browser-automation
Browser automation powers web testing, scraping, and AI agent interactions. The difference between a flaky script and a reliable system comes down to understanding selectors, waiting strategies, and anti-detection patterns. This skill covers Playwright (recommended) and Puppeteer, with patterns for testing, scraping, and agentic browser control. Key insight: Playwright won the framework war. Unless you need Puppeteer's stealth ecosystem or are Chrome-only, Playwright is the better choice in 202
Overall
score
37%
Does it follow best practices?
Validation for skill structure
Install with Tessl CLI
npx tessl i github:sickn33/antigravity-awesome-skills --skill browser-automationActivation
33%This description reads like an educational overview rather than a skill selection guide. While it establishes the domain (browser automation with Playwright/Puppeteer) and provides some context about framework choice, it fails to include explicit trigger conditions and lacks concrete action verbs that would help Claude know when to select this skill. The description is also truncated (ends mid-word '202').
Suggestions
Add an explicit 'Use when...' clause with trigger terms like 'browser automation', 'Playwright', 'Puppeteer', 'web scraping', 'E2E testing', 'headless browser', or 'automated browser'.
Replace the editorial content ('Key insight: Playwright won the framework war') with concrete capabilities like 'Automate browser interactions, handle dynamic content, manage authentication flows, capture screenshots'.
Include common user phrases and file/technology markers like '.spec.ts', 'playwright.config', 'page.goto', 'browser testing' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (browser automation) and mentions some actions (web testing, scraping, AI agent interactions) but lacks concrete specific actions like 'click buttons', 'fill forms', 'capture screenshots'. The description focuses more on concepts (selectors, waiting strategies, anti-detection patterns) than actionable capabilities. | 2 / 3 |
Completeness | Describes what the skill covers (browser automation frameworks and patterns) but completely lacks a 'Use when...' clause or any explicit trigger guidance. The description reads more like an introduction to a tutorial than skill selection criteria. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Playwright', 'Puppeteer', 'browser automation', 'web testing', 'scraping', but misses common user terms like 'headless browser', 'web crawler', 'automated testing', 'E2E tests', 'end-to-end', or 'selenium alternative'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of Playwright and Puppeteer specifically helps distinguish it, but 'web testing' and 'scraping' could overlap with other testing or data extraction skills. The framework-specific focus provides some distinctiveness. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
22%This skill content appears to be incomplete or truncated, with sections that cut off mid-sentence and a Sharp Edges table with placeholder 'Issue' text instead of actual issues. The content lacks any executable code examples despite being about browser automation, and the pattern descriptions are conceptual without concrete implementation guidance. The persona framing adds unnecessary tokens without value.
Suggestions
Add complete, executable Playwright code examples for each pattern (e.g., show actual user-facing locator syntax like `page.getByRole('button', { name: 'Submit' })`)
Complete the Sharp Edges table with actual issues and full solution code, not just comment fragments
Remove the persona paragraph and capabilities list - replace with a quick start section showing a minimal working automation script
Add a clear workflow for common tasks (e.g., '1. Launch browser → 2. Navigate → 3. Interact → 4. Assert → 5. Cleanup') with validation steps
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content includes some unnecessary persona framing ('You are a browser automation expert who has debugged thousands...') that Claude doesn't need. The capabilities list is verbose. However, the patterns/anti-patterns sections are reasonably lean. | 2 / 3 |
Actionability | The skill is severely lacking in concrete, executable guidance. Pattern sections mention concepts but provide no code examples. The Sharp Edges table has solutions that appear truncated (just comments like '# REMOVE all waitForTimeout calls' with no actual code). No copy-paste ready examples exist. | 1 / 3 |
Workflow Clarity | There is no clear workflow or sequence of steps. The content describes patterns conceptually but doesn't show how to implement them or in what order. No validation checkpoints or feedback loops are present for what should be multi-step automation processes. | 1 / 3 |
Progressive Disclosure | The content has some structure with sections for Patterns, Anti-Patterns, and Sharp Edges. However, the Related Skills section references other skills but there are no links to detailed documentation, examples, or reference materials. The content appears incomplete/truncated rather than well-organized. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
56%Validation — 9 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
body_examples | No examples detected (no code fences and no 'Example' wording) | Warning |
body_output_format | No obvious output/return/format terms detected; consider specifying expected outputs | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 9 / 16 Passed | |
Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.