{ "schemaVersion": "1.0", "item": { "slug": "humanizer-enhanced", "name": "Humanizer Enhanced", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/dorukardahan/humanizer-enhanced", "canonicalUrl": "https://clawhub.ai/dorukardahan/humanizer-enhanced", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/humanizer-enhanced", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=humanizer-enhanced", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/communication-crypto-soul-patterns.md", "references/content-patterns.md", "references/language-style-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. 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/humanizer-enhanced" }, "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/humanizer-enhanced", "agentPageUrl": "https://openagent3.xyz/skills/humanizer-enhanced/agent", "manifestUrl": "https://openagent3.xyz/skills/humanizer-enhanced/agent.json", "briefUrl": "https://openagent3.xyz/skills/humanizer-enhanced/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 enhanced: remove AI writing patterns", "body": "Identify and remove signs of AI-generated text. This enhanced version includes crypto/Web3 patterns and adds personality to make content sound genuinely human-written." }, { "title": "Quick start", "body": "/humanizer # Humanize current file or selection\n/humanizer path/to/file.md # Humanize specific file\n/humanizer --scan # Scan only, don't edit (show issues)\n/humanizer --batch drafts/ # Process all .md files in directory" }, { "title": "Step 1: Scan for patterns", "body": "Identify all AI patterns in the text, categorize by severity:\n\nHIGH — Obvious AI tells, must fix (negative parallelism, chatbot artifacts, em dash overuse, vague attributions, copula avoidance)\nMEDIUM — Common AI patterns, should fix (rule of three, significance inflation, synonym cycling)\nLOW — Minor tells, fix if time permits (title case headings, excessive bold)" }, { "title": "Step 2: Report findings", "body": "Show user a summary:\n\n## Humanizer scan results\n\nHIGH (3 issues)\n- Line 45: Negative parallelism \"isn't X. It's Y\"\n- Line 89: Em dash overuse (5 instances)\n- Line 120: \"Research shows\" without attribution\n\nMEDIUM (5 issues)\n- Line 23: Rule of three pattern\n- Line 67: Copula avoidance \"serves as\"\n...\n\nLOW (2 issues)\n- Line 12: Title case heading\n...\n\nTotal: 10 issues found\nEstimated humanization: ~15 edits needed" }, { "title": "Step 3: Fix (with user approval)", "body": "Ask user: \"Fix all issues? Or review one by one?\"" }, { "title": "Step 4: Add soul", "body": "After fixing patterns, review for personality. Sterile writing is still obvious AI. See references/communication-crypto-soul-patterns.md for the full soul/personality guide." }, { "title": "Step 5: Readability check", "body": "Check Flesch-Kincaid readability. Target grade 10-12 for developer content, grade 8-10 for general audience. If score is too high (too complex), simplify longest sentences and replace jargon." }, { "title": "Step 6: Em dash regression scan", "body": "After all other fixes, run a final check for em dashes (—) across the text. Humanizer rewrites can reintroduce em dashes. Remove any that were added during the fix process." }, { "title": "Pattern routing table", "body": "All 34 patterns are documented with before/after examples in the reference files below.