Testing & QA Plugins
58 testing & qa Claude plugins for Claude Code and AI agents, ranked by real installs from npm, PyPI and skills.sh.
#Type
- 1promptfooTest your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration. Used by OpenAI and Anthropic.Jul 2026
- 2claude-octopusv9.54.2 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider…Jul 2026
- 3playwright-skillClaude Code Skill for general-purpose browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp, and autonomously handles any browser automation task.Dec 2025
- 4swift-testing-agent-skillExpert Swift Testing guidance for test structure, #expect/#require usage, traits and tags, parameterized tests, async waiting patterns, parallel execution, and XCTest migration.Apr 2026
- 5agentic-qeAgentic Quality Engineering — AI-powered QE platform with 60 specialized agents, 75+ skills, sublinear coverage analysis, ReasoningBank pattern learning, and deep MCP integration for Claude Code and 11 coding agent platformsJul 2026
- 6evanflowA TDD-driven iterative feedback loop for software development with Claude Code. 16 cohesive skills + 2 custom subagents walk an idea from brainstorm → plan → execute → tdd → iterate, with checkpoints throughout.May 2026
- 7swift-testing-agent-skillSwift Testing agent skill for Claude Code, Codex, and other AI tools.May 2026
- 8researcherskillAutonomous experimentation skill — your AI coding agent designs experiments, tests hypotheses, discards failures, keeps wins. Runs overnight while you sleep.Jun 2026
- 9squirrelscanWebsite QA tool built for coding agents (Claude Code, Cursor). 260+ rules across SEO, performance, security, accessibility & agent experience: audit from the CLI, fix findings in code, publish reports, and connect over MCP.Jul 2026
- 10empiricaMake AI agents and AI workflows measurably reliable. Epistemic measurement, Noetic RAG, Sentinel gating, and grounded calibration for Claude Code and beyondJul 2026
- 11testdriveraiComputer-Use SDK for E2E QA TestingMay 2026
- 12distributed-system-testingTwo coupled skills that design and execute claim-driven, Jepsen-style test plans for distributed and stateful systems.Jul 2026
- 13test-automation-skills-agentsTool-agnostic QA Automation library: Playwright, Selenium, API testing, accessibility (WCAG 2.1 AA), and ISTQB-aligned QA artifacts. Includes 7 specialized agents and 9 reusable skills.Jul 2026
- 14qaskillsQA Skills Directory QA Skills is a curated directory of testing-specific skills for AI coding agents (Claude Code, Cursor, Copilot, etc.).Jul 2026
- 15probityTDD enforcement and guardrails for Claude Code, Codex, and GitHub Copilot CLI.Jul 2026
- 16disciplined-agentic-engineeringAcceptance Test Driven Development for Claude Code. Enforces the ATDD methodology: write Given/When/Then specs first, generate a project-specific test pipeline, maintain two test streams (acceptance + unit). Inspired by Robert C.Jun 2026
- 17rayfernando-skillsRay Fernando's collection of Skill files for AI coding agents. First up: running-bug-review-board, a real-user QA workflow with a Bug Review Board (BRB) feedback loop.Jul 2026
- 18firecrawl-workflowsOutcome-focused Firecrawl workflow skills for research, SEO audits, QA, knowledge bases, lead lists, dashboard reporting, shopping, and design-system extraction.Jun 2026
- 19skillkitProfessional skill creation with TDD workflow. Features dual-mode (fast/full), behavioral validation, and automated quality gates for 9.0/10+ scores.Mar 2026
- 20skillsWebsite audit tool built for AI agents. 249+ SEO, performance, security & agent readiness rules: run audits from the CLI, fix findings in code, publish reports, and connect over MCP.Jul 2026
- 21testany-agent-skillsTestany 公司的 Agent Skills 集合，提供产品研发流程中的各类专业技能May 2026
- 22quality-playbookThe Quality Playbook is an open-source skill that turns AI coding agents into rigorous quality engineers. Point it at your code, in any language. Feed it whatever docs you have: READMEs, GitHub issues, Discord threads, AI chat history.Jul 2026
- 23hegel-skillTeaches agents how to write property-based tests using HegelJul 2026
- 24muki-ai-pluginsA Claude Code plugin marketplace for quality assurance — visual regression testing and test review.Jul 2026
- 25makotoHolds Claude Code to its word — every claim checked against the agent's own logged record; faked checks blocked, not warned (four narrow advisory self-checks excepted). Two-tier catalog (15 pre-checks, 19 Stop gates), each shipped at measured zero false positives.Jul 2026
- 26fable-ishVerification-gated workflow plugin for Claude Code tasks. Adds lightweight hooks for task classification, verification tracking, and stop-time completion review.Jun 2026
- 27mk-qa-masterAI 測試大師 — v1.1 QA testing skill backed by an MCP server. 22 tools (21 v1.0-frozen + analyze_stream): run / generate / debug / harden software tests via mk-qa-master.Jun 2026
- 28fat-agent-skillFAT Agent (Fix, Audit, Test) — a Claude Skill that automates post-launch website QA. Audits SEO, security, accessibility, performance, and more.Jul 2026
- 29ai-toolkitCreate, update, and fix Cypress tests. Connect to Cypress Cloud to see test results and use data to manage your test suite.Jul 2026
