{
  "schemaVersion": "1.0",
  "item": {
    "slug": "humanize-ai-text",
    "name": "Humanize AI text",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/moltbro/humanize-ai-text",
    "canonicalUrl": "https://clawhub.ai/moltbro/humanize-ai-text",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/humanize-ai-text",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=humanize-ai-text",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/transform.py",
      "scripts/patterns.json",
      "scripts/detect.py",
      "scripts/compare.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-text"
    },
    "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-text",
    "agentPageUrl": "https://openagent3.xyz/skills/humanize-ai-text/agent",
    "manifestUrl": "https://openagent3.xyz/skills/humanize-ai-text/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/humanize-ai-text/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 AI Text",
        "body": "Comprehensive CLI for detecting and transforming AI-generated text to bypass detectors. Based on Wikipedia's Signs of AI Writing."
      },
      {
        "title": "Quick Start",
        "body": "# Detect AI patterns\npython scripts/detect.py text.txt\n\n# Transform to human-like\npython scripts/transform.py text.txt -o clean.txt\n\n# Compare before/after\npython scripts/compare.py text.txt -o clean.txt"
      },
      {
        "title": "Detection Categories",
        "body": "The analyzer checks for 16 pattern categories from Wikipedia's guide:"
      },
      {
        "title": "Critical (Immediate AI Detection)",
        "body": "CategoryExamplesCitation Bugsoaicite, turn0search, contentReferenceKnowledge Cutoff\"as of my last training\", \"based on available information\"Chatbot Artifacts\"I hope this helps\", \"Great question!\", \"As an AI\"Markdown**bold**, ## headers, code blocks"
      },
      {
        "title": "High Signal",
        "body": "CategoryExamplesAI Vocabularydelve, tapestry, landscape, pivotal, underscore, fosterSignificance Inflation\"serves as a testament\", \"pivotal moment\", \"indelible mark\"Promotional Languagevibrant, groundbreaking, nestled, breathtakingCopula Avoidance\"serves as\" instead of \"is\", \"boasts\" instead of \"has\""
      },
      {
        "title": "Medium Signal",
        "body": "CategoryExamplesSuperficial -ing\"highlighting the importance\", \"fostering collaboration\"Filler Phrases\"in order to\", \"due to the fact that\", \"Additionally,\"Vague Attributions\"experts believe\", \"industry reports suggest\"Challenges Formula\"Despite these challenges\", \"Future outlook\""
      },
      {
        "title": "Style Signal",
        "body": "CategoryExamplesCurly Quotes\"\" instead of \"\" (ChatGPT signature)Em Dash OveruseExcessive use of — for emphasisNegative Parallelisms\"Not only... but also\", \"It's not just... it's\"Rule of ThreeForced triplets like \"innovation, inspiration, and insight\""
      },
      {
        "title": "detect.py — Scan for AI Patterns",
        "body": "python scripts/detect.py essay.txt\npython scripts/detect.py essay.txt -j  # JSON output\npython scripts/detect.py essay.txt -s  # score only\necho \"text\" | python scripts/detect.py\n\nOutput:\n\nIssue count and word count\nAI probability (low/medium/high/very high)\nBreakdown by category\nAuto-fixable patterns marked"
      },
      {
        "title": "transform.py — Rewrite Text",
        "body": "python scripts/transform.py essay.txt\npython scripts/transform.py essay.txt -o output.txt\npython scripts/transform.py essay.txt -a  # aggressive\npython scripts/transform.py essay.txt -q  # quiet\n\nAuto-fixes:\n\nCitation bugs (oaicite, turn0search)\nMarkdown (**, ##, ```)\nChatbot sentences\nCopula avoidance → \"is/has\"\nFiller phrases → simpler forms\nCurly → straight quotes\n\nAggressive (-a):\n\nSimplifies -ing clauses\nReduces em dashes"
      },
      {
        "title": "compare.py — Before/After Analysis",
        "body": "python scripts/compare.py essay.txt\npython scripts/compare.py essay.txt -a -o clean.txt\n\nShows side-by-side detection scores before and after transformation"
      },
      {
        "title": "Workflow",
        "body": "Scan for detection risk:\npython scripts/detect.py document.txt\n\n\n\nTransform with comparison:\npython scripts/compare.py document.txt -o document_v2.txt\n\n\n\nVerify improvement:\npython scripts/detect.py document_v2.txt -s\n\n\n\nManual review for AI vocabulary and promotional language (requires judgment)"
      },
      {
        "title": "AI Probability Scoring",
        "body": "RatingCriteriaVery HighCitation bugs, knowledge cutoff, or chatbot artifacts presentHigh>30 issues OR >5% issue densityMedium>15 issues OR >2% issue densityLow<15 issues AND <2% density"
      },
      {
        "title": "Customizing Patterns",
        "body": "Edit scripts/patterns.json to add/modify:\n\nai_vocabulary — words to flag\nsignificance_inflation — puffery phrases\npromotional_language — marketing speak\ncopula_avoidance — phrase → replacement\nfiller_replacements — phrase → simpler form\nchatbot_artifacts — phrases triggering sentence removal"
      },
      {
        "title": "Batch Processing",
