{
  "schemaVersion": "1.0",
  "item": {
    "slug": "predicate-snapshot",
    "name": "Predicate Snapshot",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/rcholic/predicate-snapshot",
    "canonicalUrl": "https://clawhub.ai/rcholic/predicate-snapshot",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/predicate-snapshot",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=predicate-snapshot",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "demo/compare.ts",
      "demo/llm-action.ts",
      "demo/login-demo.ts",
      "docker-compose.yml"
    ],
    "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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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/predicate-snapshot"
    },
    "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/predicate-snapshot",
    "agentPageUrl": "https://openagent3.xyz/skills/predicate-snapshot/agent",
    "manifestUrl": "https://openagent3.xyz/skills/predicate-snapshot/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/predicate-snapshot/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Predicate Snapshot Engine",
        "body": "Replaces default browser snapshots with Predicate's ML-ranked DOM elements.\nReduces prompt token usage by 95% while preserving actionable elements."
      },
      {
        "title": "Why Use This?",
        "body": "ApproachTokensElementsSignal QualityAccessibility Tree (default)~18,000~800Low (noise)Predicate Snapshot~80050High (ranked)\n\nResult: Faster LLM inference, lower costs, fewer retries."
      },
      {
        "title": "Requirements",
        "body": "Node.js 18+\nPREDICATE_API_KEY environment variable (optional)\n\nWithout API key: Local heuristic-based pruning (~80% token reduction)\nWith API key: ML-powered ranking for cleaner output (~95% token reduction, less noise)\n\nGet your free API key at predicate.systems/keys"
      },
      {
        "title": "Installation",
        "body": "npx clawdhub@latest install predicate-snapshot\n\nOr manually:\n\ngit clone https://github.com/predicate-systems/predicate-snapshot-skill ~/.openclaw/skills/predicate-snapshot\ncd ~/.openclaw/skills/predicate-snapshot && npm install && npm run build"
      },
      {
        "title": "Configuration",
        "body": "For enhanced ML-powered ranking, set your API key:\n\nexport PREDICATE_API_KEY=\"sk-...\"\n\nOr configure in ~/.openclaw/config.yaml:\n\nskills:\n  predicate-snapshot:\n    api_key: \"sk-...\"\n    # Optional: set usage limits\n    max_credits_per_session: 100"
      },
      {
        "title": "/predicate-snapshot",
        "body": "Capture a pruned DOM snapshot optimized for LLM consumption.\n\n/predicate-snapshot [--limit=50] [--include-ordinal]\n\nOptions:\n\n--limit=N - Maximum elements to return (default: 50)\n--include-ordinal - Include ordinal ranking for list items\n\nOutput format:\n\nID|role|text|imp|is_primary|docYq|ord|DG|href\n42|button|Add to Cart|0.95|true|320|1|cart-actions|\n15|button|Buy Now|0.92|true|340|2|cart-actions|\n23|link|Product Details|0.78|false|400|0||/dp/..."
      },
      {
        "title": "/predicate-act",
        "body": "Execute an action on an element by its Predicate ID.\n\n/predicate-act <action> <element_id> [value]\n\nExamples:\n\n# Click element 42\n/predicate-act click 42\n\n# Type into element 15\n/predicate-act type 15 \"search query\"\n\n# Scroll to element 23\n/predicate-act scroll 23"
      },
      {
        "title": "/predicate-snapshot-local",
        "body": "Local-only snapshot without ML re-ranking (free, lower accuracy).\n\n/predicate-snapshot-local [--limit=50]\n\nUse this for development or when you don't need ML-powered ranking."
      },
      {
        "title": "Example Workflow",
        "body": "1. Navigate to page\n2. /predicate-snapshot          # Get ranked elements\n3. /predicate-act click 42      # Click \"Add to Cart\" (element 42)\n4. /predicate-snapshot          # Refresh snapshot\n5. Verify cart updated"
      },
      {
        "title": "Pricing",
        "body": "TierCredits/MonthPriceHobby500FreeBuilder20,000$19/moPro40,000$49/moTeams120,000$149/moEnterpriseCustomContact us\n\nEach snapshot consumes 1 credit. Local snapshots are free."
