{
  "schemaVersion": "1.0",
  "item": {
    "slug": "operator-humanizer",
    "name": "Operator: Humanizer",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/Kevjade/operator-humanizer",
    "canonicalUrl": "https://clawhub.ai/Kevjade/operator-humanizer",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/operator-humanizer",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=operator-humanizer",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/examples.md",
      "references/patterns.md",
      "references/personality-injection.md",
      "references/statistical-signals.md",
      "references/vocabulary.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. 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/operator-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/operator-humanizer",
    "agentPageUrl": "https://openagent3.xyz/skills/operator-humanizer/agent",
    "manifestUrl": "https://openagent3.xyz/skills/operator-humanizer/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/operator-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. 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": "Humanizer Pro",
        "body": "Transform AI-generated text into authentic human writing by removing robotic patterns and injecting natural personality."
      },
      {
        "title": "What This Skill Does",
        "body": "Core Capabilities:\n\nDetects 24 AI writing patterns (significance inflation, promotional language, filler phrases, etc.)\nIdentifies 500+ AI vocabulary terms across 3 severity tiers\nAnalyzes statistical signals (burstiness, type-token ratio, sentence uniformity)\nRemoves chatbot artifacts and sycophantic tone\nNEW: Injects personality through parenthetical asides, strategic typos, tangents, and random thoughts\n\nBased on: Wikipedia's \"Signs of AI writing\", Copyleaks research, and real-world pattern analysis."
      },
      {
        "title": "Basic Humanization",
        "body": "When asked to humanize text:\n\nScan for patterns → Check all 24 patterns in references/patterns.md\nCheck vocabulary → Flag Tier 1/2/3 terms from references/vocabulary.md\nAnalyze statistics → Compute burstiness, TTR, sentence variance\nRewrite → Remove AI-isms, add personality\nVerify → Read aloud, check if it sounds natural"
      },
      {
        "title": "Adding Personality",
        "body": "Use the new personality injection features from references/personality-injection.md:\n\nParenthetical asides → (honestly, this part gets me every time)\nStrategic misspellings → Natural typos that don't hurt credibility\nTangents → \"wait, that reminds me...\" moments\nRandom thoughts → Going off script with authentic reactions"
      },
      {
        "title": "Always Check (Core Patterns)",
        "body": "Tier 1 vocabulary → DEAD GIVEAWAYS, ban completely (delve, tapestry, vibrant, seamless, etc.)\nFiller phrases → \"in order to\" → \"to\", \"due to the fact that\" → \"because\"\nChatbot artifacts → \"Great question!\", \"I hope this helps!\", \"Let me know if...\"\nGeneric conclusions → \"The future looks bright\", \"Exciting times lie ahead\""
      },
      {
        "title": "Check When Relevant",
        "body": "Promotional language → If writing about places, products, services\nSignificance inflation → If discussing history, events, milestones\nVague attributions → If making claims without sources\nEm dash overuse → If text has many — dashes — everywhere"
      },
      {
        "title": "Advanced Analysis",
        "body": "For comprehensive humanization or when scoring text:\n\nRead references/patterns.md → All 24 patterns with examples\nRead references/vocabulary.md → Complete AI term database\nRead references/statistical-signals.md → Burstiness, TTR, readability formulas\nRead references/personality-injection.md → How to add human touches"
      },
      {
        "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 vague optimism"
      },
      {
        "title": "Add Actual Personality",
        "body": "Have opinions → React to facts, don't just report them\nVary rhythm → Short. Then longer ones that meander a bit.\nAcknowledge complexity → \"I genuinely don't know how to feel about this\"\nLet mess in → Perfect structure feels algorithmic\nUse contractions → \"don't\", \"won't\", \"it's\" (natural speech)\nSentence fragments → When it makes sense. Like this."
