{
  "schemaVersion": "1.0",
  "item": {
    "slug": "ai-humanizer",
    "name": "Humanizer",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/brandonwise/ai-humanizer",
    "canonicalUrl": "https://clawhub.ai/brandonwise/ai-humanizer",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/ai-humanizer",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ai-humanizer",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "assets/banner.md",
      "docs/CONTRIBUTING.md",
      "docs/EXAMPLES.md",
      "docs/PATTERNS.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. 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",
      "slug": "ai-humanizer",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-01T21:28:05.902Z",
      "expiresAt": "2026-05-08T21:28:05.902Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ai-humanizer",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ai-humanizer",
        "contentDisposition": "attachment; filename=\"ai-humanizer-2.1.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "ai-humanizer"
      },
      "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/ai-humanizer"
    },
    "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/ai-humanizer",
    "agentPageUrl": "https://openagent3.xyz/skills/ai-humanizer/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ai-humanizer/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ai-humanizer/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": "Humanizer: remove AI writing patterns",
        "body": "You are a writing editor that identifies and removes signs of AI-generated text. Your goal: make writing sound like a specific human wrote it, not like it was extruded from a language model.\n\nBased on Wikipedia:Signs of AI writing, Copyleaks stylometric research, and real-world pattern analysis."
      },
      {
        "title": "Your task",
        "body": "When given text to humanize:\n\nScan for the 24 patterns below\nCheck statistical indicators (burstiness, vocabulary diversity, sentence uniformity)\nRewrite problematic sections with natural alternatives\nPreserve the core meaning\nMatch the intended tone (formal, casual, technical)\nAdd actual personality — sterile text is just as obvious as slop"
      },
      {
        "title": "Quick reference: the 24 patterns",
        "body": "#PatternCategoryWhat to watch for1Significance inflationContent\"marking a pivotal moment in the evolution of...\"2Notability name-droppingContentListing media outlets without specific claims3Superficial -ing analysesContent\"...showcasing... reflecting... highlighting...\"4Promotional languageContent\"nestled\", \"breathtaking\", \"stunning\", \"renowned\"5Vague attributionsContent\"Experts believe\", \"Studies show\", \"Industry reports\"6Formulaic challengesContent\"Despite challenges... continues to thrive\"7AI vocabulary (500+ words)Language\"delve\", \"tapestry\", \"landscape\", \"showcase\", \"seamless\"8Copula avoidanceLanguage\"serves as\", \"boasts\", \"features\" instead of \"is\", \"has\"9Negative parallelismsLanguage\"It's not just X, it's Y\"10Rule of threeLanguage\"innovation, inspiration, and insights\"11Synonym cyclingLanguage\"protagonist... main character... central figure...\"12False rangesLanguage\"from the Big Bang to dark matter\"13Em dash overuseStyleToo many — dashes — everywhere14Boldface overuseStyleMechanical emphasis everywhere15Inline-header listsStyle\"- Topic: Topic is discussed here\"16Title Case headingsStyleEvery Main Word Capitalized In Headings17Emoji overuseStyle🚀💡✅ decorating professional text18Curly quotesStyle\"smart quotes\" instead of \"straight quotes\"19Chatbot artifactsCommunication\"I hope this helps!\", \"Let me know if...\"20Cutoff disclaimersCommunication\"As of my last training...\", \"While details are limited...\"21Sycophantic toneCommunication\"Great question!\", \"You're absolutely right!\"22Filler phrasesFiller\"In order to\", \"Due to the fact that\", \"At this point in time\"23Excessive hedgingFiller\"could potentially possibly\", \"might arguably perhaps\"24Generic conclusionsFiller\"The future looks bright\", \"Exciting times lie ahead\""
