{ "schemaVersion": "1.0", "item": { "slug": "midscene-computer-chrome-bridge", "name": "Midscene Automations Skills for Browser with Bridge", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/quanru/midscene-computer-chrome-bridge", "canonicalUrl": "https://clawhub.ai/quanru/midscene-computer-chrome-bridge", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/midscene-computer-chrome-bridge", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=midscene-computer-chrome-bridge", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md" ], "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/midscene-computer-chrome-bridge" }, "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/midscene-computer-chrome-bridge", "agentPageUrl": "https://openagent3.xyz/skills/midscene-computer-chrome-bridge/agent", "manifestUrl": "https://openagent3.xyz/skills/midscene-computer-chrome-bridge/agent.json", "briefUrl": "https://openagent3.xyz/skills/midscene-computer-chrome-bridge/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": "Chrome Bridge Automation", "body": "CRITICAL RULES — VIOLATIONS WILL BREAK THE WORKFLOW:\n\nNever run midscene commands in the background. Each command must run synchronously so you can read its output (especially screenshots) before deciding the next action. Background execution breaks the screenshot-analyze-act loop.\nRun only one midscene command at a time. Wait for the previous command to finish, read the screenshot, then decide the next action. Never chain multiple commands together.\nAllow enough time for each command to complete. Midscene commands involve AI inference and screen interaction, which can take longer than typical shell commands. A typical command needs about 1 minute; complex act commands may need even longer.\nAlways report task results before finishing. After completing the automation task, you MUST proactively summarize the results to the user — including key data found, actions completed, screenshots taken, and any relevant findings. Never silently end after the last automation step; the user expects a complete response in a single interaction.\n\nAutomate the user's real Chrome browser via the Midscene Chrome Extension (Bridge mode), preserving cookies, sessions, and login state. You (the AI agent) act as the brain, deciding which actions to take based on screenshots." }, { "title": "Command Format", "body": "CRITICAL — Every command MUST follow this EXACT format. Do NOT modify the command prefix.\n\nnpx @midscene/web@1 --bridge [args]\n\n--bridge flag is MANDATORY here — it activates Bridge mode to connect to the user's desktop Chrome browser" }, { "title": "Prerequisites", "body": "The user has already prepared Chrome and the Midscene Extension. Do NOT check browser or extension status before connecting — just connect directly.\n\nMidscene requires models with strong visual grounding capabilities. The following environment variables must be configured — either as system environment variables or in a .env file in the current working directory (Midscene loads .env automatically):\n\nMIDSCENE_MODEL_API_KEY=\"your-api-key\"\nMIDSCENE_MODEL_NAME=\"model-name\"\nMIDSCENE_MODEL_BASE_URL=\"https://...\"\nMIDSCENE_MODEL_FAMILY=\"family-identifier\"\n\nExample: Gemini (Gemini-3-Flash)\n\nMIDSCENE_MODEL_API_KEY=\"your-google-api-key\"\nMIDSCENE_MODEL_NAME=\"gemini-3-flash\"\nMIDSCENE_MODEL_BASE_URL=\"https://generativelanguage.googleapis.com/v1beta/openai/\"\nMIDSCENE_MODEL_FAMILY=\"gemini\"\n\nExample: Qwen 3.5\n\nMIDSCENE_MODEL_API_KEY=\"your-aliyun-api-key\"\nMIDSCENE_MODEL_NAME=\"qwen3.5-plus\"\nMIDSCENE_MODEL_BASE_URL=\"https://dashscope.aliyuncs.com/compatible-mode/v1\"\nMIDSCENE_MODEL_FAMILY=\"qwen3.5\"\nMIDSCENE_MODEL_REASONING_ENABLED=\"false\"\n# If using OpenRouter, set:\n# MIDSCENE_MODEL_API_KEY=\"your-openrouter-api-key\"\n# MIDSCENE_MODEL_NAME=\"qwen/qwen3.5-plus\"\n# MIDSCENE_MODEL_BASE_URL=\"https://openrouter.ai/api/v1\"\n\nExample: Doubao Seed 2.0 Lite\n\nMIDSCENE_MODEL_API_KEY=\"your-doubao-api-key\"\nMIDSCENE_MODEL_NAME=\"doubao-seed-2-0-lite\"\nMIDSCENE_MODEL_BASE_URL=\"https://ark.cn-beijing.volces.com/api/v3\"\nMIDSCENE_MODEL_FAMILY=\"doubao-seed\"\n\nCommonly used models: Doubao Seed 2.0 Lite, Qwen 3.5, Zhipu GLM-4.6V, Gemini-3-Pro, Gemini-3-Flash.