Agent Plugins Marketplace
← All plugins

qa-kit

v0.1.0

QA toolkit: clarify and solve problems (grill-me, brainstorm, problem-solving, predict), generate test cases and edge cases, write Playwright/Vitest/k6 automation, run and audit test suites, explore apps in a browser, and debug failures to root cause.

CodexClaude Code9 Skills

By huutri0 GitHub starsUpdated yesterday

Directory evidence

Runtimes
Codex and Claude Code
Parsed components
9 skill or MCP entries
Source updated
Sep 23, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install qa-kit for Codex and Claude Code

Installs for the current user
codex plugin marketplace add hongbietcode/qa-kit
codex plugin marketplace upgrade qa-kit
codex plugin add qa-kit@qa-kit

Paste and run these commands in a terminal with Codex. They add and refresh the qa-kit catalog, then install this plugin.

Compatibility: the page URL and API slug “qa-kit” remain stable.

  • Codex: qa-kit@agent-plugin-marketplace → qa-kit@qa-kit

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/hongbietcode/qa-kit

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/qa-kit/.

Plugin files

plugins/qa-kit/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── skills/agent-browser/SKILL.md
├── skills/brainstorm/SKILL.md
├── skills/debug/SKILL.md
├── skills/grill-me/SKILL.md
├── skills/predict/SKILL.md
├── skills/problem-solving/SKILL.md
├── skills/scenario/SKILL.md
├── skills/test/SKILL.md
└── skills/web-testing/SKILL.md

Included Skills9

agent-browserskills/agent-browser/SKILL.md

Browser and desktop automation through the agent-browser CLI. Use for exploratory QA, bug hunts, login/test flows without real Chrome profile state, compact page snapshots, screenshots, form filling, scraping, long autonomous browsing, cloud browsers, Electron apps, and Slack automation.

brainstormskills/brainstorm/SKILL.md

Turn unclear intent into an accepted outcome and compare viable approaches before delivery. Use to clear up a fuzzy problem, frame a bug fix or test strategy, or weigh design trade-offs before any code changes.

debugskills/debug/SKILL.md

Debug systematically with root cause analysis before fixes. Use for test failures, flaky tests, bugs, unexpected behavior, performance issues, call stack tracing, multi-layer validation, log analysis, CI/CD failures, database diagnostics, and system investigation.

grill-meskills/grill-me/SKILL.md

Grill the user relentlessly about a plan, decision, design, or test strategy until you reach a shared understanding. Use when the user wants to stress-test their thinking, clear up a fuzzy problem, or uses any "grill me" trigger phrase.

predictskills/predict/SKILL.md

5 expert personas debate a proposed change before implementation. Catches architectural, security, performance, and UX issues early. Use before major features, risky changes, or when choosing between competing approaches.

problem-solvingskills/problem-solving/SKILL.md

Apply systematic problem-solving techniques when stuck. Use for complexity spirals, innovation blocks, recurring patterns, assumption constraints, simplification cascades, and scale uncertainty.

scenarioskills/scenario/SKILL.md

Generate test cases, edge cases, and QA scenarios by decomposing a feature or code path across 12 dimensions. Use for pre-implementation risk discovery, QA planning, regression design, and iterative saturation when coverage must be exhaustive.

testskills/test/SKILL.md

Run unit, integration, e2e, and UI tests, and create, optimize, or audit test suites. Use for test execution, coverage analysis, build verification, visual regression, and QA reports.

web-testingskills/web-testing/SKILL.md

Write and maintain web test automation with Playwright, Vitest, and k6 — E2E, unit, integration, API, load, security, visual, and accessibility tests. Use for test automation, flaky tests, Core Web Vitals, mobile gestures, and cross-browser coverage.

Plugin manifests2

plugins/qa-kit/.codex-plugin/plugin.json
{
  "name": "qa-kit",
  "version": "0.1.0",
  "description": "QA toolkit: clarify and solve problems (grill-me, brainstorm, problem-solving, predict), generate test cases and edge cases, write Playwright/Vitest/k6 automation, run and audit test suites, explore apps in a browser, and debug failures to root cause.",
  "author": {
    "name": "huutri",
    "email": "[email protected]"
  },
  "keywords": [
    "qa",
    "testing",
    "test-cases",
    "edge-cases",
    "playwright",
    "vitest",
    "k6",
    "e2e",
    "debugging",
    "brainstorm",
    "grill-me",
    "problem-solving",
    "risk-analysis"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "QA Kit",
    "shortDescription": "Clarify problems, generate test cases, write test automation",
    "longDescription": "Nine skills in one plugin. Clarify and solve: grill-me stress-tests a plan a round of questions at a time, brainstorm turns fuzzy intent into an outcome contract and compares approaches, problem-solving reframes a stuck problem, and predict has five expert personas debate a risky change. Test: scenario generates test cases and edge cases across 12 dimensions, test runs, creates, optimizes, and audits suites, web-testing writes Playwright, Vitest, and k6 automation, agent-browser drives exploratory QA in a browser, and debug proves the root cause of a failure before any fix.",
    "developerName": "huutri",
    "category": "Engineering",
    "capabilities": [
      "Interactive",
      "Read",
      "Write"
    ],
    "defaultPrompt": [
      "Use $qa-kit:grill-me to stress-test my plan for the checkout redesign",
      "Use $qa-kit:scenario to generate test cases and edge cases for src/api/payment.ts",
      "Use $qa-kit:web-testing to write Playwright E2E tests for the checkout flow"
    ]
  }
}
plugins/qa-kit/.claude-plugin/plugin.json
{
  "name": "qa-kit",
  "version": "0.1.0",
  "description": "QA toolkit: clarify and solve problems (grill-me, brainstorm, problem-solving, predict), generate test cases and edge cases, write Playwright/Vitest/k6 automation, run and audit test suites, explore apps in a browser, and debug failures to root cause.",
  "author": {
    "name": "huutri",
    "email": "[email protected]"
  },
  "keywords": [
    "qa",
    "testing",
    "test-cases",
    "edge-cases",
    "playwright",
    "vitest",
    "k6",
    "e2e",
    "debugging",
    "code-review",
    "brainstorm",
    "grill-me",
    "problem-solving",
    "risk-analysis"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[qa-kit on Agent Plugins Marketplace](https://pluginsmp.com/plugins/qa-kit)