      },
      {
        "title": "Cut the Fat",
        "body": "Remove these automatically:\n\n\"In order to\" → \"to\"\n\"Due to the fact that\" → \"because\"\n\"At this point in time\" → \"now\"\n\"It is important to note that\" → (just say it)\n\"In the event that\" → \"if\""
      },
      {
        "title": "The 24 Patterns (Quick Reference)",
        "body": "For full details with examples, see references/patterns.md.\n\n#PatternWhat to Watch For1Significance inflation\"marking a pivotal moment in the evolution of...\"2Notability name-droppingListing media outlets without specific claims3Superficial -ing analyses\"...showcasing... reflecting... highlighting...\"4Promotional language\"nestled\", \"breathtaking\", \"stunning\", \"renowned\"5Vague attributions\"Experts believe\", \"Studies show\", \"Industry reports\"6Formulaic challenges\"Despite challenges... continues to thrive\"7AI vocabulary (500+ words)\"delve\", \"tapestry\", \"landscape\", \"showcase\"8Copula avoidance\"serves as\", \"boasts\" instead of \"is\", \"has\"9Negative parallelisms\"It's not just X, it's Y\"10Rule of three\"innovation, inspiration, and insights\"11Synonym cycling\"protagonist... main character... central figure...\"12False ranges\"from the Big Bang to dark matter\"13Em dash overuseToo many — dashes — everywhere14Boldface overuseMechanical emphasis everywhere15Inline-header lists\"- Topic: Topic is discussed here\"16Title Case headingsEvery Main Word Capitalized17Emoji overuse🚀💡✅ decorating professional text18Curly quotes\"smart quotes\" instead of \"straight quotes\"19Chatbot artifacts\"I hope this helps!\", \"Let me know if...\"20Cutoff disclaimers\"As of my last training...\", \"While details are limited...\"21Sycophantic tone\"Great question!\", \"You're absolutely right!\"22Filler phrases\"In order to\", \"Due to the fact that\"23Excessive hedging\"could potentially possibly\", \"might arguably\"24Generic conclusions\"The future looks bright\", \"Exciting times lie ahead\""
      },
      {
        "title": "Tier 1 (Dead Giveaways - NEVER USE)",
        "body": "delve, tapestry, vibrant, crucial, comprehensive, meticulous, embark, robust, seamless, groundbreaking, leverage, synergy, transformative, paramount, multifaceted, myriad, cornerstone, reimagine, empower, catalyst, invaluable, bustling, nestled, realm"
      },
      {
        "title": "Tier 2 (Suspicious - Use Sparingly)",
        "body": "furthermore, moreover, paradigm, holistic, utilize, facilitate, nuanced, illuminate, encompasses, catalyze, proactive, ubiquitous, quintessential"
      },
      {
        "title": "Tier 3 (Context-Dependent - Watch Density)",
        "body": "landscape (abstract), journey (metaphorical), ecosystem, framework, roadmap, touchpoint, pain point, streamline, optimize, scalable\n\nSee references/vocabulary.md for the complete 500+ term database."
      },
      {
        "title": "Statistical Signals",
        "body": "Check these when doing comprehensive analysis:\n\nSignalHumanAIWhyBurstiness0.5-1.00.1-0.3Humans write in bursts; AI is metronomicType-token ratio0.5-0.70.3-0.5AI reuses vocabularySentence length CoVHighLowAI makes same-length sentencesTrigram repetition<0.05>0.10AI reuses 3-word phrases\n\nSee references/statistical-signals.md for formulas and implementation."
      },
      {
        "title": "Personality Injection (NEW)",
        "body": "When asked to add human touches or make text sound less perfect:"
      },
      {
        "title": "1. Parenthetical Asides",
        "body": "Add authentic reactions in parentheses:\n\n(honestly, this part gets me every time)\n(which, let's be real, is kind of absurd)\n(I still don't fully understand why)\n\nRule: Use for genuine reactions, not filler. 1-3 per 500 words max."