\n\nIf the model is not configured, ask the user to set it up. See Model Configuration for supported providers." }, { "title": "Connect to a Web Page", "body": "npx @midscene/web@1 --bridge connect --url https://example.com" }, { "title": "Take Screenshot", "body": "npx @midscene/web@1 --bridge take_screenshot\n\nAfter taking a screenshot, read the saved image file to understand the current page state before deciding the next action." }, { "title": "Perform Action", "body": "Use act to interact with the page and get the result. It autonomously handles all UI interactions internally — clicking, typing, scrolling, hovering, waiting, and navigating — so you should give it complex, high-level tasks as a whole rather than breaking them into small steps. Describe what you want to do and the desired effect in natural language:\n\n# specific instructions\nnpx @midscene/web@1 --bridge act --prompt \"click the Login button and fill in the email field with 'user@example.com'\"\nnpx @midscene/web@1 --bridge act --prompt \"scroll down and click the Submit button\"\n\n# or target-driven instructions\nnpx @midscene/web@1 --bridge act --prompt \"click the country dropdown and select Japan\"" }, { "title": "Disconnect", "body": "npx @midscene/web@1 --bridge disconnect" }, { "title": "Workflow Pattern", "body": "Bridge mode connects to the user's real Chrome browser. Each CLI command establishes its own temporary connection, but the browser, tabs, and all state (cookies, login sessions) are always preserved regardless of whether you disconnect. This makes reconnecting lightweight and lossless.\n\nFollow this pattern:\n\nConnect to a URL to establish a session\nTake screenshot to see the current state, make sure the page is loaded.\nExecute action using act to perform the desired action or target-driven instructions.\nReport results — summarize what was accomplished, present key findings and data extracted during the task, and list any generated files (screenshots, logs, etc.) with their paths\nDisconnect only when the user's overall task is fully complete. Do NOT disconnect if the user may have follow-up actions — keep the session available for continued interaction in subsequent conversation turns." }, { "title": "Best Practices", "body": "Always connect first: Navigate to the target URL with connect --url before any interaction.\nBe specific about UI elements: Instead of \"the button\", say \"the blue Submit button in the contact form\".\nUse natural language: Describe what you see on the page, not CSS selectors. Say \"the red Buy Now button\" instead of \"#buy-btn\".\nHandle loading states: After navigation or actions that trigger page loads, take a screenshot to verify the page has loaded.\nDisconnect only when fully done: Only disconnect when the user's overall task is completely finished and no follow-up actions are expected. In multi-turn conversations, skip the disconnect to allow continued browser interaction. Disconnecting is safe — it only closes the CLI-side bridge connection, not the browser or tabs — but reconnecting adds unnecessary overhead if the user wants to continue.\nNever run in background: Every midscene command must run synchronously — background execution breaks the screenshot-analyze-act loop.\nBatch related operations into a single act command: When performing consecutive operations within the same page, combine them into one act prompt instead of splitting them into separate commands. For example, \"fill in the email and password fields, then click the Login button\" should be a single act call, not three. This reduces round-trips, avoids unnecessary screenshot-analyze cycles, and is significantly faster.\nAlways report results after completion: After finishing the automation task, you MUST proactively present the results to the user without waiting for them to ask. This includes: (1) the answer to the user's original question or the outcome of the requested task, (2) key data extracted or observed during execution, (3) screenshots and other generated files with their paths, (4) a brief summary of steps taken. Do NOT silently finish after the last automation command — the user expects complete results in a single interaction.\n\nExample — Dropdown selection:\n\nnpx @midscene/web@1 --bridge act --prompt \"click the country dropdown and select Japan\"\nnpx @midscene/web@1 --bridge take_screenshot\n\nExample — Form interaction:\n\nnpx @midscene/web@1 --bridge act --prompt \"fill in the email field with 'user@example.com' and the password field with 'pass123', then click the Log In button\"\nnpx @midscene/web@1 --bridge take_screenshot" }, { "title": "Bridge Mode Connection Failures", "body": "Ask user to check if Chrome is open with the Midscene Extension installed and enabled.\nThe Midscene Extension can be installed from the Chrome Web Store: https://chromewebstore.google.com/detail/midscenejs/gbldofcpkknbggpkmbdaefngejllnief\nCheck that the 'bridge mode' indicator in the extension shows \"Listening\" status.