{
  "schemaVersion": "1.0",
  "item": {
    "slug": "humanize-ai",
    "name": "Humanize AI",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/artur-zhdan/humanize-ai",
    "canonicalUrl": "https://clawhub.ai/artur-zhdan/humanize-ai",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/humanize-ai",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=humanize-ai",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/humanize.py",
      "scripts/patterns.json",
      "scripts/analyze.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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/humanize-ai"
    },
    "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/humanize-ai",
    "agentPageUrl": "https://openagent3.xyz/skills/humanize-ai/agent",
    "manifestUrl": "https://openagent3.xyz/skills/humanize-ai/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/humanize-ai/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": "Humanize CLI",
        "body": "Command-line tools for detecting and auto-fixing AI writing patterns."
      },
      {
        "title": "analyze.py — Detect AI Patterns",
        "body": "Scans text and reports AI vocabulary, puffery, chatbot artifacts, and auto-replaceable phrases.\n\n# Analyze a file\npython scripts/analyze.py input.txt\n\n# Analyze from stdin\necho \"This serves as a testament to our commitment\" | python scripts/analyze.py\n\n# JSON output for programmatic use\npython scripts/analyze.py input.txt --json\n\nOutput example:\n\n==================================================\nAI PATTERN ANALYSIS - 5 issues found\n==================================================\n\nAI VOCABULARY:\n  • testament: 1x\n  • crucial: 2x\n\nAUTO-REPLACEABLE:\n  • \"serves as\" → \"is\": 1x\n  • \"in order to\" → \"to\": 1x"
      },
      {
        "title": "humanize.py — Auto-Replace Patterns",
        "body": "Performs automatic replacements for common AI-isms.\n\n# Humanize and print to stdout\npython scripts/humanize.py input.txt\n\n# Write to output file\npython scripts/humanize.py input.txt -o output.txt\n\n# Include em dash replacement\npython scripts/humanize.py input.txt --fix-dashes\n\n# Quiet mode (no change log)\npython scripts/humanize.py input.txt -q\n\nWhat it fixes automatically:\n\nFiller phrases: \"in order to\" → \"to\", \"due to the fact that\" → \"because\"\nCopula avoidance: \"serves as\" → \"is\", \"boasts\" → \"has\"\nSentence starters: removes \"Additionally,\", \"Furthermore,\", \"Moreover,\"\nCurly quotes → straight quotes\nChatbot artifacts: removes \"I hope this helps\", \"Let me know if\", etc."
      },
      {
        "title": "Workflow",
        "body": "Analyze first to see what needs fixing:\npython scripts/analyze.py document.txt\n\n\n\nAuto-fix safe replacements:\npython scripts/humanize.py document.txt -o document_clean.txt\n\n\n\nManual review for AI vocabulary and puffery flagged by analyze (these require human judgment)\n\n\nRe-analyze to confirm improvements:\npython scripts/analyze.py document_clean.txt"
      },
      {
        "title": "Customizing Patterns",
        "body": "Edit scripts/patterns.json to add/remove:\n\nai_words — vocabulary that flags but doesn't auto-replace\npuffery — promotional language to flag\nreplacements — phrase → replacement mappings (empty string = delete)\nchatbot_artifacts — phrases to auto-remove\nhedging_phrases — excessive hedging to flag"
      },
      {
        "title": "Batch Processing",
        "body": "Process multiple files:\n\n# Analyze all markdown files\nfor f in *.md; do\n  echo \"=== $f ===\" \n  python scripts/analyze.py \"$f\"\ndone\n\n# Humanize all txt files in place\nfor f in *.txt; do\n  python scripts/humanize.py \"$f\" -o \"$f.tmp\" && mv \"$f.tmp\" \"$f\"\ndone"
      }
    ],
    "body": "Humanize CLI\n\nCommand-line tools for detecting and auto-fixing AI writing patterns.\n\nScripts\nanalyze.py — Detect AI Patterns\n\nScans text and reports AI vocabulary, puffery, chatbot artifacts, and auto-replaceable phrases.\n\n# Analyze a file\npython scripts/analyze.py input.txt\n\n# Analyze from stdin\necho \"This serves as a testament to our commitment\" | python scripts/analyze.py\n\n# JSON output for programmatic use\npython scripts/analyze.py input.txt --json\n\n\nOutput example:\n\n==================================================\nAI PATTERN ANALYSIS - 5 issues found\n==================================================\n\nAI VOCABULARY:\n  • testament: 1x\n  • crucial: 2x\n\nAUTO-REPLACEABLE:\n  • \"serves as\" → \"is\": 1x\n  • \"in order to\" → \"to\": 1x\n\nhumanize.py — Auto-Replace Patterns\n\nPerforms automatic replacements for common AI-isms.\n\n# Humanize and print to stdout\npython scripts/humanize.py input.txt\n\n# Write to output file\npython scripts/humanize.py input.txt -o output.txt\n\n# Include em dash replacement\npython scripts/humanize.py input.txt --fix-dashes\n\n# Quiet mode (no change log)\npython scripts/humanize.py input.txt -q\n\n\nWhat it fixes automatically:\n\nFiller phrases: \"in order to\" → \"to\", \"due to the fact that\" → \"because\"\nCopula avoidance: \"serves as\" → \"is\", \"boasts\" → \"has\"\nSentence starters: removes \"Additionally,\", \"Furthermore,\", \"Moreover,\"\nCurly quotes → straight quotes\nChatbot artifacts: removes \"I hope this helps\", \"Let me know if\", etc.\nWorkflow\n\nAnalyze first to see what needs fixing:\n\npython scripts/analyze.py document.txt\n\n\nAuto-fix safe replacements:\n\npython scripts/humanize.py document.txt -o document_clean.txt\n\n\nManual review for AI vocabulary and puffery flagged by analyze (these require human judgment)\n\nRe-analyze to confirm improvements:\n\npython scripts/analyze.py document_clean.txt\n\nCustomizing Patterns\n\nEdit scripts/patterns.json to add/remove:\n\nai_words — vocabulary that flags but doesn't auto-replace\npuffery — promotional language to flag\nreplacements — phrase → replacement mappings (empty string = delete)\nchatbot_artifacts — phrases to auto-remove\nhedging_phrases — excessive hedging to flag\nBatch Processing\n\nProcess multiple files:\n\n# Analyze all markdown files\nfor f in *.md; do\n  echo \"=== $f ===\" \n  python scripts/analyze.py \"$f\"\ndone\n\n# Humanize all txt files in place\nfor f in *.txt; do\n  python scripts/humanize.py \"$f\" -o \"$f.tmp\" && mv \"$f.tmp\" \"$f\"\ndone"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/artur-zhdan/humanize-ai",
    "publisherUrl": "https://clawhub.ai/artur-zhdan/humanize-ai",
    "owner": "artur-zhdan",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/humanize-ai",
    "downloadUrl": "https://openagent3.xyz/downloads/humanize-ai",
    "agentUrl": "https://openagent3.xyz/skills/humanize-ai/agent",
    "manifestUrl": "https://openagent3.xyz/skills/humanize-ai/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/humanize-ai/agent.md"
  }
}