Testing plugins

Validate documentation by simulating a developer with zero project knowledge

1 skill · 1 agent

Skill and MCP server for driving fermut mutation testing: score a Python test suite, triage surviving mutants, and write targeted tests that kill them. The MCP server needs fermut on PATH.

1 skill · 1 MCP server

Skills for adopting rstest (migrate a pytest suite, make it parallel-safe, speed it up) and for triaging failures on a suite that already runs on rstest (replay, bisect, audit, flaky-test policy).

2 skills

Run tests locally with vci, attest what they depended on, and let CI skip them.

2 skills

Robust Playwright/TypeScript E2E test generation: qualify the intent (reads docs/ PRDs and glossary), ground selectors on the live site, plan, write reusing existing code, prove non-flakiness by repeated cross-browser runs, and review with independent critics.

1 skill

Claude Code Skill for general-purpose browser automation with Playwright (Python). Claude autonomously writes and executes custom automation for testing pages, validating UX, and any browser task.

1 skill

Comprehensive RSpec testing toolkit - matchers, mocks, Rails integration, Factory Bot, and test organization patterns for Ruby applications

7 skills · 3 commands · 2 agents

Installs and verifies a complete E2E toolchain (Playwright for web, Maestro for mobile), then drives spec-driven test authoring, live verification, and versioned HTML reporting.

9 skills · 1 agent · hooks

Whole-app QA by a team of Claude Code agents: maps every feature, tests each one in parallel, lists the bugs for your approval, fixes them in isolated git worktrees and has a fresh agent verify every fix, cycle after cycle. Also ships /regression and /manual-qa for checking a single change.

3 skills · 5 agents

Thin Claude host for Sentinel's single-service trusted core: OpenAPI 3.0/3.1 JSON, static literal Vue Router, bearer-token roles, and system Chrome/Chromium; coverage is complete, partial, or unsupported

1 skill · 1 command · 3 agents

Comprehensive test generation and analysis plugin that automates test creation, identifies coverage gaps, and improves test quality across your entire codebase

5 commands

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

Turns code-review findings into tests: one test-writer agent per finding writes the smallest test that proves it, runs it, and reports whether it reproduced the defect. A hook confines the writer to test files

1 skill · 1 agent · hooks

Pre-commit gate: runs test, lint and type check and prints a PASS/FAIL table. A check that could not run counts as FAIL, not as a pass.

1 skill · hooks

Verifies test-count claims against real pytest output before a commit lands. If the message makes no claim, it does nothing.

1 skill · hooks

Test web application features in Chrome browser using DevTools MCP. Use proactively after implementing features or bug fixes.

1 agent · hooks

Test a first-party or third-party AdCP sales agent with governed buyer workflows.

1 skill · 1 MCP server

Claude Code Stop hook that blocks fixed/done claims with no evidence in the session and asks for proof.

1 skill · hooks

Plugin para testes E2E com Playwright CLI — setup, execução, test-agents (planner/generator/healer) e autenticação via storageState.

1 skill

Diagnoses failing tests, separates product regressions from flaky or stale tests, and proposes minimal fixes with verification steps.

1 skill

Designs a focused test plan for a feature, bug fix, refactor, or release by choosing the right unit, integration, end-to-end, and regression tests.

1 skill

YAGNI, stdlib first, framework-adaptive QA. One test, one verdict, move on.

35 skills · 8 agents

Know which green tests you can trust. QA judgment skills for Claude Code — test planning, testability and coverage review, mutation-backed test audits, flake triage, and an evidence-based ship gate.

15 skills

Comprehensive codebase cleanup across 11 quality dimensions — dead code, duplication, weak types, circular deps, defensive cruft, legacy code, AI slop, type consolidation, security, performance, and async patterns. Confidence scoring and build verification gates.

1 skill · 11 agents

Find your product's blind spots — dogfood against specs, run user trials, A/B experiment across variants, and interview synthetic personas

1 skill · 5 commands · 5 agents

QA-цикл на русском: тест-план и прогон по задаче из Jira, экспериментальный автономный QA-конвейер из субагентов, критерии приёмки, баг-репорт, отчёт о тестировании, тест-кейсы Allure TestOps, WireMock-стабы, логи OpenSearch/Jaeger, деплой на стенд через Bamboo.

10 skills

Comprehensive Playwright E2E testing plugin with test generation, Page Object Models, debugging, and maintenance. Features data-testid locators, TypeScript-first approach, and Playwright MCP integration for browser automation.

4 skills · 4 commands

Blind TDD gate: a fresh agent writes failing tests from the spec alone (path-guard hook blocks implementation reads), the implementer makes them pass, a blind runner verifies green, and an arbiter rules on challenges.

2 commands · 3 agents · hooks

Analyze code and suggest specific, purpose-driven tests tied to actual behavior and intent — not arbitrary coverage

6 skills