\nSee the Bridge Mode documentation." }, { "title": "Timeouts", "body": "Web pages may take time to load. After connecting, take a screenshot to verify readiness before interacting.\nFor slow pages, wait briefly between steps." }, { "title": "Screenshots Not Displaying", "body": "The screenshot path is an absolute path to a local file. Use the Read tool to view it." } ], "body": "Chrome Bridge Automation\n\nCRITICAL RULES — VIOLATIONS WILL BREAK THE WORKFLOW:\n\nNever run midscene commands in the background. Each command must run synchronously so you can read its output (especially screenshots) before deciding the next action. Background execution breaks the screenshot-analyze-act loop.\nRun only one midscene command at a time. Wait for the previous command to finish, read the screenshot, then decide the next action. Never chain multiple commands together.\nAllow enough time for each command to complete. Midscene commands involve AI inference and screen interaction, which can take longer than typical shell commands. A typical command needs about 1 minute; complex act commands may need even longer.\nAlways report task results before finishing. After completing the automation task, you MUST proactively summarize the results to the user — including key data found, actions completed, screenshots taken, and any relevant findings. Never silently end after the last automation step; the user expects a complete response in a single interaction.\n\nAutomate the user's real Chrome browser via the Midscene Chrome Extension (Bridge mode), preserving cookies, sessions, and login state. You (the AI agent) act as the brain, deciding which actions to take based on screenshots.\n\nCommand Format\n\nCRITICAL — Every command MUST follow this EXACT format. Do NOT modify the command prefix.\n\nnpx @midscene/web@1 --bridge [args]\n\n--bridge flag is MANDATORY here — it activates Bridge mode to connect to the user's desktop Chrome browser\nPrerequisites\n\nThe user has already prepared Chrome and the Midscene Extension. Do NOT check browser or extension status before connecting — just connect directly.\n\nMidscene requires models with strong visual grounding capabilities. The following environment variables must be configured — either as system environment variables or in a .env file in the current working directory (Midscene loads .env automatically):\n\nMIDSCENE_MODEL_API_KEY=\"your-api-key\"\nMIDSCENE_MODEL_NAME=\"model-name\"\nMIDSCENE_MODEL_BASE_URL=\"https://...\"\nMIDSCENE_MODEL_FAMILY=\"family-identifier\"\n\n\nExample: Gemini (Gemini-3-Flash)\n\nMIDSCENE_MODEL_API_KEY=\"your-google-api-key\"\nMIDSCENE_MODEL_NAME=\"gemini-3-flash\"\nMIDSCENE_MODEL_BASE_URL=\"https://generativelanguage.googleapis.com/v1beta/openai/\"\nMIDSCENE_MODEL_FAMILY=\"gemini\"\n\n\nExample: Qwen 3.5\n\nMIDSCENE_MODEL_API_KEY=\"your-aliyun-api-key\"\nMIDSCENE_MODEL_NAME=\"qwen3.5-plus\"\nMIDSCENE_MODEL_BASE_URL=\"https://dashscope.aliyuncs.com/compatible-mode/v1\"\nMIDSCENE_MODEL_FAMILY=\"qwen3.5\"\nMIDSCENE_MODEL_REASONING_ENABLED=\"false\"\n# If using OpenRouter, set:\n# MIDSCENE_MODEL_API_KEY=\"your-openrouter-api-key\"\n# MIDSCENE_MODEL_NAME=\"qwen/qwen3.5-plus\"\n# MIDSCENE_MODEL_BASE_URL=\"https://openrouter.ai/api/v1\"\n\n\nExample: Doubao Seed 2.0 Lite\n\nMIDSCENE_MODEL_API_KEY=\"your-doubao-api-key\"\nMIDSCENE_MODEL_NAME=\"doubao-seed-2-0-lite\"\nMIDSCENE_MODEL_BASE_URL=\"https://ark.cn-beijing.volces.com/api/v3\"\nMIDSCENE_MODEL_FAMILY=\"doubao-seed\"\n\n\nCommonly used models: Doubao Seed 2.0 Lite, Qwen 3.5, Zhipu GLM-4.6V, Gemini-3-Pro, Gemini-3-Flash.\n\nIf the model is not configured, ask the user to set it up. See Model Configuration for supported providers.\n\nCommands\nConnect to a Web Page\nnpx @midscene/web@1 --bridge connect --url https://example.com\n\nTake Screenshot\nnpx @midscene/web@1 --bridge take_screenshot\n\n\nAfter taking a screenshot, read the saved image file to understand the current page state before deciding the next action.\n\nPerform Action\n\nUse act to interact with the page and get the result. It autonomously handles all UI interactions internally — clicking, typing, scrolling, hovering, waiting, and navigating — so you should give it complex, high-level tasks as a whole rather than breaking them into small steps. Describe what you want to do and the desired effect in natural language:\n\n# specific instructions\nnpx @midscene/web@1 --bridge act --prompt \"click the Login button and fill in the email field with 'user@example.com'\"\nnpx @midscene/web@1 --bridge act --prompt \"scroll down and click the Submit button\"\n\n# or target-driven instructions\nnpx @midscene/web@1 --bridge act --prompt \"click the country dropdown and select Japan\"\n\nDisconnect\nnpx @midscene/web@1 --bridge disconnect\n\nWorkflow Pattern\n\nBridge mode connects to the user's real Chrome browser. Each CLI command establishes its own temporary connection, but the browser, tabs, and all state (cookies, login sessions) are always preserved regardless of whether you disconnect. This makes reconnecting lightweight and lossless.