      },
      {
        "title": "Comparison: Before & After",
        "body": "Before (Accessibility Tree):\n\n@e1 navigation \"Skip to main content\"\n@e2 link \"Amazon\"\n@e3 search \"Search Amazon\"\n... (800+ elements)\n@e742 button \"Add to Cart\"  <-- buried in noise\n... (more elements)\n\nAfter (Predicate Snapshot):\n\nID|role|text|imp|is_primary|docYq|ord|DG|href\n42|button|Add to Cart|0.98|true|520|1|cart-actions|  <-- ranked #1\n15|button|Buy Now|0.95|true|540|2|cart-actions|\n23|link|See All Buying...|0.72|false|560|3|cart-actions|"
      },
      {
        "title": "Support",
        "body": "Documentation: predicatesystems.ai/docs\nIssues: GitHub Issues\nDiscord: Predicate Community"
      }
    ],
    "body": "Predicate Snapshot Engine\n\nReplaces default browser snapshots with Predicate's ML-ranked DOM elements. Reduces prompt token usage by 95% while preserving actionable elements.\n\nWhy Use This?\nApproach\tTokens\tElements\tSignal Quality\nAccessibility Tree (default)\t~18,000\t~800\tLow (noise)\nPredicate Snapshot\t~800\t50\tHigh (ranked)\n\nResult: Faster LLM inference, lower costs, fewer retries.\n\nRequirements\nNode.js 18+\nPREDICATE_API_KEY environment variable (optional)\n\nWithout API key: Local heuristic-based pruning (~80% token reduction) With API key: ML-powered ranking for cleaner output (~95% token reduction, less noise)\n\nGet your free API key at predicate.systems/keys\n\nInstallation\nnpx clawdhub@latest install predicate-snapshot\n\n\nOr manually:\n\ngit clone https://github.com/predicate-systems/predicate-snapshot-skill ~/.openclaw/skills/predicate-snapshot\ncd ~/.openclaw/skills/predicate-snapshot && npm install && npm run build\n\nConfiguration\n\nFor enhanced ML-powered ranking, set your API key:\n\nexport PREDICATE_API_KEY=\"sk-...\"\n\n\nOr configure in ~/.openclaw/config.yaml:\n\nskills:\n  predicate-snapshot:\n    api_key: \"sk-...\"\n    # Optional: set usage limits\n    max_credits_per_session: 100\n\nUsage\n/predicate-snapshot\n\nCapture a pruned DOM snapshot optimized for LLM consumption.\n\n/predicate-snapshot [--limit=50] [--include-ordinal]\n\n\nOptions:\n\n--limit=N - Maximum elements to return (default: 50)\n--include-ordinal - Include ordinal ranking for list items\n\nOutput format:\n\nID|role|text|imp|is_primary|docYq|ord|DG|href\n42|button|Add to Cart|0.95|true|320|1|cart-actions|\n15|button|Buy Now|0.92|true|340|2|cart-actions|\n23|link|Product Details|0.78|false|400|0||/dp/...\n\n/predicate-act\n\nExecute an action on an element by its Predicate ID.\n\n/predicate-act <action> <element_id> [value]\n\n\nExamples:\n\n# Click element 42\n/predicate-act click 42\n\n# Type into element 15\n/predicate-act type 15 \"search query\"\n\n# Scroll to element 23\n/predicate-act scroll 23\n\n/predicate-snapshot-local\n\nLocal-only snapshot without ML re-ranking (free, lower accuracy).\n\n/predicate-snapshot-local [--limit=50]\n\n\nUse this for development or when you don't need ML-powered ranking.\n\nExample Workflow\n1. Navigate to page\n2. /predicate-snapshot          # Get ranked elements\n3. /predicate-act click 42      # Click \"Add to Cart\" (element 42)\n4. /predicate-snapshot          # Refresh snapshot\n5. Verify cart updated\n\nPricing\nTier\tCredits/Month\tPrice\nHobby\t500\tFree\nBuilder\t20,000\t$19/mo\nPro\t40,000\t$49/mo\nTeams\t120,000\t$149/mo\nEnterprise\tCustom\tContact us\n\nEach snapshot consumes 1 credit. Local snapshots are free.\n\nComparison: Before & After\n\nBefore (Accessibility Tree):\n\n@e1 navigation \"Skip to main content\"\n@e2 link \"Amazon\"\n@e3 search \"Search Amazon\"\n... (800+ elements)\n@e742 button \"Add to Cart\"  <-- buried in noise\n... (more elements)\n\n\nAfter (Predicate Snapshot):\n\nID|role|text|imp|is_primary|docYq|ord|DG|href\n42|button|Add to Cart|0.98|true|520|1|cart-actions|  <-- ranked #1\n15|button|Buy Now|0.95|true|540|2|cart-actions|\n23|link|See All Buying...|0.72|false|560|3|cart-actions|\n\nSupport\nDocumentation: predicatesystems.ai/docs\nIssues: GitHub Issues\nDiscord: Predicate Community"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/rcholic/predicate-snapshot",
    "publisherUrl": "https://clawhub.ai/rcholic/predicate-snapshot",
    "owner": "rcholic",
    "version": "0.4.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/predicate-snapshot",
    "downloadUrl": "https://openagent3.xyz/downloads/predicate-snapshot",
    "agentUrl": "https://openagent3.xyz/skills/predicate-snapshot/agent",
    "manifestUrl": "https://openagent3.xyz/skills/predicate-snapshot/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/predicate-snapshot/agent.md"
  }
}