{ "schemaVersion": "1.0", "item": { "slug": "omni-research", "name": "Omni Research", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/lmanchu/omni-research", "canonicalUrl": "https://clawhub.ai/lmanchu/omni-research", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/omni-research", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=omni-research", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "browser.py", "requirements.txt", "research.py", "setup.py" ], "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/omni-research" }, "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/omni-research", "agentPageUrl": "https://openagent3.xyz/skills/omni-research/agent", "manifestUrl": "https://openagent3.xyz/skills/omni-research/agent.json", "briefUrl": "https://openagent3.xyz/skills/omni-research/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": "omni-research", "body": "Research any topic by querying multiple AI services through your own browser.\nNo API keys — uses your existing Perplexity Pro, X Premium, Gemini Advanced subscriptions." }, { "title": "How It Works", "body": "Connects to your running browser via CDP (Chrome DevTools Protocol)\nOpens parallel tabs to Perplexity, Grok, and Gemini (you're already logged in)\nSubmits your query, waits for response, extracts answer from each\nSynthesizes all results into a unified summary" }, { "title": "Prerequisites", "body": "Python 3.10+ with httpx and websockets\nChrome, Edge, or any Chromium browser running with CDP:\n# Add to your browser shortcut or launch command (one-time)\n--remote-debugging-port=9222\n\n\nLogged into your AI services in the browser" }, { "title": "Usage", "body": "# All browser sources (Perplexity + Grok + Gemini)\npython3 research.py \"AIPC market trends 2026\"\n\n# Specific sources\npython3 research.py --sources perplexity,grok \"topic\"\n\n# API-only mode (no browser needed)\npython3 research.py --sources gemini-api \"quick question\"\n\n# JSON output\npython3 research.py --json \"query\"" }, { "title": "Available Sources", "body": "SourceTypeRequiresperplexityBrowserPerplexity Pro logingrokBrowserX Premium / Grok logingeminiBrowserGoogle account logingemini-apiAPIOpenAI-compatible endpoint" }, { "title": "Configuration", "body": "Optional ~/.config/omni-research/config.json:\n\n{\n \"cdp_port\": 9222,\n \"cliproxy_url\": \"http://127.0.0.1:8317/v1\",\n \"cliproxy_key\": \"your-key\",\n \"synthesis_model\": \"glm-4.7\",\n \"gemini_api_model\": \"gemini-2.5-flash\"\n}" }, { "title": "Architecture", "body": "User's Browser (Chrome/Edge/Comet/Arc, CDP :9222)\n ├── Tab: perplexity.ai → user's Pro session\n ├── Tab: grok.com → user's Premium session\n └── Tab: gemini.google.com → user's Google session\n ↓ WebSocket (CDP Input.insertText + dispatchKeyEvent)\n BrowserBridge (browser.py — httpx + websockets)\n ↓ ← IrisGo runtime replaces this layer\n omni-research skill (parallel query + extract + synthesize)\n ↓\n Markdown output with per-source sections + synthesis" }, { "title": "For IrisGo", "body": "The BrowserBridge in browser.py is an abstract interface.\nCurrent implementation uses direct CDP via WebSocket.\nIrisGo runtime provides native browser APIs — just swap the bridge layer.\n\n# skill.json requirement\n{ \"requirements\": { \"tools\": [\"browser\"] } }" } ], "body": "omni-research\n\nResearch any topic by querying multiple AI services through your own browser. No API keys — uses your existing Perplexity Pro, X Premium, Gemini Advanced subscriptions.\n\nHow It Works\nConnects to your running browser via CDP (Chrome DevTools Protocol)\nOpens parallel tabs to Perplexity, Grok, and Gemini (you're already logged in)\nSubmits your query, waits for response, extracts answer from each\nSynthesizes all results into a unified summary\nPrerequisites\nPython 3.10+ with httpx and websockets\nChrome, Edge, or any Chromium browser running with CDP:\n# Add to your browser shortcut or launch command (one-time)\n--remote-debugging-port=9222\n\nLogged into your AI services in the browser\nUsage\n# All browser sources (Perplexity + Grok + Gemini)\npython3 research.py \"AIPC market trends 2026\"\n\n# Specific sources\npython3 research.py --sources perplexity,grok \"topic\"\n\n# API-only mode (no browser needed)\npython3 research.py --sources gemini-api \"quick question\"\n\n# JSON output\npython3 research.py --json \"query\"\n\nAvailable Sources\nSource\tType\tRequires\nperplexity\tBrowser\tPerplexity Pro login\ngrok\tBrowser\tX Premium / Grok login\ngemini\tBrowser\tGoogle account login\ngemini-api\tAPI\tOpenAI-compatible endpoint\nConfiguration\n\nOptional ~/.config/omni-research/config.json:\n\n{\n \"cdp_port\": 9222,\n \"cliproxy_url\": \"http://127.0.0.1:8317/v1\",\n \"cliproxy_key\": \"your-key\",\n \"synthesis_model\": \"glm-4.7\",\n \"gemini_api_model\": \"gemini-2.5-flash\"\n}\n\nArchitecture\nUser's Browser (Chrome/Edge/Comet/Arc, CDP :9222)\n ├── Tab: perplexity.ai → user's Pro session\n ├── Tab: grok.com → user's Premium session\n └── Tab: gemini.google.com → user's Google session\n ↓ WebSocket (CDP Input.insertText + dispatchKeyEvent)\n BrowserBridge (browser.py — httpx + websockets)\n ↓ ← IrisGo runtime replaces this layer\n omni-research skill (parallel query + extract + synthesize)\n ↓\n Markdown output with per-source sections + synthesis\n\nFor IrisGo\n\nThe BrowserBridge in browser.py is an abstract interface. Current implementation uses direct CDP via WebSocket. IrisGo runtime provides native browser APIs — just swap the bridge layer.\n\n# skill.json requirement\n{ \"requirements\": { \"tools\": [\"browser\"] } }" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/lmanchu/omni-research", "publisherUrl": "https://clawhub.ai/lmanchu/omni-research", "owner": "lmanchu", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/omni-research", "downloadUrl": "https://openagent3.xyz/downloads/omni-research", "agentUrl": "https://openagent3.xyz/skills/omni-research/agent", "manifestUrl": "https://openagent3.xyz/skills/omni-research/agent.json", "briefUrl": "https://openagent3.xyz/skills/omni-research/agent.md" } }