ticket's description, its diff, and its unit tests — plus a testing-guide section when the ticket carries one — then verifies they run.

5 skills

Testing, QA, and quality gates with 3 specialized agents for automated validation and code quality checks

1 command · 3 agents

Unit and integration test automation for Python and JavaScript with debugging support

1 command · 2 agents