- 30skillcheck-freeValidates Claude Code SKILL.md files against ~25 contract rules including structure, triggers, anti-patterns, and naming. Works with Claude Code, Claude Desktop/Web, and Cursor.Jul 2026
- 31zacs-claude-skillsZac's collection of Claude Code skills for development workflows, testing, and quality assuranceJan 2026
- 32qa-useAgent-first E2E testing CLIMay 2026
- 33qa-skillsQA testing pipeline with 6 personas (smoke, UX, adversarial, security, performance, mobile) — generate workflow docs, convert to Playwright E2E tests, run interactively or in CI.May 2026
- 34storybook-workbenchWork WITH Storybook on React+Vite apps: audit a vibe-coded codebase for real-vs-slop components, capture flows/app-maps, write CSF3 stories, and ship — as focused skills, not one monolith.Jul 2026
- 35claude-chrome-user-testingPersona-based user testing agent that simulates realistic user interactions with web applications. Embodies different user archetypes (Boomers, Millennials, Gen Z, Gen Alpha) with authentic behaviors, timing patterns, and frustration triggers to identify UX issues before real…Jan 2026
- 36autoworkerAuto-loop execution workflow with quality gates for Claude Code. Automatically decomposes tasks, implements code, runs tests, and iterates through quality gates until completion.Mar 2026
- 37toru-claude-agentsA dev pipeline for Claude Code that will not call work done until tests, lint and a security audit all exit zero. Seven specialists run it, for ~1.1k tokens of always-on context.Jul 2026
- 38cws-featured-badge-skillAudit any Chrome extension against Chrome Web Store Featured-badge and Established Publisher badge criteria, and produce a prioritized fix plan to qualify.Jul 2026
- 39skillsE2E testing and test result classification skills for MomenticJul 2026
- 40mcpbrExpert benchmark runner for MCP servers using mcpbr. Handles Docker checks, config generation, and result parsing.Apr 2026
- 41claude-code-tdd-marketplace這個 marketplace 提供兩種互補的測試驅動開發（TDD）方法，讓您根據不同的開發情境選擇最適合的方法。Nov 2025
- 42claude-marketplaceClaude Code plugin marketplace featuring accessibility (WCAG 2.1), Playwright testing, and developer toolsFeb 2026
- 43fagunGive any AI a browser to use a site as real end users, run full UAT, validate user journeys, hunt real bugs, and deliver a product-readiness verdict. QA + a11y + perf + security + readiness scorecard in one MCP server. Token-lean by default.Jul 2026
- 44heimdallNothing ships unproven. Heimdall is an autonomous multi-agent orchestrator for Claude Code that turns one prompt into a finished project — and keeps moving the bar on what counts as done: every plan wires an external, falsifiable oracle so the implementation can never grade its…Jul 2026
- 45claude-plugins-validationComprehensive validation, management, and standardization suite for Claude Code plugins and marketplaces. Includes 190+ validation rules, plugin lifecycle management, marketplace operations, health checks, security auditing, GitHub repo validation, plugin/marketplace repo…Jul 2026
- 46test-builderClaude Code plugin for educators: evidence-based test construction — blueprints, Bloom matrices, item writing by format rules, review checklists, and classroom psychometrics (P-value, D-index, Rit, distractor analysis).Jul 2026
- 47msbaek-claude-pluginsClaude Code TDD Plugin MarketplaceJul 2026
- 48pev-harnessClaude Opus 4.8 native Plan-Execute-Verify coding harness. Minimal 3-phase pipeline for team-shared coding workflows.Jul 2026
- 49regressionledgerStop your coding agent from re-applying fixes that already failed. Blocks repeat failed fixes across sessions, with the reason attached.Jul 2026
- 50kelp-claude-pluginsClaude Code plugins: language-agnostic TDD pipeline and Zig 0.15.x corrective contextJul 2026
- 51agent-testkitUniversal E2E and manual acceptance testing for any repo: test-init generates project test plans (TESTS_E2E.md, TESTS_MANUAL.md), test-e2e executes them autonomously, test-manual conducts them with you at the controls. Every run writes a timestamped protocol file.Jul 2026
- 52evil-twinYour shadow self — adversarial challenge + independent blind verification. Claude-only.Apr 2026
- 53conformAutomated validation for Claude Code plugins and shared `.claude` configurations.Apr 2026
- 54ringmasterTurns Claude Code into a disciplined engineering team: it frames the goal, plans behind an approval gate, routes each step to the best specialist plugin (with built-in fallbacks), and runs a bundled Test Architect, an adversarial Security Gate, a two-axis code review, and an…Jul 2026
- 55delivery-loopContinuous fullstack delivery loops — orchestrates frontend, backend, and quality subagents (behaviour drivers, engineers, UI/UX specialist, code/security reviewers, architects) in a test → diagnose → fix → review → secure → re-test cycle until the work is production-readyJul 2026
- 56claude-pluginsClaude Code plugin marketplace by Observo (https://observoai.co). Hosts QA / product-spec tooling for the Observo test management platform.May 2026
- 57spec-compliance-skillsW3C/IETF仕様準拠チェック用スキル集。EPUB 3.3品質レビュー、PDF/A検証、RFC準拠チェックなど、仕様の規範的要件（MUST/SHOULD/MAY）に基づいた構造化検証とレポート生成を行います。Jul 2026
- 58claude-plugins-marketplaceClaude Code plugins marketplace — UX design, QA bug hunting, and development workflowsMar 2026
