AI Knowledge Hub
Menu

Adtech / Other

Playwright Agentic E2E QA

Build and maintain reusable Playwright smoke tests with planner, generator, and healer loops for web app regression checks.

DocumentationAgent instructionsRequirements & limits

Use when a web app needs Playwright smoke coverage, failure diagnosis, and minimal healing suggestions.

Inputs

  • app_base_url or local dev command
  • target routes (default smoke set)
  • selectors or user-visible labels for key actions
  • monorepo path hints (where playwright.config.* and app package live)

Outputs

  • Playwright spec
  • Run summary
  • Healing suggestions

Before you begin

  • Reading and copying the procedure require no terminal setup. Check requirements for any packaged programs separately.

Try this first

Read the procedure and supply its documented inputs. Use the full text in an agent app or chat that supports pasted instructions, following that host's guidance.

Limits for this step
  • Instruction package only; it does not provide or authorize an executable runtime capability.
  • May run local test commands and propose fixes; require human approval before deleting tests or broadening coverage scope.
Read full instructionsHide full instructionsSKILL.md · v0.1.0

Playwright Agentic E2E QA

When to use

Use for repeatable browser QA before merge, especially when UI changes often and tests need fast regeneration/healing.

Inputs required

  • app_base_url or local dev command
  • target routes (default smoke set)
  • selectors or user-visible labels for key actions
  • monorepo path hints (where playwright.config.* and app package live)

Workflow

  1. Planner: lock test scope first (smoke routes + highest-risk interactions).
  2. Generator: produce Playwright tests using user-facing locators and stable assertions.
  3. Runner: execute tests locally/CI and capture traces/screenshots on failure.
  4. Healer: when tests break, update selectors/flows with smallest safe patch and re-run.
  5. Promote: keep the suite reusable as shared QA coverage for new hub features.

Monorepo / subdir setup rules

  • Always set explicit testDir, outputDir, and webServer.cwd in Playwright config.
  • Keep CI working directory explicit when app code is in a subfolder (for example apps/web).
  • Prefer a deterministic base URL (http://127.0.0.1:3000) for local + CI parity.

Output format

  • Test Plan: routes + interactions + pass criteria
  • Generated/updated test files
  • Run Summary: pass/fail, key failures, healing changes applied
  • Follow-up Risks: flaky areas and selector hardening actions

Guardrails

  • Do not claim coverage beyond implemented tests.
  • Keep smoke scope small and deterministic before expanding.
  • Never auto-delete failing tests; heal with minimal, explainable changes.
  • If selectors are unstable, prefer role/text/test-id improvements over brittle CSS chains.
View file metadata
---
name: playwright-agentic-e2e
description: Plan, generate, run, and heal Playwright smoke tests for web routes and core UI interactions in monorepo-safe setups.
---

Summary sources · Catalogue metadata, skill.yaml, SKILL.md · v0.1.0 · Release package

Install instruction files

These commands copy guidance into the selected runtime directories. Confirm that your agent app discovers it. Any packaged programs need separate setup and verification.

Install (Codex)

./bin/skills-hub install adtech/[email protected] --runtime codex

Install (Claude)

./bin/skills-hub install adtech/[email protected] --runtime claude

Install (Generic)

./bin/skills-hub install adtech/[email protected] --runtime generic --target ./my-agent/skills

How You Can Use This

Documentation

Resource form: Agent instructions

Read or copy the guidance. Any packaged programs have separate execution requirements and evidence.

First run: Read SKILL.md and follow the documented workflow.

Current limits

  • Instruction package only; it does not provide or authorize an executable runtime capability.
What installation and verification mean
File installation
Places package files and generated configuration in the selected directories.
Native discovery
Your agent app finds and accepts the instructions, tools or plugin registrations.
Mock execution
Exercises sample fixtures. Connected data and provider effects need a separate check.
Connected operation
Requires current configuration, provider authentication, scoped permissions and a successful operation in your intended environment.

Declared compatibility

Compatibility unknown: versions and capabilities have not been declared.

Classification: declared

Technical details and release files

Operational Summary

Execution mode: may-run-local-verification

Approval boundary: May run local test commands and propose fixes; require human approval before deleting tests or broadening coverage scope.

Review and lifecycle

Review maturity: Experimental

Security review declaration: Not declared

Lifecycle: Active

These release declarations are separate from evidence that a workflow operates in your environment.

Runtime & Dependencies

ID: adtech/playwright-agentic-e2e

Tags: qa, e2e, playwright, smoke-tests, ci

Runtimes: codex, claude, generic

Tool dependencies: 3

API dependencies: 0

Dependencies

Tools: node, pnpm, npx

APIs: Not documented

Outputs

  • Playwright spec
  • Run summary
  • Healing suggestions