AG

agentra-e2e-testing

Browser-based E2E validation for Agentra applications.

Install

mkdir -p .claude/skills/agentra-e2e-testing && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14816" && unzip -o skill.zip -d .claude/skills/agentra-e2e-testing && rm skill.zip

Installs to .claude/skills/agentra-e2e-testing

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Plan, write, run, or review Agentra E2E tests using Playwright/browser tooling. Use for critical chat/auth/user journeys, flaky tests, screenshots, traces, and browser-driven validation.
186 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Identify critical user journeys and owning workspaces
  • Use stable selectors and explicit waits for validation
  • Capture screenshots, traces, or console/network details for diagnosis
  • Quarantine or document flaky behavior
  • Report journey, command, artifacts, result, and follow-up risk

How it works

The skill validates Agentra workflows at the browser level, focusing on critical user journeys, and uses Playwright/browser tooling to capture diagnostic information and report findings.

Inputs & outputs

You give it
Agentra workflow or user journey
You get back
Validation report with captured artifacts, result, and follow-up risk

When to use agentra-e2e-testing

  • Test auth flow redirects
  • Validate chat stream interruption
  • Debug flaky browser-based tests

About this skill

Agentra E2E Testing

Use this skill for browser-level validation of Agentra workflows.

Sources of truth

  • AGENTS.md
  • Existing Playwright/browser-use tooling in the Codex environment.
  • .claude/skills/e2e-testing/SKILL.md remains a reference for generic E2E patterns when deeper examples are needed.

Workflow

  1. Identify the critical user journey and owning workspace.
  2. Prefer existing app scripts and test patterns before introducing new test structure.
  3. Use stable selectors and explicit waits based on user-visible state.
  4. Capture screenshots, traces, or console/network details when diagnosing.
  5. Quarantine or document flaky behavior instead of hiding it with broad waits.

Agentra focus areas

  • Auth redirects and signed-in/signed-out states.
  • Chat request lifecycle and SSE/stream interruption behavior.
  • Error, loading, empty, and cancellation states.
  • Runtime smoke handoff when UI symptoms point to AgentCore behavior.

Output

Report journey, command or browser target, artifacts captured, result, and follow-up risk.

When not to use it

  • The user needs generic E2E patterns when deeper examples are needed
  • The user needs to write video scripts or storyboards

Limitations

  • Does not hide flaky behavior with broad waits
  • Does not write video scripts or storyboards

How it compares

This skill provides specialized E2E testing for Agentra workflows, focusing on browser-level validation and specific Agentra focus areas, unlike a generic E2E testing approach.

Compared to similar skills

agentra-e2e-testing side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
agentra-e2e-testing (this skill)03moNo flagsIntermediate
ui-ux-expert-skill919moReviewAdvanced
frontend-testing113moReviewIntermediate
feature-flags66moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry