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
40
Quality
27%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent/skills/browser-automation/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description reads like introductory documentation rather than a skill selection guide. While it establishes the domain (browser automation with Playwright/Puppeteer) and provides context about framework choice, it lacks explicit trigger conditions and concrete action verbs. The description is also truncated (ends mid-word '202'), suggesting incomplete content.
Suggestions
Add an explicit 'Use when...' clause with trigger terms like 'automate browser', 'web scraping', 'Playwright', 'Puppeteer', 'headless', 'click buttons', 'fill web forms'
Replace conceptual language ('understanding selectors, waiting strategies') with concrete actions ('navigate pages, click elements, extract data, handle authentication, capture screenshots')
Remove the editorial commentary ('Playwright won the framework war', 'Key insight') and focus on actionable capability descriptions
| 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) 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 documentation than 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', 'automate website', 'click', 'navigate', or file extensions. | 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%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill content is essentially a stub with persona framing and a list of links to sub-skills. It lacks any actionable code, concrete examples, or workflow guidance in the main file. While the progressive disclosure structure via sub-skills is reasonable, the main SKILL.md provides insufficient standalone value.
Suggestions
Add a Quick Start section with executable Playwright code showing basic page navigation and element interaction
Include at least one concrete example comparing good vs bad selector patterns inline
Remove the persona framing paragraph and replace with actionable guidance
Add a brief workflow showing the typical automation development cycle (write -> run -> debug -> fix selectors)
| 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 core insight paragraph is useful but could be tighter. | 2 / 3 |
Actionability | No executable code, commands, or concrete examples are provided. The content describes concepts and links to sub-skills but gives no copy-paste ready guidance in the main skill file itself. | 1 / 3 |
Workflow Clarity | No workflow or sequence is defined. The content lists patterns and anti-patterns via links but provides no steps, validation checkpoints, or process guidance for actually performing browser automation tasks. | 1 / 3 |
Progressive Disclosure | The skill does reference sub-skills with clear links, which is good structure. However, the main file provides almost no substantive content - it's essentially just a table of contents with no quick-start or overview content to orient the reader. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Dokhacgiakhoa/antigravity-ide
- Commit
3395991
- 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.