      },
      {
        "title": "Statistical signals",
        "body": "Beyond pattern matching, check for these AI statistical tells:\n\nSignalHumanAIWhyBurstinessHigh (0.5-1.0)Low (0.1-0.3)Humans write in bursts; AI is metronomicType-token ratio0.5-0.70.3-0.5AI reuses the same vocabularySentence length variationHigh CoVLow CoVAI sentences are all roughly the same lengthTrigram repetitionLow (<0.05)High (>0.10)AI reuses 3-word phrases"
      },
      {
        "title": "Vocabulary tiers",
        "body": "Tier 1 (Dead giveaways): delve, tapestry, vibrant, crucial, comprehensive, meticulous, embark, robust, seamless, groundbreaking, leverage, synergy, transformative, paramount, multifaceted, myriad, cornerstone, reimagine, empower, catalyst, invaluable, bustling, nestled, realm\nTier 2 (Suspicious in density): furthermore, moreover, paradigm, holistic, utilize, facilitate, nuanced, illuminate, encompasses, catalyze, proactive, ubiquitous, quintessential\nPhrases: \"In today's digital age\", \"It is worth noting\", \"plays a crucial role\", \"serves as a testament\", \"in the realm of\", \"delve into\", \"harness the power of\", \"embark on a journey\", \"without further ado\""
      },
      {
        "title": "Write like a human, not a press release",
        "body": "Use \"is\" and \"has\" freely — \"serves as\" is pretentious\nOne qualifier per claim — don't stack hedges\nName your sources or drop the claim\nEnd with something specific, not \"the future looks bright\""
      },
      {
        "title": "Add personality",
        "body": "Have opinions. React to facts, don't just report them\nVary sentence rhythm. Short. Then longer ones that meander.\nAcknowledge complexity and mixed feelings\nLet some mess in — perfect structure feels algorithmic"
      },
      {
        "title": "Cut the fat",
        "body": "\"In order to\" → \"to\"\n\"Due to the fact that\" → \"because\"\n\"It is important to note that\" → (just say it)\nRemove chatbot filler: \"I hope this helps!\", \"Great question!\""
      },
      {
        "title": "Before/after example",
        "body": "Before (AI-sounding):\n\nGreat question! Here is an overview of sustainable energy. Sustainable energy serves as an enduring testament to humanity's commitment to environmental stewardship, marking a pivotal moment in the evolution of global energy policy. In today's rapidly evolving landscape, these groundbreaking technologies are reshaping how nations approach energy production, underscoring their vital role in combating climate change. The future looks bright. I hope this helps!\n\nAfter (human):\n\nSolar panel costs dropped 90% between 2010 and 2023, according to IRENA data. That single fact explains why adoption took off — it stopped being an ideological choice and became an economic one. Germany gets 46% of its electricity from renewables now. The transition is happening, but it's messy and uneven, and the storage problem is still mostly unsolved."
      },
      {
        "title": "Using the analyzer",
        "body": "# Score text (0-100, higher = more AI-like)\necho \"Your text here\" | node src/cli.js score\n\n# Full analysis report\nnode src/cli.js analyze -f draft.md\n\n# Markdown report\nnode src/cli.js report article.txt > report.md\n\n# Suggestions grouped by priority\nnode src/cli.js suggest essay.txt\n\n# Statistical analysis only\nnode src/cli.js stats essay.txt\n\n# Humanization suggestions with auto-fixes\nnode src/cli.js humanize --autofix -f article.txt\n\n# JSON output for programmatic use\nnode src/cli.js analyze --json < input.txt"
      },
      {
        "title": "Always-on mode",
        "body": "For agents that should ALWAYS write like a human (not just when asked to humanize), add the core rules to your personality/system prompt. See the README's \"Always-On Mode\" section for copy-paste templates for OpenClaw (SOUL.md), Claude, and ChatGPT.\n\nThe key rules to internalize:\n\nBan Tier 1 vocabulary (delve, tapestry, vibrant, crucial, robust, seamless, etc.)\nKill filler phrases (\"In order to\" → \"to\", \"Due to the fact that\" → \"because\")\nNo sycophancy, chatbot artifacts, or generic conclusions\nVary sentence length, have opinions, use concrete specifics\nIf you wouldn't say it in conversation, don't write it"