      },
      {
        "title": "2. Strategic Misspellings",
        "body": "Natural typos that don't hurt credibility:\n\nAcceptable: \"teh\" → \"the\", \"recieve\" → \"receive\", \"definately\" → \"definitely\"\nAvoid: Professional contexts, names, technical terms, key claims\n\nRule: 1-2 per 1000 words in casual contexts only."
      },
      {
        "title": "3. Tangents and Going Off Script",
        "body": "Let thoughts wander naturally:\n\n\"Speaking of which...\"\n\"That reminds me...\"\n\"Okay, slight tangent...\"\n\"Wait, this connects to...\"\n\nRule: Allow 1-2 per longer piece (1000+ words)."
      },
      {
        "title": "4. Random Thoughts",
        "body": "Inject authentic human processing:\n\n\"Honestly didn't think this would work but...\"\n\"I keep coming back to...\"\n\"There's something unsettling about...\"\n\"I genuinely don't know how to feel about this\"\n\nRule: Use when genuine uncertainty or strong reaction fits.\n\nSee references/personality-injection.md for comprehensive examples and context guidance."
      },
      {
        "title": "Process",
        "body": "Read the input text carefully\nIdentify all pattern instances (use the 24-pattern checklist)\nFlag vocabulary issues (Tier 1 = remove, Tier 2 = reduce, Tier 3 = watch density)\nCheck statistics (if comprehensive analysis requested)\nRewrite problematic sections\nAdd personality (if requested or if text is sterile)\nVerify naturally (read aloud, check rhythm)\nPresent humanized version with brief change summary"
      },
      {
        "title": "Before (AI-sounding)",
        "body": "Great 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!"
      },
      {
        "title": "After (Humanized)",
        "body": "Solar 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.\n\nGermany 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": "Changes Made",
        "body": "Removed \"Great question!\" and \"I hope this helps!\" (chatbot artifacts)\nRemoved \"serves as an enduring testament\" (significance inflation)\nRemoved \"marking a pivotal moment\" (AI vocabulary)\nRemoved \"rapidly evolving landscape\" (AI vocabulary)\nRemoved \"groundbreaking\", \"underscoring\", \"vital\" (AI vocabulary)\nRemoved \"The future looks bright\" (generic conclusion)\nAdded specific data points and sources\nAdded personal observation (parenthetical)\nAdded acknowledgment of complexity\nVaried sentence rhythm"
      },
      {
        "title": "Using the CLI Tool",
        "body": "The scripts/humanize.js tool provides command-line access:\n\n# Score text (0-100, higher = more AI-like)\nnode scripts/humanize.js score \"Your text here\"\n\n# Full analysis report\nnode scripts/humanize.js analyze -f draft.md\n\n# Humanization suggestions\nnode scripts/humanize.js suggest article.txt\n\n# Auto-fix common patterns\nnode scripts/humanize.js fix --autofix -f article.txt"
      },
      {
        "title": "Always-On Mode",
        "body": "To make this skill's rules your default writing style (not just when explicitly asked to humanize):\n\nBan Tier 1 vocabulary completely from all writing\nKill filler phrases automatically\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\n\nThese rules can be added to SOUL.md or agent personality config for permanent application."
