Testing plugins

Plan, write, run, and debug QaaS Runner/Mocker tests and custom hooks using only the QaaS docs. 20 skills including SUT repo/Helm/K8s analysis and 4 subagents. Airgap-ready and docs-backed.

20 skills · 5 commands · 4 agents · hooks

通过自然语言契约逆向工程从官方文档提取结构化约束，结合多 Agent 辩论机制在 Docker 沙箱中自动发现向量数据库的合规性缺陷。

4 skills · 4 commands · 17 agents · 1 MCP server · hooks

A suite of agent skills for the full GrowthBook feature flag and experimentation lifecycle.

25 skills

QA posture monitoring and feedback-loop orchestration for coding agents. Claude Code: /testchimp project-init once per repo, then /testchimp init per developer.

1 skill · 17 commands · 1 MCP server

Test your product with synthetic personas. Run one persona through a flow in a real browser, or run a behavioral study: the plugin picks the behavioral factors that matter for your users (patience, trust, familiarity and more), generates an archetype per factor plus a baseline and a stress case, runs them in parallel isolated headless browsers with a video per run, and reports completion per archetype, which factor made people give up, with what confidence, and what to change.

9 skills · 2 agents · 7 MCP servers · hooks

SDODS for Claude Code and GitHub Copilot CLI: BDD test automation for UI, API and hybrid flows. Run, plan, generate, heal and review tests with the SDODS MCP server, skills and subagents.

10 skills · 5 agents · 1 MCP server · hooks

QA Automation AI skills and agents for Claude Code — Playwright, Selenium, API, accessibility, QA Planner, and ISTQB-aligned workflows.

10 skills · 7 agents

Core: engine, /agentic-tests:run and /agentic-tests:setup, planner, auditor, verifier and repair agents.

7 skills · 8 agents

Author, run and debug ContextQA test cases from your agent. Bundles thirteen skills and wires up the hosted ContextQA MCP server.

13 skills · 1 MCP server

DVERA connects coding agents to CT for C/C++ unit and integration verification in functional-safety projects through MCP and Skills.

14 skills

End-to-end QA testing as a Claude Code plugin. Drop it into any web-app repo and Claude detects the framework, walks every page in a real browser, drives every form / modal / button / role gate, runs the whole platform in parallel, verifies each verdict against its screenshot evidence, and files defects with screenshots.

7 skills · 6 agents · hooks

Auditoria completa de sistemas web: personas sintéticas, testes de API, carga com k6 e plano de correção.

5 skills · 7 agents · hooks

Clarify and solve problems (grill-me, brainstorm, problem-solving, predict), generate test cases and edge cases, turn manual cases into Playwright tests with web-testing from-manual, write Vitest/k6 automation, run and audit suites, explore apps, and debug failures. Includes tester, debugger, code-reviewer, and brainstormer agents.

8 skills · 4 agents

BDD scenario authoring and E2E testing via checkmate + playwright-http. Project-agnostic.

7 skills · 3 commands · 1 agent · hooks

QA Engineer Automation plugin for Playwright E2E testing with auto-scenario generation and validation

3 skills · 4 commands · 3 agents

Turn a GitHub issue into reviewed, stable Playwright E2E tests: checks the issue is testable and asks when it isn't, plans, generates and heals tests with Playwright's official test agents engine, and posts the evidence on the issue.

5 skills · 4 agents · 1 MCP server

Record UI tests with your AI agent and replay local Markdown traces without an account, API key, or hosted workspace.

3 skills · 3 commands · 3 agents

TesterPayKit plugin — bootstrap a TPK project incl. payout rule, integrate the SDK into Flutter (testerpaykit + moinsen_runapp), Expo/React-Native (@testerpaykit/expo), Web/TypeScript (@testerpaykit/react), or native Swift (TesterPayKit Swift Package, early access) apps, query sessions/bugs/recruiting, install the tpk CLI from pub.dev, order tests with real human testers and read their results over the remote testerpaykit MCP server (/tpk:connect), see and drive your own running app and keep a tester checklist (/tpk:live), and close the agentic feedback loop via /tpk:fix-next-bug. Start with /tpk:guide, an interactive course with saved progress. Skills are namespaced /tpk:* so they're easy to find. Real testers report, Claude fixes, you ship.

8 skills · 1 MCP server

Use TestDino inside Claude Code through the hosted remote MCP server to inspect test runs, debug failing test cases, manage manual tests, and run TestDino audits.

7 skills · 1 MCP server

Visual regression testing powered by AI. Captures screenshots with Playwright, pre-filters with pixelmatch, and uses Claude (locally) or Gemini (in CI) to classify visual changes as regressions, intentional changes, or noise. Includes slash commands for interactive workflows and a CI orchestrator for GitHub Actions.

1 skill · 6 commands · 1 agent

Automated exploratory bug hunting on web applications — explore, detect, and report bugs via browser automation

2 skills · 3 commands · 2 agents

Loadster load testing and synthetic monitoring integration. Write and play load test scripts with Playwright or real browsers at scale, build scenarios, set up monitors, and analyze results, and launch tests when you approve. Skills include setup, setup-script, setup-scenario, setup-monitor, load-test, and results. Connects over OAuth: run /mcp after installing.

6 skills · 1 MCP server

Diff-aware, pluggable QA for Angular apps: maps a PR to feature manifests, finds Playwright coverage gaps, writes the missing specs against the live app, runs them and separates regressions from test drift.

3 skills · 4 agents

专业的单元测试生成工具，支持多种编程语言和测试框架，能够智能分析代码并生成高质量的测试用例

3 skills · 3 commands · 1 agent

Portable CATS API fuzzing toolkit: bootstrap per-repo config (init), run fuzz campaigns through config-declared shell hooks (run), query and render results from SQLite (report), triage true positives into a remediation plan (analyze), and manage declarative false-positive rules (fp). Repo-specific setup lives in .local/cats/config.yaml; false-positive rules live in a committed YAML file.

5 skills · 1 agent

Quality OS MCP for coding agents — VRT, FRT, tracking proof, PR gates

4 skills · 1 agent · 1 MCP server

Python test engineering skills — pytest project structure, Playwright API and browser tests, SQLAlchemy test fixtures — and the untangling workflow for large unmerged test suites.

5 skills · 1 agent

Autonomous web app testing with agent-browser — auto-discovery, structured flows, and bug reporting

2 skills · 4 commands

Run red-green-refactor workflows with TDD agents, review steps, and guided test-first commands.

4 commands · 2 agents

Autonomous QA coverage crawler: maps the whole app and inspects every node (the inverted maze). Deterministic MCP engine (frontier, dedup, replay, SQLite coverage ledger, a11y/visual/functional checks) + qa-crawl skill + /qa-crawl command + orchestrator/worker subagents. Drives a visible Neko browser (local or remote) with per-session tab isolation. NOTE: run `sh setup.sh` in the plugin directory once after install (native SQLite + Chromium).

1 skill · 1 command · 2 agents · 2 MCP servers