ksycz/playwright-ai-qa-workflow
AI-assisted QA workflow with Playwright: requirements, a human-written test strategy, AI-planned and generated tests, planted bugs, healing and a requirements-to-tests traceability report. Every AI step is reviewed and logged.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
up to ~3.3k tokens
Claude Code loads MCP tools on demand, so the real cost is usually lower.
Moderate · median rig: 2.3k · breakdown
Copy this rig
# review before running: this installs third-party code $ claude mcp add playwright-test -- npx playwright run-test-mcp-server $ npx degit ksycz/playwright-ai-qa-workflow/.claude ./rig-playwright-ai-qa-workflow # inspect, then merge into .claude/
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add playwright-test -- npx playwright run-test-mcp-server $ npx degit ksycz/playwright-ai-qa-workflow/.claude/skills/derive-test-data .claude/skills/derive-test-data $ npx degit ksycz/playwright-ai-qa-workflow/.claude/skills/refine-requirements .claude/skills/refine-requirements $ npx degit ksycz/playwright-ai-qa-workflow/.claude/skills/review-generated-test .claude/skills/review-generated-test $ npx degit ksycz/playwright-ai-qa-workflow/.claude/skills/review-test-plan .claude/skills/review-test-plan
$ curl -fsSL --create-dirs -o .claude/agents/playwright-test-generator.md https://raw.githubusercontent.com/ksycz/playwright-ai-qa-workflow/main/.claude/agents/playwright-test-generator.md $ curl -fsSL --create-dirs -o .claude/agents/playwright-test-healer.md https://raw.githubusercontent.com/ksycz/playwright-ai-qa-workflow/main/.claude/agents/playwright-test-healer.md $ curl -fsSL --create-dirs -o .claude/agents/playwright-test-planner.md https://raw.githubusercontent.com/ksycz/playwright-ai-qa-workflow/main/.claude/agents/playwright-test-planner.md
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"permissions": {
"deny": [
"Edit(requirements/**)",
"Write(requirements/**)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| playwright · "playwright-test" | npm | 2.5k |
Skills (4)
Subagents (3)
| playwright-test-generator model: sonnet | Use this agent when you need to create automated browser tests using Playwright Examples: <example>Context: User wants to generate a test for the test plan item. <test-suite><!-- Verbatim name of the |
| playwright-test-healer model: sonnet | Use this agent when you need to debug and fix failing Playwright tests |
| playwright-test-planner model: sonnet | Use this agent when you need to create comprehensive test plan for a web application or website |
Permissions
deny (2)
Edit(requirements/**)
Write(requirements/**)
ask (0)
—
allow (2)
Bash(npm run *)
Bash(npx playwright *)
Similar rigs
ella79/agentic-playwright-suite
Playwright + TypeScript E2E, API and visual regression suite for Automation Exercise, authored and healed through Claude Code agents over Playwright MCP, with a containerised CI pipeline and a published Allure dashboard.
Orchestrator 11.8k tok · · Q18
borysjakub/toolshop-qa-agentic
Agentický QA projekt: E2E testy e-shopu Toolshop v Playwright + TypeScript, řízené přes Claude Code s lidskou verifikací
Fort Knox 3.9k tok · · Q20
saltbo/agent-kanban
An agent-first task board, Take human out of the loop.
Pragmatist 1.1k tok · · Q15
stsiazhkin/agent-workflow-bootstrap
A reusable bootstrap template for specification-driven development with GitHub Copilot and Claude Code. Includes shared instructions, custom agents, prompt workflows, feature documentation templates, Jira ticket planning, agent handoffs, va
Pragmatist 1.6k tok · · Q5