Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Comprehensive guide for browser automation and web scraping with go-rod (Chrome DevTools Protocol) including stealth anti-bot-detection patterns.
.claude/skills/go-rod-master/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 22% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 59% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -13% | 0% |
Read the detailed guide before executing this skill. It retains the complete procedure and reference material. Treat its safety, prerequisites, and validation requirements as mandatory. For focused work, load the relevant sections; for end-to-end work, read the guide completely.
Risk Level: 🔵 Safe
defer pattern — browsers and pages close automatically.See the examples/ directory for complete, runnable Go files:
examples/basic_scrape.go — Minimal scraping exampleexamples/stealth_page.go — Anti-detection with go-rod/stealthexamples/request_hijacking.go — Intercepting and modifying network requestsexamples/concurrent_pages.go — Page pool for concurrent scrapinggo-rod/stealth handles common detection (WebDriver, plugin fingerprints, WebGL), extremely strict systems (some Cloudflare configurations, Akamai Bot Manager) may still detect automation. Additional measures (residential proxies, human-like behavioral patterns) may be needed.PagePool and limit concurrency on memory-constrained systems.Headless(false) with XVFB for server environments.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-12 | pass→pass | 16,614 | 31,173 | +88% | 1 | 1 | 0% | 1,857 | 2,410 | +30% | 0 | 0 | — |
case-01 | fail→pass | 97,312 | 18,012 | -81% | 1 | 1 | 0% | 2,525 | 2,748 | +9% | 0 | 0 | — |
case-02 | fail→pass | 30,110 | 44,761 | +49% | 1 | 1 | 0% | 4,418 | 3,479 | -21% | 0 | 0 | — |
case-03 | pass→pass | 16,084 | 13,140 | -18% | 1 | 1 | 0% | 2,549 | 2,886 | +13% | 0 | 0 | — |
case-04 | fail→pass | 23,669 | 16,492 | -30% | 1 | 1 | 0% | 3,008 | 3,662 | +22% | 0 | 0 | — |
case-05 | pass→pass | 26,098 | 14,199 | -46% | 1 | 1 | 0% | 1,945 | 2,236 | +15% | 0 | 0 | — |
case-06 | pass→pass | 14,015 | 10,332 | -26% | 1 | 1 | 0% | 1,472 | 1,226 | -17% | 0 | 0 | — |
case-07 | fail→fail | 17,065 | 16,188 | -5% | 1 | 1 | 0% | 2,421 | 2,284 | -6% | 0 | 0 | — |
case-08 | pass→pass | 15,627 | 11,497 | -26% | 1 | 1 | 0% | 1,644 | 1,592 | -3% | 0 | 0 | — |
case-09 | fail→pass | 26,009 | 30,403 | +17% | 1 | 1 | 0% | 3,071 | 4,893 | +59% | 0 | 0 | — |
case-10 | pass→pass | 57,919 | 17,740 | -69% | 1 | 1 | 0% | 2,344 | 2,795 | +19% | 0 | 0 | — |
case-11 | fail→pass | 22,463 | 22,632 | +1% | 1 | 1 | 0% | 3,180 | 2,756 | -13% | 0 | 0 | — |
case-13 | pass→pass | 22,762 | 10,868 | -52% | 1 | 1 | 0% | 1,080 | 1,790 | +66% | 0 | 0 | — |
case-14 | pass→pass | 14,287 | 13,172 | -8% | 1 | 1 | 0% | 1,389 | 2,057 | +48% | 0 | 0 | — |
case-15 | fail→pass | 16,525 | 8,305 | -50% | 1 | 1 | 0% | 1,443 | 1,778 | +23% | 0 | 0 | — |
case-16 | pass→pass | 12,468 | 17,164 | +38% | 1 | 1 | 0% | 1,743 | 2,136 | +23% | 0 | 0 | — |
case-17 | pass→pass | 22,271 | 17,730 | -20% | 1 | 1 | 0% | 2,620 | 3,502 | +34% | 0 | 0 | — |
case-18 | pass→pass | 20,115 | 18,894 | -6% | 1 | 1 | 0% | 3,464 | 2,399 | -31% | 0 | 0 | — |
case-19 | pass→pass | 18,723 | 12,180 | -35% | 1 | 1 | 0% | 2,315 | 1,691 | -27% | 0 | 0 | — |
case-20 | fail→pass | 25,641 | 24,838 | -3% | 1 | 1 | 0% | 2,618 | 2,188 | -16% | 0 | 0 | — |
case-21 | pass→pass | 23,717 | 24,775 | +4% | 1 | 1 | 0% | 703 | 1,287 | +83% | 0 | 0 | — |
case-22 | fail→pass | 24,781 | 16,123 | -35% | 1 | 1 | 0% | 2,675 | 1,969 | -26% | 0 | 0 | — |
case-23 | fail→fail | 21,836 | 20,760 | -5% | 1 | 1 | 0% | 2,621 | 3,183 | +21% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 23 cases were attempted. The headline lift of +35 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 7/28/2026 | +50% |
Other measured skills in the registry, with their headline benchmark lift.