anthropics/skills180kwebapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
浏览器自动化
搜索文档、Skill 和 MCP
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.
把这段话发给 Claude Code、Codex 或 Cursor。智能体会先检查安全性,你确认后才安装。
读取 https://funcoding.ai/skills/aden-hive/hive/browser-edge-cases/install.md ,按里面的步骤帮我安装这个 Skill。
Standard Operating Procedure for debugging and fixing browser automation failures on complex websites.
browser_interact(action="scroll") succeeds but page doesn't movebrowser_interact(action="left_click") succeeds but no action triggeredbrowser_interact(action="type") text disappears or doesn't workbrowser_snapshot hangs or returns stale contentbrowser_navigate loads wrong content1. 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
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; try a type action with no selector |
| Snapshot hangs | Huge DOM | Check node count in snapshot |
| Snapshot stale | SPA hydration | Wait after navigation |
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)
1. Run against problematic site → should work
2. Run against simple site → should still work (regression check)
3. Document in registry.md
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.
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.
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();
Sites: LinkedIn, Facebook, Twitter (feeds with 1000s of nodes)
Detection:
document.querySelectorAll('*').length > 5000
Fix:
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)
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;
}
| 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 | use_insert_text=False (per-keystroke) | Use a type action (Input.insertText) |
| Snapshot hangs | Add timeout_s | DOM snapshot fallback |
| Stale content | Wait for selector | Increase wait_until timeout |
| Shadow DOM | Pierce selector | JavaScript traversal |
anthropics/skills180kToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
浏览器自动化
addyosmani/agent-skills103kTests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.
浏览器自动化
ComposioHQ/awesome-claude-skills77kToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
浏览器自动化
code-yeongyu/oh-my-openagent70kDrives a real browser through the omowright library from the js eval kernel: sites the user is already signed into, forms and clicks, JS-rendered pages, screenshots, web QA, extension popups, a human handoff for login, CAPTCHA or OTP, and a browser you own for scraping, bot-scored targets, network capture and QA traces. Use for any interactive browser task; not for a plain search or an unblocked static fetch.
浏览器自动化
shanraisshan/claude-code-best-practice67kBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
浏览器自动化
CherryHQ/cherry-studio52kCherry Studio first-party tool and bundled-shell routing for general agents. For straightforward local work in shell-capable sessions, run JS/TS with `bun <file>` and one-off JS tools with `bun x`; run Python with `uv run [--with <pkg>] python` and one-off Python CLIs with `uvx`; search with `rg`. Load this guide before changing project dependencies, deciding whether a tool should be ephemeral or reusable, reading or converting local Office/PDF files, coordinating or delegating across Agent Sessions, or using Cherry-owned web/browser, knowledge, persistent memory, schedules/notifications, IM channels, image generation, artifact reporting, managed CLI, skill, or MCP-server-registration capabilities—even if the user names no tool. Consult it before shell/file workarounds; live tool schemas are authoritative.
浏览器自动化