browser-automation
Expert in browser automation using Chrome DevTools Protocol (CDP) and WebDriver. Specializes in secure web automation, testing, and scraping with proper credential handling, domain restrictions, and audit logging. HIGH-RISK skill due to web access and data handling.
69
58%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./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.
The description establishes technical credibility with CDP/WebDriver references and appropriately flags risk level, but fails to provide explicit trigger guidance for when Claude should select this skill. It uses appropriate third-person voice but relies too heavily on technical jargon rather than natural user language, and lacks the concrete action specificity needed for reliable skill selection.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios like 'Use when the user needs to automate browser interactions, scrape dynamic websites, run web tests, or interact with pages requiring JavaScript rendering.'
Include natural user terms alongside technical ones: 'automate clicking', 'fill web forms', 'scrape websites', 'browser testing', 'Puppeteer', 'Selenium', 'headless browser'.
List specific concrete actions: 'Navigate pages, click elements, fill forms, capture screenshots, extract data from dynamic content, handle authentication flows.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (browser automation, CDP, WebDriver) and mentions actions (automation, testing, scraping, credential handling, audit logging), but doesn't list specific concrete actions like 'click elements', 'fill forms', 'capture screenshots', or 'navigate pages'. | 2 / 3 |
Completeness | Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per rubric guidelines, missing explicit trigger guidance should cap completeness at 2, and this has no trigger guidance at all. | 1 / 3 |
Trigger Term Quality | Includes some relevant technical terms (CDP, WebDriver, browser automation, scraping) but misses common user-facing terms like 'automate website', 'web crawler', 'click buttons', 'fill out forms', 'Selenium', or 'Puppeteer'. | 2 / 3 |
Distinctiveness Conflict Risk | The CDP/WebDriver focus and 'HIGH-RISK' designation provide some distinctiveness, but 'web automation, testing, and scraping' could overlap with general testing skills or web scraping tools without browser automation. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill with excellent actionable code examples and clear TDD workflow. The main weakness is some verbosity in explanatory sections that describe concepts Claude already understands (CDP, WebDriver basics, what frameworks do). The security patterns and performance optimizations are particularly well-documented with good/bad comparisons.
Suggestions
Remove or significantly condense sections 4 (Core Responsibilities) and 5.1 (Automation Frameworks) which explain concepts Claude already knows - the code examples already demonstrate these principles
Consolidate the 'Core Principles' and 'Core Expertise Areas' lists in the overview into a single, shorter list focused on what's unique to this skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity, particularly in the 'Core Expertise Areas' and 'Technical Foundation' sections which list concepts Claude already knows. The overview section could be significantly tightened, though the code examples themselves are appropriately lean. | 2 / 3 |
Actionability | Excellent executable code examples throughout - the SecureBrowserAutomation class, rate limiter, test fixtures, and performance patterns are all copy-paste ready with complete implementations. Commands for running tests are specific and actionable. | 3 / 3 |
Workflow Clarity | Clear TDD workflow with explicit steps (write failing test → implement minimum → refactor → verify). The pre-implementation checklist provides explicit validation checkpoints, and the 'Implementation Order' summary reinforces the sequence with clear gates. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from overview to implementation to security standards. References to external files (secure-session-full.md, security-examples.md, threat-model.md) are one level deep and clearly signaled at the end. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 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 |
Total | 12 / 16 Passed | |
- Repository
- martinholovsky/claude-skills-generator
- Commit
1086ef2
- 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.