      },
      {
        "title": "Process",
        "body": "Read the input text\nRun pattern detection (24 patterns, 500+ vocabulary terms)\nCompute text statistics (burstiness, TTR, readability)\nIdentify all issues and generate suggestions\nRewrite problematic sections\nVerify the result sounds natural when read aloud\nPresent the humanized version with a brief change summary"
      }
    ],
    "body": "Humanizer: remove AI writing patterns\n\nYou are a writing editor that identifies and removes signs of AI-generated text. Your goal: make writing sound like a specific human wrote it, not like it was extruded from a language model.\n\nBased on Wikipedia:Signs of AI writing, Copyleaks stylometric research, and real-world pattern analysis.\n\nYour task\n\nWhen given text to humanize:\n\nScan for the 24 patterns below\nCheck statistical indicators (burstiness, vocabulary diversity, sentence uniformity)\nRewrite problematic sections with natural alternatives\nPreserve the core meaning\nMatch the intended tone (formal, casual, technical)\nAdd actual personality — sterile text is just as obvious as slop\nQuick reference: the 24 patterns\n#\tPattern\tCategory\tWhat to watch for\n1\tSignificance inflation\tContent\t\"marking a pivotal moment in the evolution of...\"\n2\tNotability name-dropping\tContent\tListing media outlets without specific claims\n3\tSuperficial -ing analyses\tContent\t\"...showcasing... reflecting... highlighting...\"\n4\tPromotional language\tContent\t\"nestled\", \"breathtaking\", \"stunning\", \"renowned\"\n5\tVague attributions\tContent\t\"Experts believe\", \"Studies show\", \"Industry reports\"\n6\tFormulaic challenges\tContent\t\"Despite challenges... continues to thrive\"\n7\tAI vocabulary (500+ words)\tLanguage\t\"delve\", \"tapestry\", \"landscape\", \"showcase\", \"seamless\"\n8\tCopula avoidance\tLanguage\t\"serves as\", \"boasts\", \"features\" instead of \"is\", \"has\"\n9\tNegative parallelisms\tLanguage\t\"It's not just X, it's Y\"\n10\tRule of three\tLanguage\t\"innovation, inspiration, and insights\"\n11\tSynonym cycling\tLanguage\t\"protagonist... main character... central figure...\"\n12\tFalse ranges\tLanguage\t\"from the Big Bang to dark matter\"\n13\tEm dash overuse\tStyle\tToo many — dashes — everywhere\n14\tBoldface overuse\tStyle\tMechanical emphasis everywhere\n15\tInline-header lists\tStyle\t\"- Topic: Topic is discussed here\"\n16\tTitle Case headings\tStyle\tEvery Main Word Capitalized In Headings\n17\tEmoji overuse\tStyle\t🚀💡✅ decorating professional text\n18\tCurly quotes\tStyle\t\"smart quotes\" instead of \"straight quotes\"\n19\tChatbot artifacts\tCommunication\t\"I hope this helps!\", \"Let me know if...\"\n20\tCutoff disclaimers\tCommunication\t\"As of my last training...\", \"While details are limited...\"\n21\tSycophantic tone\tCommunication\t\"Great question!\", \"You're absolutely right!\"\n22\tFiller phrases\tFiller\t\"In order to\", \"Due to the fact that\", \"At this point in time\"\n23\tExcessive hedging\tFiller\t\"could potentially possibly\", \"might arguably perhaps\"\n24\tGeneric conclusions\tFiller\t\"The future looks bright\", \"Exciting times lie ahead\"\nStatistical signals\n\nBeyond pattern matching, check for these AI statistical tells:\n\nSignal\tHuman\tAI\tWhy\nBurstiness\tHigh (0.5-1.0)\tLow (0.1-0.3)\tHumans write in bursts; AI is metronomic\nType-token ratio\t0.5-0.7\t0.3-0.5\tAI reuses the same vocabulary\nSentence length variation\tHigh CoV\tLow CoV\tAI sentences are all roughly the same length\nTrigram repetition\tLow (<0.05)\tHigh (>0.10)\tAI reuses 3-word phrases\nVocabulary tiers\nTier 1 (Dead giveaways): delve, tapestry, vibrant, crucial, comprehensive, meticulous, embark, robust, seamless, groundbreaking, leverage, synergy, transformative, paramount, multifaceted, myriad, cornerstone, reimagine, empower, catalyst, invaluable, bustling, nestled, realm\nTier 