Browser Tool Edge Cases

SkillWeb & browsing

This skill gives your AI a step-by-step method for diagnosing and fixing browser automation failures on complex websites. When browser tools fail on sites like LinkedIn, Twitter/X, or single-page apps, your AI can use it to find the cause and get the task done.

Available today. Use it from your connected AI after setup.

Add the skill, then the next time your AI's browser tools fail on a tricky site, ask it to debug and fix the failure.

Then ask your AI: use the Browser Tool Edge Cases skill

What your AI can do with it

  • Diagnose why browser tools fail on specific sites like LinkedIn or Twitter/X
  • Fix browser automation failures on single-page apps
  • Handle pages built with Shadow DOM
  • Work through a step-by-step debugging method for complex websites

What this skill tells your AI

The instructions your AI receives, as published by aden-hive/hive in .claude/skills/browser-edge-cases/SKILL.md and read by ahel’s review.

Standard Operating Procedure for debugging and fixing browser automation failures on complex websites.

When to Use This Skill

  • browser_interact(action="scroll") succeeds but page doesn't move
  • browser_interact(action="left_click") succeeds but no action triggered
  • browser_interact(action="type") text disappears or doesn't work
  • browser_snapshot hangs or returns stale content
  • browser_navigate loads wrong content

SOP: Debugging Browser Tool Failures

Phase 1: Reproduce & Isolate

1. Create minimal test case demonstrating failure
2. Test against simple site (example.com) to verify tool works
3. Test against problematic site to confirm issue

Quick isolation test:

# Test 1: Does the tool work at all?
await browser_navigate(tab_id, "https://example.com")
result = await browser_interact(action="scroll", tab_id=tab_id, scroll_direction="down", scroll_amount=100)
# Should work on simple sites

# Test 2: Does it fail on the problematic site?
await browser_navigate(tab_id, "https://linkedin.com/feed")
result = await browser_interact(action="scroll", tab_id=tab_id, scroll_direction="down", scroll_amount=100)
# If this fails but example.com works → site-specific edge case

Phase 2: Analyze Root Cause

Step 2a: Check console for errors

console = await browser_console(tab_id)
# Look for: CSP violations, React errors, JavaScript exceptions

Step 2b: Inspect DOM structure

html = await browser_html(tab_id)
snapshot = await browser_snapshot(tab_id)
# Look for:
# - Nested scrollable divs (overflow: scroll/auto)
# - Shadow DOM roots
# - iframes
# - Custom widgets

Step 2c: Identify the pattern

SymptomLikely CauseCheck
Scroll doesn't moveNested scroll containerLook for overflow: scroll divs
Click no effectElement coveredCheck getBoundingClientRect vs viewport
Type clearsAutocomplete/ReactCheck for event listeners on input; try a type action with no selector
Snapshot hangsHuge DOMCheck node count in snapshot
Snapshot staleSPA hydrationWait after navigation

Phase 3: Implement Multi-Layer Fix

Pattern: Always have fallbacks

async def robust_operation(tab_id):
    # Method 1: Primary approach
    try:
        result = await primary_method(tab_id)
        if verify_success(result):
            return result
    except Exception:
        pass

    # Method 2: CDP fallback
    try:
        result = await cdp_fallback(tab_id)
        if verify_success(result):
            return result
    except Exception:
        pass

    # Method 3: JavaScript fallback
    return await javascript_fallback(tab_id)

Pattern: Always add timeouts

# Bad - can hang forever
result = await browser_snapshot(tab_id)

# Good - fails fast with useful error
try:
    result = await browser_snapshot(tab_id, timeout_s=10.0)
except asyncio.TimeoutError:
    # Handle timeout gracefully
    result = await fallback_snapshot(tab_id)

Phase 4: Verify Fix

1. Run against problematic site → should work
2. Run against simple site → should still work (regression check)
3. Document in registry.md

Pattern Library

P1: Nested Scrollable Containers

Sites: LinkedIn, Twitter/X, any SPA with scrollable feeds

Detection:

// Find largest scrollable container
const candidates = [];
document.querySelectorAll('*').forEach(el => {
    const style = getComputedStyle(el);
    if (style.overflow.includes('scroll') || style.overflow.includes('auto')) {
        const rect = el.getBoundingClientRect();
        if (rect.width > 100 && rect.height > 100) {
            candidates.push({el, area: rect.width * rect.height});
        }
    }
});
candidates.sort((a, b) => b.area - a.area);
return candidates[0]?.el;

Fix: Dispatch scroll events at container's center, not viewport center.

P2: Element Covered by Overlay

Sites: Modals, tooltips, SPAs with loading overlays

Detection:

const rect = element.getBoundingClientRect();
const centerX = rect.left + rect.width / 2;
const centerY = rect.top + rect.height / 2;
const topElement = document.elementFromPoint(centerX, centerY);
return topElement === element || element.contains(topElement);

Fix: Wait for overlay to disappear, or use JavaScript click.

P3: React Synthetic Events

Sites: React SPAs, modern web apps

Detection: If CDP click doesn't trigger handler but manual click works.

Fix: Use JavaScript click as primary:

element.click();

P4: Huge DOM / Accessibility Tree

Sites: LinkedIn, Facebook, Twitter (feeds with 1000s of nodes)

Detection:

document.querySelectorAll('*').length > 5000

Fix:

  1. Add timeout to snapshot operation
  2. Truncate tree at 2000 nodes
  3. Fall back to DOM-based snapshot if accessibility tree too large

P5: SPA Hydration Delay

Sites: React, Vue, Angular SPAs after navigation

Detection:

// Check if React app has hydrated
document.querySelector('[data-reactroot]') ||
document.querySelector('[data-reactid]')

Fix: Wait for specific selector after navigation:

await browser_navigate(tab_id, url, wait_until="load")
await browser_interact(action="wait", tab_id=tab_id, wait_for_selector='[data-testid="content"]', timeout_ms=5000)

P6: Shadow DOM

Sites: Components using Shadow DOM, Lit elements

Detection:

document.querySelectorAll('*').some(el => el.shadowRoot)

Fix: Pierce shadow root:

function queryShadow(selector) {
    const parts = selector.split('>>>');
    let node = document;
    for (const part of parts) {
        if (node.shadowRoot) {
            node = node.shadowRoot.querySelector(part.trim());
        } else {
            node = node.querySelector(part.trim());
        }
    }
    return node;
}

Quick Reference

IssuePrimary FixFallback
Scroll not workingFind scrollable containerMouse wheel at container center
Click no effectJavaScript click()CDP mouse events
Type clearsuse_insert_text=False (per-keystroke)Use a type action (Input.insertText)
Snapshot hangsAdd timeout_sDOM snapshot fallback
Stale contentWait for selectorIncrease wait_until timeout
Shadow DOMPierce selectorJavaScript traversal

References

Signals

GitHub stars
11k
Forks
6k
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
browser-edge-cases
Source
github.com/aden-hive/hive