ella79

Create Agentic Playwright Project — Testing skill for Claude Code

Testing community

Free scaffolder for a Playwright + TypeScript agentic-QA project with Claude Code agents and skills, MCP, evals and CI.

How to install Create Agentic Playwright Project

This entry records only its repository, not the path inside it, so there is no exact command to give. Open ella79/create-agentic-playwright-project and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Create Agentic Playwright Project does

Free scaffolder for a Playwright + TypeScript agentic-QA project with Claude Code agents and skills, MCP, evals and CI.

Alternatives in Testing

OpenAgentsControl — AI agent framework for plan-first development workflows with approval-based execution 4.8k ★
Langgraphjs — by langchain-ai - Offers comprehensive build and test commands with detailed TypeScript style guidelines, laye 2.7k ★
Inkline — by inkline - Structures development workflow using pnpm with emphasis on TypeScript and Vue 3 Composition API 1.4k ★

README

create-agentic-playwright-project

Scaffold a production-shaped **QA project** in one command: Playwright + TypeScript, with Claude Code agents and skills, Playwright MCP, an evals gate, CI and architecture docs. It gives you the architecture already defined in the repo, so you start a new project from a real structure instead of a blank page.

What you get

Playwright + TypeScript, Page Object Model (two bases), fixtures, semantic locators, utils/url.ts, auth setup project.
Three test projects: e2e, visual, api. Independent tests, fullyParallel, CI sharded in parallel.
Claude Code setup: CLAUDE.md, agents (planner, generator, healer, reviewer, reporter), skills (requirements, page-object, visual-regression, api-testing, playwright-mcp, evals, bug-reporting, jira-ticket, test-status), commands (/feature, /ticket, /coverage).
Playwright MCP wired in .mcp.json; seed.spec.ts for the agents workflow; optional Jira MCP.
Programmatic runner using @anthropic-ai/claude-agent-sdk (agent/run.ts).
Evals gate (evals/run-evals.ts) + GitHub Actions CI (build image -> static gate -> sharded suite -> merged report).
Requirements-driven plans with traceability, specs/STATUS.md coverage report, Dockerfile, ADRs as project memory.
Templates for stories, plans, page objects and tests.

Everything follows official guidance (Playwright best practices, POM, fixtures, snapshots, API testing, test-agents, reporters, sharding; Claude Agent SDK; MCP). Sources are cited in the generated `ARCHITECTURE.md`.

Install and use

# install the scaffolder globally from GitHub (public repo, no token)
npm install -g github:ella79/create-agentic-playwright-project
create-agentic-playwright-project my-app

Other ways to run it (public repo, no account needed):

npx github:ella79/create-agentic-playwright-project my-app   # no global install
npx create-agentic-playwright-project my-app                 # if also published to npm
`