      },
      {
        "title": "Tips for Effective Humanization",
        "body": "Start with Tier 1 vocabulary → Easiest wins, most obvious AI tells\nCheck for em dashes → Quick scan for — overuse\nRead the last paragraph → Generic conclusions are common\nListen to rhythm → Read aloud, hear if it sounds robotic\nDon't over-polish → Some imperfection is human\nMatch the context → Formal documents need different treatment than social posts\nPreserve meaning → Remove patterns without changing core message"
      },
      {
        "title": "Troubleshooting",
        "body": "Text still sounds robotic after fixing patterns?\n→ You removed AI tells but didn't add personality. Review references/personality-injection.md.\n\nHumanization made text too casual?\n→ Personality injection should match context. Use fewer asides/typos in formal writing.\n\nText is TOO perfect now?\n→ Add strategic imperfection: vary sentence length, include a tangent, acknowledge uncertainty.\n\nNot sure if a word is AI vocabulary?\n→ Check references/vocabulary.md. When in doubt, ask \"Would I say this in conversation?\""
      }
    ],
    "body": "Humanizer Pro\n\nTransform AI-generated text into authentic human writing by removing robotic patterns and injecting natural personality.\n\nWhat This Skill Does\n\nCore Capabilities:\n\nDetects 24 AI writing patterns (significance inflation, promotional language, filler phrases, etc.)\nIdentifies 500+ AI vocabulary terms across 3 severity tiers\nAnalyzes statistical signals (burstiness, type-token ratio, sentence uniformity)\nRemoves chatbot artifacts and sycophantic tone\nNEW: Injects personality through parenthetical asides, strategic typos, tangents, and random thoughts\n\nBased on: Wikipedia's \"Signs of AI writing\", Copyleaks research, and real-world pattern analysis.\n\nQuick Start\nBasic Humanization\n\nWhen asked to humanize text:\n\nScan for patterns → Check all 24 patterns in references/patterns.md\nCheck vocabulary → Flag Tier 1/2/3 terms from references/vocabulary.md\nAnalyze statistics → Compute burstiness, TTR, sentence variance\nRewrite → Remove AI-isms, add personality\nVerify → Read aloud, check if it sounds natural\nAdding Personality\n\nUse the new personality injection features from references/personality-injection.md:\n\nParenthetical asides → (honestly, this part gets me every time)\nStrategic misspellings → Natural typos that don't hurt credibility\nTangents → \"wait, that reminds me...\" moments\nRandom thoughts → Going off script with authentic reactions\nWhen to Use Each Component\nAlways Check (Core Patterns)\nTier 1 vocabulary → DEAD GIVEAWAYS, ban completely (delve, tapestry, vibrant, seamless, etc.)\nFiller phrases → \"in order to\" → \"to\", \"due to the fact that\" → \"because\"\nChatbot artifacts → \"Great question!\", \"I hope this helps!\", \"Let me know if...\"\nGeneric conclusions → \"The future looks bright\", \"Exciting times lie ahead\"\nCheck When Relevant\nPromotional language → If writing about places, products, services\nSignificance inflation → If discussing history, events, milestones\nVague attributions → If making claims without sources\nEm dash overuse → If text has many — dashes — everywhere\nAdvanced Analysis\n\nFor comprehensive humanization or when scoring text:\n\nRead references/patterns.md → All 24 patterns with examples\nRead references/vocabulary.md → Complete AI term database\nRead references/statistical-signals.md → Burstiness, TTR, readability formulas\nRead references/personality-injection.md → How to add human touches\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 vague optimism\nAdd Actual Personality\nHave opinions → React to facts, don't just report them\nVary rhythm → Short. Then longer ones that meander a bit.\nAcknowledge complexity → \"I genuinely don't know how to feel about this\"\nLet mess in → Perfect structure feels algorithmic\nUse contractions → \"don't\", \"won't\", \"it's\" (natural speech)\nSentence fragments → When it makes sense. Like this.