\n\nPatternsSeverityReference file1. Significance inflationMEDIUMreferences/content-patterns.md2. Promotional languageMEDIUMreferences/content-patterns.md3. Superficial -ing analysesMEDIUMreferences/content-patterns.md4. Vague attributionsHIGHreferences/content-patterns.md5. Formulaic challenges sectionsMEDIUMreferences/content-patterns.md6. Generic positive conclusionsMEDIUMreferences/content-patterns.md7. AI vocabulary wordsMEDIUMreferences/language-style-patterns.md8. Copula avoidanceHIGHreferences/language-style-patterns.md9. Negative parallelismHIGHreferences/language-style-patterns.md10. Rule of threeMEDIUMreferences/language-style-patterns.md11. Synonym cyclingMEDIUMreferences/language-style-patterns.md12. False rangesLOWreferences/language-style-patterns.md13. Em dash overuseHIGHreferences/language-style-patterns.md14. Excessive boldfaceLOWreferences/language-style-patterns.md15. Inline-header listsMEDIUMreferences/language-style-patterns.md16. Title case headingsLOWreferences/language-style-patterns.md17. Curly quotesLOWreferences/language-style-patterns.md18. Chatbot artifactsHIGHreferences/communication-crypto-soul-patterns.md19. Knowledge cutoff disclaimersHIGHreferences/communication-crypto-soul-patterns.md20. Sycophantic toneMEDIUMreferences/communication-crypto-soul-patterns.md21. Excessive hedgingMEDIUMreferences/communication-crypto-soul-patterns.md22. Filler phrasesMEDIUMreferences/communication-crypto-soul-patterns.md23. Crypto hype languageHIGHreferences/communication-crypto-soul-patterns.md24. Vague \"ecosystem\" claimsMEDIUMreferences/communication-crypto-soul-patterns.md25. Unsubstantiated statsHIGHreferences/communication-crypto-soul-patterns.md26. \"Seamless\" and \"frictionless\"MEDIUMreferences/communication-crypto-soul-patterns.md27. Abstract \"empowerment\" languageMEDIUMreferences/communication-crypto-soul-patterns.md28. Fake decentralization claimsHIGHreferences/communication-crypto-soul-patterns.md29. Meta-narrationHIGHreferences/communication-crypto-soul-patterns.md30. False audience rangeMEDIUMreferences/communication-crypto-soul-patterns.md31. Parenthetical definitionsMEDIUMreferences/communication-crypto-soul-patterns.md32. Sequential numberingMEDIUMreferences/communication-crypto-soul-patterns.md33. \"It's worth noting\" fillerMEDIUMreferences/communication-crypto-soul-patterns.md34. Identical paragraph structureHIGHreferences/communication-crypto-soul-patterns.mdSoul and personality guide—references/communication-crypto-soul-patterns.md" }, { "title": "Severity reference", "body": "SeverityPatternsActionHIGHNegative parallelism, em dash overuse, chatbot artifacts, vague attributions, copula avoidance, crypto hype, unsubstantiated stats, meta-narration, identical paragraph structure, fake decentralization, knowledge cutoff disclaimersMust fixMEDIUMRule of three, significance inflation, promotional language, -ing analyses, AI vocabulary, sycophantic tone, hedging, filler phrases, ecosystem claims, false audience range, parenthetical definitions, sequential numbering, \"it's worth noting\" filler, inline-header lists, \"seamless\"/\"frictionless\", abstract empowermentShould fixLOWTitle case, curly quotes, excessive bold, false rangesFix if time permits" }, { "title": "Quick reference: find and replace", "body": "FindReplace— (em dash, multiple), or . serves as / stands asisisn't X. It's YRewrite as single statementcrucial / vital / pivotalimportant or key or deleteFurthermore, / Moreover,Also, or deleteIt is important to noteDeleteResearch showsAdd specific sourcelandscape (abstract)Be specificrevolutionizing / game-changingDescribe what it actually doesseamless / frictionlessDescribe the actual UXIn this article, we'll exploreDeleteLet's dive in / Let's take a lookDeleteFirst,... Second,... Third,...Vary transitionsIt's worth noting / Notably,Deletedelve\"look at\" / \"examine\"AdditionallyDelete" }, { "title": "Batch mode", "body": "To humanize multiple files:\n\n# Scan all markdown files in drafts/\n/humanizer --scan drafts/*.md\n\n# Fix all files (with confirmation)\n/humanizer --batch drafts/\n\nOutput format for batch:\n\n## Batch humanization report\n\ndrafts/post-1.md\n HIGH 3 | MEDIUM 5 | LOW 2\n\ndrafts/post-2.md\n HIGH 1 | MEDIUM 3 | LOW 4\n\ndrafts/post-3.md\n Clean! No issues found.