\n\nFollow this pattern:\n\nConnect to a URL to establish a session\nTake screenshot to see the current state, make sure the page is loaded.\nExecute action using act to perform the desired action or target-driven instructions.\nReport results — summarize what was accomplished, present key findings and data extracted during the task, and list any generated files (screenshots, logs, etc.) with their paths\nDisconnect only when the user's overall task is fully complete. Do NOT disconnect if the user may have follow-up actions — keep the session available for continued interaction in subsequent conversation turns.\nBest Practices\nAlways connect first: Navigate to the target URL with connect --url before any interaction.\nBe specific about UI elements: Instead of \"the button\", say \"the blue Submit button in the contact form\".\nUse natural language: Describe what you see on the page, not CSS selectors. Say \"the red Buy Now button\" instead of \"#buy-btn\".\nHandle loading states: After navigation or actions that trigger page loads, take a screenshot to verify the page has loaded.\nDisconnect only when fully done: Only disconnect when the user's overall task is completely finished and no follow-up actions are expected. In multi-turn conversations, skip the disconnect to allow continued browser interaction. Disconnecting is safe — it only closes the CLI-side bridge connection, not the browser or tabs — but reconnecting adds unnecessary overhead if the user wants to continue.\nNever run in background: Every midscene command must run synchronously — background execution breaks the screenshot-analyze-act loop.\nBatch related operations into a single act command: When performing consecutive operations within the same page, combine them into one act prompt instead of splitting them into separate commands. For example, \"fill in the email and password fields, then click the Login button\" should be a single act call, not three. This reduces round-trips, avoids unnecessary screenshot-analyze cycles, and is significantly faster.\nAlways report results after completion: After finishing the automation task, you MUST proactively present the results to the user without waiting for them to ask. This includes: (1) the answer to the user's original question or the outcome of the requested task, (2) key data extracted or observed during execution, (3) screenshots and other generated files with their paths, (4) a brief summary of steps taken. Do NOT silently finish after the last automation command — the user expects complete results in a single interaction.\n\nExample — Dropdown selection:\n\nnpx @midscene/web@1 --bridge act --prompt \"click the country dropdown and select Japan\"\nnpx @midscene/web@1 --bridge take_screenshot\n\n\nExample — Form interaction:\n\nnpx @midscene/web@1 --bridge act --prompt \"fill in the email field with 'user@example.com' and the password field with 'pass123', then click the Log In button\"\nnpx @midscene/web@1 --bridge take_screenshot\n\nTroubleshooting\nBridge Mode Connection Failures\nAsk user to check if Chrome is open with the Midscene Extension installed and enabled.\nThe Midscene Extension can be installed from the Chrome Web Store: https://chromewebstore.google.com/detail/midscenejs/gbldofcpkknbggpkmbdaefngejllnief\nCheck that the 'bridge mode' indicator in the extension shows \"Listening\" status.\nSee the Bridge Mode documentation.\nTimeouts\nWeb pages may take time to load. After connecting, take a screenshot to verify readiness before interacting.\nFor slow pages, wait briefly between steps.\nScreenshots Not Displaying\nThe screenshot path is an absolute path to a local file. Use the Read tool to view it." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/quanru/midscene-computer-chrome-bridge", "publisherUrl": "https://clawhub.ai/quanru/midscene-computer-chrome-bridge", "owner": "quanru", "version": "1.0.3", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/midscene-computer-chrome-bridge", "downloadUrl": "https://openagent3.xyz/downloads/midscene-computer-chrome-bridge", "agentUrl": "https://openagent3.xyz/skills/midscene-computer-chrome-bridge/agent", "manifestUrl": "https://openagent3.xyz/skills/midscene-computer-chrome-bridge/agent.json", "briefUrl": "https://openagent3.xyz/skills/midscene-computer-chrome-bridge/agent.md" } }