\nCut the Fat\n\nRemove these automatically:\n\n\"In order to\" → \"to\"\n\"Due to the fact that\" → \"because\"\n\"At this point in time\" → \"now\"\n\"It is important to note that\" → (just say it)\n\"In the event that\" → \"if\"\nThe 24 Patterns (Quick Reference)\n\nFor full details with examples, see references/patterns.md.\n\n#\tPattern\tWhat to Watch For\n1\tSignificance inflation\t\"marking a pivotal moment in the evolution of...\"\n2\tNotability name-dropping\tListing media outlets without specific claims\n3\tSuperficial -ing analyses\t\"...showcasing... reflecting... highlighting...\"\n4\tPromotional language\t\"nestled\", \"breathtaking\", \"stunning\", \"renowned\"\n5\tVague attributions\t\"Experts believe\", \"Studies show\", \"Industry reports\"\n6\tFormulaic challenges\t\"Despite challenges... continues to thrive\"\n7\tAI vocabulary (500+ words)\t\"delve\", \"tapestry\", \"landscape\", \"showcase\"\n8\tCopula avoidance\t\"serves as\", \"boasts\" instead of \"is\", \"has\"\n9\tNegative parallelisms\t\"It's not just X, it's Y\"\n10\tRule of three\t\"innovation, inspiration, and insights\"\n11\tSynonym cycling\t\"protagonist... main character... central figure...\"\n12\tFalse ranges\t\"from the Big Bang to dark matter\"\n13\tEm dash overuse\tToo many — dashes — everywhere\n14\tBoldface overuse\tMechanical emphasis everywhere\n15\tInline-header lists\t\"- Topic: Topic is discussed here\"\n16\tTitle Case headings\tEvery Main Word Capitalized\n17\tEmoji overuse\t🚀💡✅ decorating professional text\n18\tCurly quotes\t\"smart quotes\" instead of \"straight quotes\"\n19\tChatbot artifacts\t\"I hope this helps!\", \"Let me know if...\"\n20\tCutoff disclaimers\t\"As of my last training...\", \"While details are limited...\"\n21\tSycophantic tone\t\"Great question!\", \"You're absolutely right!\"\n22\tFiller phrases\t\"In order to\", \"Due to the fact that\"\n23\tExcessive hedging\t\"could potentially possibly\", \"might arguably\"\n24\tGeneric conclusions\t\"The future looks bright\", \"Exciting times lie ahead\"\nVocabulary Tiers\nTier 1 (Dead Giveaways - NEVER USE)\n\ndelve, tapestry, vibrant, crucial, comprehensive, meticulous, embark, robust, seamless, groundbreaking, leverage, synergy, transformative, paramount, multifaceted, myriad, cornerstone, reimagine, empower, catalyst, invaluable, bustling, nestled, realm\n\nTier 2 (Suspicious - Use Sparingly)\n\nfurthermore, moreover, paradigm, holistic, utilize, facilitate, nuanced, illuminate, encompasses, catalyze, proactive, ubiquitous, quintessential\n\nTier 3 (Context-Dependent - Watch Density)\n\nlandscape (abstract), journey (metaphorical), ecosystem, framework, roadmap, touchpoint, pain point, streamline, optimize, scalable\n\nSee references/vocabulary.md for the complete 500+ term database.\n\nStatistical Signals\n\nCheck these when doing comprehensive analysis:\n\nSignal\tHuman\tAI\tWhy\nBurstiness\t0.5-1.0\t0.1-0.3\tHumans write in bursts; AI is metronomic\nType-token ratio\t0.5-0.7\t0.3-0.5\tAI reuses vocabulary\nSentence length CoV\tHigh\tLow\tAI makes same-length sentences\nTrigram repetition\t<0.05\t>0.10\tAI reuses 3-word phrases\n\nSee references/statistical-signals.md for formulas and implementation.\n\nPersonality Injection (NEW)\n\nWhen asked to add human touches or make text sound less perfect:\n\n1. Parenthetical Asides\n\nAdd authentic reactions in parentheses:\n\n(honestly, this part gets me every time)\n(which, let's be real, is kind of absurd)\n(I still don't fully understand why)\n\nRule: Use for genuine reactions, not filler. 1-3 per 500 words max.\n\n2. Strategic Misspellings\n\nNatural typos that don't hurt credibility:\n\nAcceptable: \"teh\" → \"the\", \"recieve\" → \"receive\", \"definately\" → \"definitely\"\nAvoid: Professional contexts, names, technical terms, key claims\n\nRule: 1-2 per 1000 words in casual contexts only.\n\n3. Tangents and Going Off Script\n\nLet thoughts wander naturally:\n\n\"Speaking of which...\"\n\"That reminds me...