🎯

browser-e2e-tester

🎯Skill

from adaptationio/skrillz

What it does

Automatically runs browser-based end-to-end tests to verify feature implementation, capturing screenshots and generating comprehensive test reports.

📦

Part of

adaptationio/skrillz(191 items)

browser-e2e-tester

Installation

Add MarketplaceAdd marketplace to Claude Code

/plugin marketplace add adaptationio/Skrillz

Install PluginInstall plugin from marketplace

/plugin install skrillz@adaptationio-Skrillz

Claude CodeAdd plugin in Claude Code

/plugin enable skrillz@adaptationio-Skrillz

Add MarketplaceAdd marketplace to Claude Code

/plugin marketplace add /path/to/skrillz

Install PluginInstall plugin from marketplace

/plugin install skrillz@local

+ 4 more commands

📖 Extracted from docs: adaptationio/skrillz

Need more details? View full documentation on GitHub →

3Installs

Last UpdatedJan 16, 2026

View on GitHub Back to Skills

Skill Details

SKILL.md

Browser-based E2E testing for feature verification. Use when running end-to-end tests, validating features in browser, verifying user flows, or testing feature completion.

Overview

# Browser E2E Tester

Runs browser-based end-to-end tests to verify feature implementation meets acceptance criteria.

Quick Start

Run Feature Tests

```python

from scripts.e2e_tester import E2ETester

tester = E2ETester(project_dir)

result = await tester.test_feature("auth-001")

if result.passed:

print(f"Feature verified: {result.feature_id}")

else:

print(f"Failed: {result.failures}")

```

Run All Tests

```python

results = await tester.test_all_features()

print(f"Passed: {results.passed}/{results.total}")

```

E2E Testing Workflow

```

┌─────────────────────────────────────────────────────────────┐

│ E2E TEST WORKFLOW │

├─────────────────────────────────────────────────────────────┤

│ │

│ 1. SETUP │

│ ├─ Load feature acceptance criteria │

│ ├─ Start test server (if needed) │

│ ├─ Initialize browser automation │

│ └─ Set test timeout │

│ │

│ 2. EXECUTE │

│ ├─ Navigate to feature entry point │

│ ├─ Execute test steps │

│ ├─ Capture screenshots on failure │

│ └─ Record test artifacts │

│ │

│ 3. VERIFY │

│ ├─ Check expected outcomes │

│ ├─ Validate UI state │

│ ├─ Verify API responses │

│ └─ Assert data persistence │

│ │

│ 4. REPORT │

│ ├─ Generate test report │

│ ├─ Update feature status │

│ └─ Store failure artifacts │

│ │

└─────────────────────────────────────────────────────────────┘

```

Test Result Structure

```python

@dataclass

class TestResult:

feature_id: str

passed: bool

duration_ms: int

steps_executed: int

steps_passed: int

failures: list[str]

screenshots: list[Path]

artifacts: dict

```

Supported Test Frameworks

| Framework | Integration | Use Case |

|-----------|-------------|----------|

| Playwright | Native | Modern web apps |

| Puppeteer | Adapter | Chrome-focused |

| Selenium | Adapter | Legacy browsers |

| Cypress | CLI | Component tests |

Feature Acceptance Format

```json

{

"feature_id": "auth-001",

"acceptance_criteria": [

{

"step": "Navigate to login page",

"action": "goto",

"target": "/login"

{

"step": "Enter credentials",

"action": "fill",

"target": "#email",

"value": "test@example.com"

{

"step": "Submit form",

"action": "click",

"target": "button[type=submit]"

{

"step": "Verify redirect",

"action": "assert_url",

"expected": "/dashboard"

}

]

}

```

Integration Points

coding-agent: Triggers tests after implementation
progress-tracker: Reports test metrics
error-recoverer: Handles test failures
checkpoint-manager: Restores state on failure

References

references/E2E-PATTERNS.md - Test patterns
references/BROWSER-AUTOMATION.md - Automation guide

Scripts

scripts/e2e_tester.py - Core tester
scripts/browser_controller.py - Browser automation
scripts/test_reporter.py - Report generation
scripts/acceptance_parser.py - Criteria parser

More from this repository10

🎯

xai-stock-sentiment🎯Skill

xai-stock-sentiment skill from adaptationio/skrillz

🎯

ralph-prompt-single-task🎯Skill

Generates Ralph-compatible prompts for single implementation tasks with clear completion criteria and automatic verification.

🎯

autonomous-loop🎯Skill

Orchestrates continuous autonomous coding sessions, managing feature implementation, testing, and progress tracking with intelligent checkpointing and recovery mechanisms.

🎯

auto-claude-troubleshooting🎯Skill

auto-claude-troubleshooting skill from adaptationio/skrillz

🎯

auto-claude-setup🎯Skill

auto-claude-setup skill from adaptationio/skrillz

🎯

observability-analyzer🎯Skill

Analyzes Claude Code observability data to generate insights on performance, costs, errors, tool usage, sessions, conversations, and subagents through advanced metrics and log querying.

🎯

xai-financial-integration🎯Skill

xai-financial-integration skill from adaptationio/skrillz

🎯

xai-agent-tools🎯Skill

xai-agent-tools skill from adaptationio/skrillz

🎯

xai-crypto-sentiment🎯Skill

xai-crypto-sentiment skill from adaptationio/skrillz

🎯

auto-claude-memory🎯Skill

auto-claude-memory skill from adaptationio/skrillz