Content
57%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable skill with excellent, executable code examples covering a wide range of go-rod features. However, it suffers from significant verbosity — explaining concepts Claude already knows (CDP, sandboxing, what stealth evasions do internally), listing obvious trigger conditions, and inlining extensive reference material that should be in separate files. The lack of explicit multi-step workflows with validation checkpoints is a notable gap for a skill involving browser automation.
Suggestions
Remove the 'When to Use This Skill' and 'Safety & Risk' sections entirely — Claude can infer when to use browser automation and doesn't need to be told that reading web pages is safe.
Trim the 'How Stealth Works' section to just the usage pattern — Claude doesn't need to know the internal details of WebGL spoofing or plugin array patching to use stealth.MustPage().
Move the 12 implementation guideline sections into a separate reference file (e.g., references/implementation-patterns.md) and keep only the top 3-4 most essential patterns inline.
Add an explicit end-to-end workflow example with validation steps, e.g., 'Scrape a dynamic site: 1. Launch with stealth → 2. Navigate → 3. Verify page loaded (check title/element) → 4. Extract data → 5. Validate extracted data is non-empty → 6. Clean up'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is significantly verbose. The 'When to Use This Skill' section lists 7 bullet points of obvious triggers Claude could infer. The 'Safety & Risk' section explains basic concepts like sandboxing and defer patterns. The 'How Stealth Works' section explains internal implementation details (WebGL spoofing, plugin arrays) that Claude doesn't need to know to use the library. The overview paragraph explains what CDP is and how Rod differs from wrappers — unnecessary context. The entire document is ~400+ lines when it could be ~150-200 lines. | 2 / 5 |
Actionability | Excellent actionability throughout. Every section provides complete, executable Go code examples covering installation, browser lifecycle, stealth usage, network hijacking, concurrent page pools, screenshots, file downloads, JS evaluation, and more. Code is copy-paste ready with proper imports shown and both Must/Error patterns demonstrated. | 5 / 5 |
Workflow Clarity | The skill presents individual features clearly but lacks explicit multi-step workflow sequences with validation checkpoints. There's no 'here's how to build a complete scraper step-by-step' workflow with verification steps. The Best Practices and Common Pitfalls sections provide good guidance but are lists rather than sequenced workflows. For a skill involving browser automation (which can fail in many ways), explicit validate-fix-retry loops would be valuable. | 3 / 5 |
Progressive Disclosure | The skill references an `examples/` directory and `references/api-reference.md`, but no bundle files are provided to verify these exist. The main SKILL.md is monolithic — inlining 12 numbered implementation guideline sections with full code examples that could be split into separate reference files. The documentation references section at the end is good, but the body itself would benefit from moving detailed sections (like network hijacking, concurrent pools, event handling) into separate files. | 3 / 5 |
Total | 13 / 20 Passed |