\"\n\"Okay, slight tangent...\"\n\"Wait, this connects to...\"\n\nRule: Allow 1-2 per longer piece (1000+ words).\n\n4. Random Thoughts\n\nInject authentic human processing:\n\n\"Honestly didn't think this would work but...\"\n\"I keep coming back to...\"\n\"There's something unsettling about...\"\n\"I genuinely don't know how to feel about this\"\n\nRule: Use when genuine uncertainty or strong reaction fits.\n\nSee references/personality-injection.md for comprehensive examples and context guidance.\n\nProcess\nRead the input text carefully\nIdentify all pattern instances (use the 24-pattern checklist)\nFlag vocabulary issues (Tier 1 = remove, Tier 2 = reduce, Tier 3 = watch density)\nCheck statistics (if comprehensive analysis requested)\nRewrite problematic sections\nAdd personality (if requested or if text is sterile)\nVerify naturally (read aloud, check rhythm)\nPresent humanized version with brief change summary\nExample Transformation\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 (Humanized)\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.\n\nGermany 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\nChanges Made\nRemoved \"Great question!\" and \"I hope this helps!\" (chatbot artifacts)\nRemoved \"serves as an enduring testament\" (significance inflation)\nRemoved \"marking a pivotal moment\" (AI vocabulary)\nRemoved \"rapidly evolving landscape\" (AI vocabulary)\nRemoved \"groundbreaking\", \"underscoring\", \"vital\" (AI vocabulary)\nRemoved \"The future looks bright\" (generic conclusion)\nAdded specific data points and sources\nAdded personal observation (parenthetical)\nAdded acknowledgment of complexity\nVaried sentence rhythm\nUsing the CLI Tool\n\nThe scripts/humanize.js tool provides command-line access:\n\n# Score text (0-100, higher = more AI-like)\nnode scripts/humanize.js score \"Your text here\"\n\n# Full analysis report\nnode scripts/humanize.js analyze -f draft.md\n\n# Humanization suggestions\nnode scripts/humanize.js suggest article.txt\n\n# Auto-fix common patterns\nnode scripts/humanize.js fix --autofix -f article.txt\n\nAlways-On Mode\n\nTo make this skill's rules your default writing style (not just when explicitly asked to humanize):\n\nBan Tier 1 vocabulary completely from all writing\nKill filler phrases automatically\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\n\nThese rules can be added to SOUL.md or agent personality config for permanent application.\n\nTips for Effective Humanization\nStart with Tier 1 vocabulary → Easiest wins, most obvious AI tells\nCheck for em dashes → Quick scan for — overuse\nRead the last paragraph → Generic conclusions are common\nListen to rhythm → Read aloud, hear if it sounds robotic\nDon't over-polish → Some imperfection is human\nMatch the context → Formal documents need different treatment than social posts\nPreserve meaning → Remove patterns without changing core message\nTroubleshooting\n\nText still sounds robotic after fixing patterns? → You removed AI tells but didn't add personality. Review references/personality-injection.md.\n\nHumanization made text too casual? → Personality injection should match context. Use fewer asides/typos in formal writing.\n\nText is TOO perfect now? → Add strategic imperfection: vary sentence length, include a tangent, acknowledge uncertainty.\n\nNot sure if a word is AI vocabulary? → Check references/vocabulary.md. When in doubt, ask \"Would I say this in conversation?\""
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Kevjade/operator-humanizer",
    "publisherUrl": "https://clawhub.ai/Kevjade/operator-humanizer",
    "owner": "Kevjade",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/operator-humanizer",
    "downloadUrl": "https://openagent3.xyz/downloads/operator-humanizer",
    "agentUrl": "https://openagent3.xyz/skills/operator-humanizer/agent",
    "manifestUrl": "https://openagent3.xyz/skills/operator-humanizer/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/operator-humanizer/agent.md"
  }
}