{ "schemaVersion": "1.0", "item": { "slug": "eye2byte", "name": "Give eyes to your openclaw", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/wolverin0/eye2byte", "canonicalUrl": "https://clawhub.ai/wolverin0/eye2byte", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/eye2byte", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=eye2byte", "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", "slug": "eye2byte", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-03T19:27:20.267Z", "expiresAt": "2026-05-10T19:27:20.267Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=eye2byte", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=eye2byte", "contentDisposition": "attachment; filename=\"eye2byte-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "eye2byte" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/eye2byte" }, "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/eye2byte", "agentPageUrl": "https://openagent3.xyz/skills/eye2byte/agent", "manifestUrl": "https://openagent3.xyz/skills/eye2byte/agent.json", "briefUrl": "https://openagent3.xyz/skills/eye2byte/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": "Eye2byte — Screen Context for Your Agent", "body": "Eye2byte is an open-source MCP server (GitHub, PyPI) that lets you see the user's screen. Use these MCP tools only when the user explicitly asks you to look at something, debug a visual issue, or capture their screen." }, { "title": "Privacy & Data Storage", "body": "All data stays local. Captures are stored in ~/.eye2byte/output/ on the user's machine. Nothing is sent to external servers (except the vision model API the user configured).\nAuto-cleanup: Captures are deleted after N days (default: 7, configurable in settings). Set to 0 to disable.\nMCP token: When using SSE remote transport, the --token flag sets a bearer token stored only in the user's openclaw.json. Treat it like any API secret. The token is never logged or transmitted beyond the Authorization header.\nNo telemetry. Eye2byte collects zero analytics or usage data." }, { "title": "capture_and_summarize", "body": "Screenshot the user's screen and get a structured analysis.\n\nParameters:\n\nmode — \"full\" (default), \"window\", or \"region\"\nmonitor — 0 = active monitor (default), 1/2/3 = specific monitor, -1 = ALL monitors at once\ndelay — seconds to wait before capturing (useful for menus/tooltips)\nwindow_name — capture a specific app window by name (e.g., \"chrome\", \"code\")\n\nUse this when the user says things like \"look at my screen\", \"what do you see\", \"debug this\", or \"what's wrong here\"." }, { "title": "capture_with_voice", "body": "Screenshot + voice recording + transcription. Returns both visual analysis and what the user said.\n\nUse when the user wants to describe something verbally while showing their screen." }, { "title": "record_clip_and_summarize", "body": "Record a short screen clip, extract keyframes, and analyze the sequence.\n\nUse when the user wants to show you something that changes over time (animations, workflows, step sequences)." }, { "title": "summarize_screenshot", "body": "Analyze an existing image file. Pass a file path to get a structured analysis." }, { "title": "transcribe_audio", "body": "Local Whisper transcription of any audio file." }, { "title": "get_recent_context", "body": "Retrieve recent Context Pack summaries from previous captures.\n\nUse this to recall what you've seen recently without re-capturing." }, { "title": "What You Get Back", "body": "Every capture returns a structured Context Pack:\n\nGoal — what the user appears to be doing\nEnvironment — OS, editor, repo, branch, language\nScreen State — visible panels, files, terminal output\nSignals — verbatim errors, stack traces, warnings\nLikely Situation — what's probably happening\nSuggested Next Info — what you should ask or do next" }, { "title": "When to Use Eye2byte", "body": "User mentions something visual (\"this button is broken\", \"the layout is wrong\")\nUser asks you to \"look at\" or \"check\" something on their screen\nYou need to see error dialogs, UI bugs, or terminal output the user can't easily copy\nUser is debugging and visual context would help your diagnosis\nUser asks you to monitor or watch something\nYou want to verify your changes had the intended visual effect" }, { "title": "Multi-Monitor Tips", "body": "monitor=-1 captures ALL monitors stitched together — useful for seeing the full workspace\nmonitor=1, 2, 3 for targeting specific displays\nDefault (monitor=0) captures whichever monitor has the active window" }, { "title": "Setup", "body": "Eye2byte must be running on the machine whose screen you want to capture:\n\nLocal (same machine): Already configured if this skill loaded.