{
  "schemaVersion": "1.0",
  "item": {
    "slug": "ui-element-ops",
    "name": "UI Element Ops",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/murongg/ui-element-ops",
    "canonicalUrl": "https://clawhub.ai/murongg/ui-element-ops",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/ui-element-ops",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ui-element-ops",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/run_parse_ui.sh",
      "scripts/operate_ui.py",
      "scripts/bootstrap_omniparser_env.sh",
      "scripts/parse_ui.py",
      "scripts/capture_and_parse.sh"
    ],
    "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/ui-element-ops"
    },
    "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/ui-element-ops",
    "agentPageUrl": "https://openagent3.xyz/skills/ui-element-ops/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ui-element-ops/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ui-element-ops/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": "UI Element Ops",
        "body": "Parse one or more screenshots into a machine-readable JSON schema with:\n\ntype (normalized UI element type)\nbbox_px and bbox_norm\ntext (OCR/caption content when available)\nclickable flag\noptional overlay image with labeled boxes\ndesktop actions via scripts/operate_ui.py (click/type/key/hotkey/screenshot)\nelement query and orchestration via scripts/operate_ui.py (find, wait)\ncoordinate calibration profile for multi-display/DPI/window offset (calibrate)"
      },
      {
        "title": "Quick Start",
        "body": "Prepare runtime once per machine:\n\nskills/ui-element-ops/scripts/bootstrap_omniparser_env.sh \"$PWD\"\n\nParse one screenshot:\n\nskills/ui-element-ops/scripts/run_parse_ui.sh /abs/path/to/1.jpeg\n\nRead outputs:\n\n<image>.elements.json\n<image>.overlay.png\n\nOne-step capture + parse with randomized names:\n\nskills/ui-element-ops/scripts/capture_and_parse.sh"
      },
      {
        "title": "Workflow",
        "body": "Confirm screenshot path and desired output path.\nRun scripts/bootstrap_omniparser_env.sh when .venv or OmniParser weights are missing.\nRun scripts/run_parse_ui.sh for standard parsing.\nReport absolute output paths and summary counts: total, clickable, by_type.\nCall out obvious quality risks for tiny text or dense icon layouts.\nExecute desktop actions when requested:\n\nlist elements: python3 skills/ui-element-ops/scripts/operate_ui.py list --elements <json>\nfind elements: python3 skills/ui-element-ops/scripts/operate_ui.py find --elements <json> --type button --text-contains login\nwait for appear/disappear: python3 skills/ui-element-ops/scripts/operate_ui.py wait --elements <json> --state appear --text-contains continue\nclick by id: python3 skills/ui-element-ops/scripts/operate_ui.py click --elements <json> --id e_0001\nscreenshot: python3 skills/ui-element-ops/scripts/operate_ui.py screenshot (defaults to user tmp dir)\ncalibrate coordinates: python3 skills/ui-element-ops/scripts/operate_ui.py calibrate --parsed-size <w> <h> --actual-size <w> <h>"
      },
      {
        "title": "Tunables",
        "body": "Edit type mapping keywords in references/type_rules.example.json.\nUse advanced parser args via scripts/parse_ui.py --help.\nUse --use-paddleocr only when paddleocr/paddlepaddle are installed."
      },
      {
        "title": "Outputs",
        "body": "Main JSON output:\n\nschema_version, pipeline, image, counts, elements\neach element has id, type, bbox_px, bbox_norm, text, clickable\n\n\nOverlay PNG output:\n\nsame screenshot with labeled detection boxes"
      },
      {
        "title": "Failure Handling",
        "body": "Missing dependencies or weights: run bootstrap script again.\nPermission/cache errors under $HOME: keep temporary caches under /tmp (handled by run script).\nCPU-only machine: expect slower inference.\nPerformance note: parse/capture-and-parse commands are heavy; avoid very tight loops and reuse recent elements.json when possible.\nHeadless environment limitation:\n\nusable without GUI: parse/list/find/wait/calibrate on existing files.\nrequires GUI session: click/click-xy/type/key/hotkey/screenshot/screen-info."
      }
    ],
    "body": "UI Element Ops\n\nParse one or more screenshots into a machine-readable JSON schema with:\n\ntype (normalized UI element type)\nbbox_px and bbox_norm\ntext (OCR/caption content when available)\nclickable flag\noptional overlay image with labeled boxes\ndesktop actions via scripts/operate_ui.py (click/type/key/hotkey/screenshot)\nelement query and orchestration via scripts/operate_ui.py (find, wait)\ncoordinate calibration profile for multi-display/DPI/window offset (calibrate)\nQuick Start\nPrepare runtime once per machine:\nskills/ui-element-ops/scripts/bootstrap_omniparser_env.sh \"$PWD\"\n\nParse one screenshot:\nskills/ui-element-ops/scripts/run_parse_ui.sh /abs/path/to/1.jpeg\n\nRead outputs:\n<image>.elements.json\n<image>.overlay.png\nOne-step capture + parse with randomized names:\nskills/ui-element-ops/scripts/capture_and_parse.sh\n\nWorkflow\nConfirm screenshot path and desired output path.\nRun scripts/bootstrap_omniparser_env.sh when .venv or OmniParser weights are missing.\nRun scripts/run_parse_ui.sh for standard parsing.\nReport absolute output paths and summary counts: total, clickable, by_type.\nCall out obvious quality risks for tiny text or dense icon layouts.\nExecute desktop actions when requested:\nlist elements: python3 skills/ui-element-ops/scripts/operate_ui.py list --elements <json>\nfind elements: python3 skills/ui-element-ops/scripts/operate_ui.py find --elements <json> --type button --text-contains login\nwait for appear/disappear: python3 skills/ui-element-ops/scripts/operate_ui.py wait --elements <json> --state appear --text-contains continue\nclick by id: python3 skills/ui-element-ops/scripts/operate_ui.py click --elements <json> --id e_0001\nscreenshot: python3 skills/ui-element-ops/scripts/operate_ui.py screenshot (defaults to user tmp dir)\ncalibrate coordinates: python3 skills/ui-element-ops/scripts/operate_ui.py calibrate --parsed-size <w> <h> --actual-size <w> <h>\nTunables\nEdit type mapping keywords in references/type_rules.example.json.\nUse advanced parser args via scripts/parse_ui.py --help.\nUse --use-paddleocr only when paddleocr/paddlepaddle are installed.\nOutputs\nMain JSON output:\nschema_version, pipeline, image, counts, elements\neach element has id, type, bbox_px, bbox_norm, text, clickable\nOverlay PNG output:\nsame screenshot with labeled detection boxes\nFailure Handling\nMissing dependencies or weights: run bootstrap script again.\nPermission/cache errors under $HOME: keep temporary caches under /tmp (handled by run script).\nCPU-only machine: expect slower inference.\nPerformance note: parse/capture-and-parse commands are heavy; avoid very tight loops and reuse recent elements.json when possible.\nHeadless environment limitation:\nusable without GUI: parse/list/find/wait/calibrate on existing files.\nrequires GUI session: click/click-xy/type/key/hotkey/screenshot/screen-info."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/murongg/ui-element-ops",
    "publisherUrl": "https://clawhub.ai/murongg/ui-element-ops",
    "owner": "murongg",
    "version": "1.0.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/ui-element-ops",
    "downloadUrl": "https://openagent3.xyz/downloads/ui-element-ops",
    "agentUrl": "https://openagent3.xyz/skills/ui-element-ops/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ui-element-ops/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ui-element-ops/agent.md"
  }
}