{ "schemaVersion": "1.0", "item": { "slug": "browser-automation-ultra", "name": "Browser Automation Ultra", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/swaylq/browser-automation-ultra", "canonicalUrl": "https://clawhub.ai/swaylq/browser-automation-ultra", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/browser-automation-ultra", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=browser-automation-ultra", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/anti-detection.md", "scripts/browser-lock.sh", "scripts/examples/publish-behance.js", "scripts/examples/publish-deviantart.js", "scripts/examples/publish-pinterest.js" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/browser-automation-ultra" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/browser-automation-ultra", "agentPageUrl": "https://openagent3.xyz/skills/browser-automation-ultra/agent", "manifestUrl": "https://openagent3.xyz/skills/browser-automation-ultra/agent.json", "briefUrl": "https://openagent3.xyz/skills/browser-automation-ultra/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Browser Automation Ultra", "body": "Explore → Record → Replay → Fix. Convert expensive browser-tool interactions into zero-token Playwright scripts that reuse OpenClaw's Chrome session (cookies/login intact)." }, { "title": "Prerequisites", "body": "Install Playwright (once per machine):\n\nnpm install -g playwright\n# or in workspace: npm init -y && npm install playwright\n\nNo browser download needed — scripts connect to OpenClaw's existing Chrome via CDP." }, { "title": "Architecture", "body": "Chrome user-data: ~/.openclaw/browser/openclaw/user-data\n ↕ shared cookies/login (mutually exclusive CDP)\n┌──────────────┐ ┌──────────────────┐\n│ browser tool │ OR │ Playwright script │\n│ (explore) │ │ (zero token) │\n└──────────────┘ └──────────────────┘\n ↕ managed by browser-lock.sh\n\nOnly one CDP client can connect at a time. browser-lock.sh handles the mutex." }, { "title": "Setup", "body": "Copy scripts/browser-lock.sh to your workspace scripts/ directory\nCopy scripts/utils/human-like.js to your workspace scripts/browser/utils/\nchmod +x scripts/browser-lock.sh\nCreate scripts/browser/ for your automation scripts" }, { "title": "1. Explore (browser tool, costs tokens)", "body": "Use the OpenClaw browser tool (snapshot/act) to figure out a workflow. Note selectors, page flow, key waits." }, { "title": "2. Record (write a Playwright script)", "body": "Convert steps into a script. Save to scripts/browser/-.js. Use the template pattern:\n\nconst { chromium } = require('playwright');\nconst { humanDelay, humanClick, humanType, humanThink, humanBrowse } = require('./utils/human-like');\n\nfunction discoverCdpUrl() {\n try {\n const { execSync } = require('child_process');\n const ps = execSync(\"ps aux | grep 'remote-debugging-port' | grep -v grep\", { encoding: 'utf8' });\n const match = ps.match(/remote-debugging-port=(\\d+)/);\n return `http://127.0.0.1:${match ? match[1] : '18800'}`;\n } catch { return 'http://127.0.0.1:18800'; }\n}\n\nasync function main() {\n const browser = await chromium.connectOverCDP(discoverCdpUrl());\n const context = browser.contexts()[0]; // reuse existing context (cookies/login)\n const page = await context.newPage();\n try {\n // automation here — use human-like functions\n await page.goto('https://example.com', { waitUntil: 'networkidle', timeout: 30000 });\n await humanBrowse(page); // simulate looking at the page\n await humanClick(page, 'button.submit');\n await humanType(page, 'input[name=\"title\"]', 'Hello World');\n } finally {\n await page.close(); // NEVER browser.close() — kills entire Chrome\n }\n}\nmain().then(() => process.exit(0)).catch(e => { console.error('❌', e.message); process.exit(1); });" }, { "title": "3. Replay (zero tokens)", "body": "./scripts/browser-lock.sh run scripts/browser/my-task.js [args]\n./scripts/browser-lock.sh run --timeout 120 scripts/browser/my-task.js" }, { "title": "4. Fix (on error)", "body": "Read script error output\nRe-explore the failing step with browser tool (snapshot) to check current UI\nUpdate script with corrected selectors/logic\nRetry\n\nNever guess fixes blindly. Always re-explore the actual page state." }, { "title": "browser-lock.sh", "body": "Manages CDP mutex between OpenClaw browser and Playwright scripts.\n\n./scripts/browser-lock.sh run [args] # acquire → run → release (300s default)\n./scripts/browser-lock.sh run --timeout 120