        "body": "# Scan all files\nfor f in *.txt; do\n  echo \"=== $f ===\"\n  python scripts/detect.py \"$f\" -s\ndone\n\n# Transform all markdown\nfor f in *.md; do\n  python scripts/transform.py \"$f\" -a -o \"${f%.md}_clean.md\" -q\ndone"
      },
      {
        "title": "Reference",
        "body": "Based on Wikipedia's Signs of AI Writing, maintained by WikiProject AI Cleanup. Patterns documented from thousands of AI-generated text examples.\n\nKey insight: \"LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases.\""
      }
    ],
    "body": "Humanize AI Text\n\nComprehensive CLI for detecting and transforming AI-generated text to bypass detectors. Based on Wikipedia's Signs of AI Writing.\n\nQuick Start\n# Detect AI patterns\npython scripts/detect.py text.txt\n\n# Transform to human-like\npython scripts/transform.py text.txt -o clean.txt\n\n# Compare before/after\npython scripts/compare.py text.txt -o clean.txt\n\nDetection Categories\n\nThe analyzer checks for 16 pattern categories from Wikipedia's guide:\n\nCritical (Immediate AI Detection)\nCategory\tExamples\nCitation Bugs\toaicite, turn0search, contentReference\nKnowledge Cutoff\t\"as of my last training\", \"based on available information\"\nChatbot Artifacts\t\"I hope this helps\", \"Great question!\", \"As an AI\"\nMarkdown\t**bold**, ## headers, code blocks\nHigh Signal\nCategory\tExamples\nAI Vocabulary\tdelve, tapestry, landscape, pivotal, underscore, foster\nSignificance Inflation\t\"serves as a testament\", \"pivotal moment\", \"indelible mark\"\nPromotional Language\tvibrant, groundbreaking, nestled, breathtaking\nCopula Avoidance\t\"serves as\" instead of \"is\", \"boasts\" instead of \"has\"\nMedium Signal\nCategory\tExamples\nSuperficial -ing\t\"highlighting the importance\", \"fostering collaboration\"\nFiller Phrases\t\"in order to\", \"due to the fact that\", \"Additionally,\"\nVague Attributions\t\"experts believe\", \"industry reports suggest\"\nChallenges Formula\t\"Despite these challenges\", \"Future outlook\"\nStyle Signal\nCategory\tExamples\nCurly Quotes\t\"\" instead of \"\" (ChatGPT signature)\nEm Dash Overuse\tExcessive use of — for emphasis\nNegative Parallelisms\t\"Not only... but also\", \"It's not just... it's\"\nRule of Three\tForced triplets like \"innovation, inspiration, and insight\"\nScripts\ndetect.py — Scan for AI Patterns\npython scripts/detect.py essay.txt\npython scripts/detect.py essay.txt -j  # JSON output\npython scripts/detect.py essay.txt -s  # score only\necho \"text\" | python scripts/detect.py\n\n\nOutput:\n\nIssue count and word count\nAI probability (low/medium/high/very high)\nBreakdown by category\nAuto-fixable patterns marked\ntransform.py — Rewrite Text\npython scripts/transform.py essay.txt\npython scripts/transform.py essay.txt -o output.txt\npython scripts/transform.py essay.txt -a  # aggressive\npython scripts/transform.py essay.txt -q  # quiet\n\n\nAuto-fixes:\n\nCitation bugs (oaicite, turn0search)\nMarkdown (**, ##, ```)\nChatbot sentences\nCopula avoidance → \"is/has\"\nFiller phrases → simpler forms\nCurly → straight quotes\n\nAggressive (-a):\n\nSimplifies -ing clauses\nReduces em dashes\ncompare.py — Before/After Analysis\npython scripts/compare.py essay.txt\npython scripts/compare.py essay.txt -a -o clean.txt\n\n\nShows side-by-side detection scores before and after transformation\n\nWorkflow\n\nScan for detection risk:\n\npython scripts/detect.py document.txt\n\n\nTransform with comparison:\n\npython scripts/compare.py document.txt -o document_v2.txt\n\n\nVerify improvement:\n\npython scripts/detect.py document_v2.txt -s\n\n\nManual review for AI vocabulary and promotional language (requires judgment)\n\nAI Probability Scoring\nRating\tCriteria\nVery High\tCitation bugs, knowledge cutoff, or chatbot artifacts present\nHigh\t>30 issues OR >5% issue density\nMedium\t>15 issues OR >2% issue density\nLow\t<15 issues AND <2% density\nCustomizing Patterns\n\nEdit scripts/patterns.json to add/modify:\n\nai_vocabulary — words to flag\nsignificance_inflation — puffery phrases\npromotional_language — marketing speak\ncopula_avoidance — phrase → replacement\nfiller_replacements — phrase → simpler form\nchatbot_artifacts — phrases triggering sentence removal\nBatch Processing\n# Scan all files\nfor f in *.txt; do\n  echo \"=== $f ===\"\n  python scripts/detect.py \"$f\" -s\ndone\n\n# Transform all markdown\nfor f in *.md; do\n  python scripts/transform.py \"$f\" -a -o \"${f%.md}_clean.md\" -q\ndone\n\nReference\n\nBased on Wikipedia's Signs of AI Writing, maintained by WikiProject AI Cleanup. Patterns documented from thousands of AI-generated text examples.\n\nKey insight: \"LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases.\""
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/moltbro/humanize-ai-text",
    "publisherUrl": "https://clawhub.ai/moltbro/humanize-ai-text",
    "owner": "moltbro",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/humanize-ai-text",
    "downloadUrl": "https://openagent3.xyz/downloads/humanize-ai-text",
    "agentUrl": "https://openagent3.xyz/skills/humanize-ai-text/agent",
    "manifestUrl": "https://openagent3.xyz/skills/humanize-ai-text/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/humanize-ai-text/agent.md"
  }
}