Agent skill
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
Install this agent skill to your Project
npx add-skill https://github.com/aden-hive/hive/tree/main/.claude/skills/browser-edge-cases
SKILL.md
Browser Tool Edge Cases
Standard Operating Procedure for debugging and fixing browser automation failures on complex websites.
When to Use This Skill
browser_scrollsucceeds but page doesn't movebrowser_clicksucceeds but no action triggeredbrowser_typetext disappears or doesn't workbrowser_snapshothangs or returns stale contentbrowser_navigateloads 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_scroll(tab_id, "down", 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_scroll(tab_id, "down", 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
| Symptom | Likely Cause | Check |
|---|---|---|
| Scroll doesn't move | Nested scroll container | Look for overflow: scroll divs |
| Click no effect | Element covered | Check getBoundingClientRect vs viewport |
| Type clears | Autocomplete/React | Check for event listeners on input |
| Snapshot hangs | Huge DOM | Check node count in snapshot |
| Snapshot stale | SPA hydration | Wait 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:
- Add timeout to snapshot operation
- Truncate tree at 2000 nodes
- 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_wait(tab_id, 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
| Issue | Primary Fix | Fallback |
|---|---|---|
| Scroll not working | Find scrollable container | Mouse wheel at container center |
| Click no effect | JavaScript click() | CDP mouse events |
| Type clears | Add delay_ms | Use execCommand |
| Snapshot hangs | Add timeout_s | DOM snapshot fallback |
| Stale content | Wait for selector | Increase wait_until timeout |
| Shadow DOM | Pierce selector | JavaScript traversal |
References
- registry.md - Full list of known edge cases
- scripts/test_case.py - Template for testing new cases
- BROWSER_USE_PATTERNS.md - Implementation patterns from browser-use
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
hive.note-taking
Maintain structured working notes throughout execution to prevent information loss during context pruning.
hive.error-recovery
Follow a structured recovery protocol when tool calls fail instead of blindly retrying or giving up.
hive.context-preservation
Proactively preserve critical information before automatic context pruning destroys it.
hive.task-decomposition
Decompose complex tasks into explicit subtasks before diving in.
hive.quality-monitor
Periodically self-assess output quality to catch degradation before the judge does.
hive.batch-ledger
Track per-item status when processing collections to prevent skipped or duplicated items.
Didn't find tool you were looking for?