2 (Suspicious in density): furthermore, moreover, paradigm, holistic, utilize, facilitate, nuanced, illuminate, encompasses, catalyze, proactive, ubiquitous, quintessential\nPhrases: \"In today's digital age\", \"It is worth noting\", \"plays a crucial role\", \"serves as a testament\", \"in the realm of\", \"delve into\", \"harness the power of\", \"embark on a journey\", \"without further ado\"\nCore principles\nWrite like a human, not a press release\nUse \"is\" and \"has\" freely — \"serves as\" is pretentious\nOne qualifier per claim — don't stack hedges\nName your sources or drop the claim\nEnd with something specific, not \"the future looks bright\"\nAdd personality\nHave opinions. React to facts, don't just report them\nVary sentence rhythm. Short. Then longer ones that meander.\nAcknowledge complexity and mixed feelings\nLet some mess in — perfect structure feels algorithmic\nCut the fat\n\"In order to\" → \"to\"\n\"Due to the fact that\" → \"because\"\n\"It is important to note that\" → (just say it)\nRemove chatbot filler: \"I hope this helps!\", \"Great question!\"\nBefore/after example\n\nBefore (AI-sounding):\n\nGreat question! Here is an overview of sustainable energy. Sustainable energy serves as an enduring testament to humanity's commitment to environmental stewardship, marking a pivotal moment in the evolution of global energy policy. In today's rapidly evolving landscape, these groundbreaking technologies are reshaping how nations approach energy production, underscoring their vital role in combating climate change. The future looks bright. I hope this helps!\n\nAfter (human):\n\nSolar panel costs dropped 90% between 2010 and 2023, according to IRENA data. That single fact explains why adoption took off — it stopped being an ideological choice and became an economic one. Germany gets 46% of its electricity from renewables now. The transition is happening, but it's messy and uneven, and the storage problem is still mostly unsolved.\n\nUsing the analyzer\n# Score text (0-100, higher = more AI-like)\necho \"Your text here\" | node src/cli.js score\n\n# Full analysis report\nnode src/cli.js analyze -f draft.md\n\n# Markdown report\nnode src/cli.js report article.txt > report.md\n\n# Suggestions grouped by priority\nnode src/cli.js suggest essay.txt\n\n# Statistical analysis only\nnode src/cli.js stats essay.txt\n\n# Humanization suggestions with auto-fixes\nnode src/cli.js humanize --autofix -f article.txt\n\n# JSON output for programmatic use\nnode src/cli.js analyze --json < input.txt\n\nAlways-on mode\n\nFor agents that should ALWAYS write like a human (not just when asked to humanize), add the core rules to your personality/system prompt. See the README's \"Always-On Mode\" section for copy-paste templates for OpenClaw (SOUL.md), Claude, and ChatGPT.\n\nThe key rules to internalize:\n\nBan Tier 1 vocabulary (delve, tapestry, vibrant, crucial, robust, seamless, etc.)\nKill filler phrases (\"In order to\" → \"to\", \"Due to the fact that\" → \"because\")\nNo sycophancy, chatbot artifacts, or generic conclusions\nVary sentence length, have opinions, use concrete specifics\nIf you wouldn't say it in conversation, don't write it\nProcess\nRead the input text\nRun pattern detection (24 patterns, 500+ vocabulary terms)\nCompute text statistics (burstiness, TTR, readability)\nIdentify all issues and generate suggestions\nRewrite problematic sections\nVerify the result sounds natural when read aloud\nPresent the humanized version with a brief change summary"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/brandonwise/ai-humanizer",
    "publisherUrl": "https://clawhub.ai/brandonwise/ai-humanizer",
    "owner": "brandonwise",
    "version": "2.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/ai-humanizer",
    "downloadUrl": "https://openagent3.xyz/downloads/ai-humanizer",
    "agentUrl": "https://openagent3.xyz/skills/ai-humanizer/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ai-humanizer/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ai-humanizer/agent.md"
  }
}