\n\nRemote (different machine): The user runs eye2byte-mcp --sse --token on their local machine, and configures the MCP connection URL in openclaw.json." } ], "body": "Eye2byte — Screen Context for Your Agent\n\nEye2byte is an open-source MCP server (GitHub, PyPI) that lets you see the user's screen. Use these MCP tools only when the user explicitly asks you to look at something, debug a visual issue, or capture their screen.\n\nPrivacy & Data Storage\nAll data stays local. Captures are stored in ~/.eye2byte/output/ on the user's machine. Nothing is sent to external servers (except the vision model API the user configured).\nAuto-cleanup: Captures are deleted after N days (default: 7, configurable in settings). Set to 0 to disable.\nMCP token: When using SSE remote transport, the --token flag sets a bearer token stored only in the user's openclaw.json. Treat it like any API secret. The token is never logged or transmitted beyond the Authorization header.\nNo telemetry. Eye2byte collects zero analytics or usage data.\nAvailable MCP Tools\ncapture_and_summarize\n\nScreenshot the user's screen and get a structured analysis.\n\nParameters:\n\nmode — \"full\" (default), \"window\", or \"region\"\nmonitor — 0 = active monitor (default), 1/2/3 = specific monitor, -1 = ALL monitors at once\ndelay — seconds to wait before capturing (useful for menus/tooltips)\nwindow_name — capture a specific app window by name (e.g., \"chrome\", \"code\")\n\nUse this when the user says things like \"look at my screen\", \"what do you see\", \"debug this\", or \"what's wrong here\".\n\ncapture_with_voice\n\nScreenshot + voice recording + transcription. Returns both visual analysis and what the user said.\n\nUse when the user wants to describe something verbally while showing their screen.\n\nrecord_clip_and_summarize\n\nRecord a short screen clip, extract keyframes, and analyze the sequence.\n\nUse when the user wants to show you something that changes over time (animations, workflows, step sequences).\n\nsummarize_screenshot\n\nAnalyze an existing image file. Pass a file path to get a structured analysis.\n\ntranscribe_audio\n\nLocal Whisper transcription of any audio file.\n\nget_recent_context\n\nRetrieve recent Context Pack summaries from previous captures.\n\nUse this to recall what you've seen recently without re-capturing.\n\nWhat You Get Back\n\nEvery capture returns a structured Context Pack:\n\nGoal — what the user appears to be doing\nEnvironment — OS, editor, repo, branch, language\nScreen State — visible panels, files, terminal output\nSignals — verbatim errors, stack traces, warnings\nLikely Situation — what's probably happening\nSuggested Next Info — what you should ask or do next\n\nWhen to Use Eye2byte\nUser mentions something visual (\"this button is broken\", \"the layout is wrong\")\nUser asks you to \"look at\" or \"check\" something on their screen\nYou need to see error dialogs, UI bugs, or terminal output the user can't easily copy\nUser is debugging and visual context would help your diagnosis\nUser asks you to monitor or watch something\nYou want to verify your changes had the intended visual effect\nMulti-Monitor Tips\nmonitor=-1 captures ALL monitors stitched together — useful for seeing the full workspace\nmonitor=1, 2, 3 for targeting specific displays\nDefault (monitor=0) captures whichever monitor has the active window\nSetup\n\nEye2byte must be running on the machine whose screen you want to capture:\n\nLocal (same machine): Already configured if this skill loaded.\n\nRemote (different machine): The user runs eye2byte-mcp --sse --token on their local machine, and configures the MCP connection URL in openclaw.json." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/wolverin0/eye2byte", "publisherUrl": "https://clawhub.ai/wolverin0/eye2byte", "owner": "wolverin0", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/eye2byte", "downloadUrl": "https://openagent3.xyz/downloads/eye2byte", "agentUrl": "https://openagent3.xyz/skills/eye2byte/agent", "manifestUrl": "https://openagent3.xyz/skills/eye2byte/agent.json", "briefUrl": "https://openagent3.xyz/skills/eye2byte/agent.md" } }