\n\nTotal: 3 files, 18 issues" }, { "title": "Sources", "body": "Based on:\n\nWikipedia: Signs of AI writing\nGitHub: blader/humanizer\nOriginal research on crypto/Web3 AI patterns\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.\"\n\nVersion 1.2.0 | Created for 0G Labs content team" } ], "body": "Humanizer enhanced: remove AI writing patterns\n\nIdentify and remove signs of AI-generated text. This enhanced version includes crypto/Web3 patterns and adds personality to make content sound genuinely human-written.\n\nQuick start\n/humanizer # Humanize current file or selection\n/humanizer path/to/file.md # Humanize specific file\n/humanizer --scan # Scan only, don't edit (show issues)\n/humanizer --batch drafts/ # Process all .md files in directory\n\nProcess\nStep 1: Scan for patterns\n\nIdentify all AI patterns in the text, categorize by severity:\n\nHIGH — Obvious AI tells, must fix (negative parallelism, chatbot artifacts, em dash overuse, vague attributions, copula avoidance)\nMEDIUM — Common AI patterns, should fix (rule of three, significance inflation, synonym cycling)\nLOW — Minor tells, fix if time permits (title case headings, excessive bold)\nStep 2: Report findings\n\nShow user a summary:\n\n## Humanizer scan results\n\nHIGH (3 issues)\n- Line 45: Negative parallelism \"isn't X. It's Y\"\n- Line 89: Em dash overuse (5 instances)\n- Line 120: \"Research shows\" without attribution\n\nMEDIUM (5 issues)\n- Line 23: Rule of three pattern\n- Line 67: Copula avoidance \"serves as\"\n...\n\nLOW (2 issues)\n- Line 12: Title case heading\n...\n\nTotal: 10 issues found\nEstimated humanization: ~15 edits needed\n\nStep 3: Fix (with user approval)\n\nAsk user: \"Fix all issues? Or review one by one?\"\n\nStep 4: Add soul\n\nAfter fixing patterns, review for personality. Sterile writing is still obvious AI. See references/communication-crypto-soul-patterns.md for the full soul/personality guide.\n\nStep 5: Readability check\n\nCheck Flesch-Kincaid readability. Target grade 10-12 for developer content, grade 8-10 for general audience. If score is too high (too complex), simplify longest sentences and replace jargon.\n\nStep 6: Em dash regression scan\n\nAfter all other fixes, run a final check for em dashes (—) across the text. Humanizer rewrites can reintroduce em dashes. Remove any that were added during the fix process.\n\nPattern routing table\n\nAll 34 patterns are documented with before/after examples in the reference files below.\n\nPatterns\tSeverity\tReference file\n1. Significance inflation\tMEDIUM\treferences/content-patterns.md\n2. Promotional language\tMEDIUM\treferences/content-patterns.md\n3. Superficial -ing analyses\tMEDIUM\treferences/content-patterns.md\n4. Vague attributions\tHIGH\treferences/content-patterns.md\n5. Formulaic challenges sections\tMEDIUM\treferences/content-patterns.md\n6. Generic positive conclusions\tMEDIUM\treferences/content-patterns.md\n7. AI vocabulary words\tMEDIUM\treferences/language-style-patterns.md\n8. Copula avoidance\tHIGH\treferences/language-style-patterns.md\n9. Negative parallelism\tHIGH\treferences/language-style-patterns.md\n10. Rule of three\tMEDIUM\treferences/language-style-patterns.md\n11. Synonym cycling\tMEDIUM\treferences/language-style-patterns.md\n12. False ranges\tLOW\treferences/language-style-patterns.md\n13. Em dash overuse\tHIGH\treferences/language-style-patterns.md\n14. Excessive boldface\tLOW\treferences/language-style-patterns.md\n15. Inline-header lists\tMEDIUM\treferences/language-style-patterns.md\n16. Title case headings\tLOW\treferences/language-style-patterns.md\n17. Curly quotes\tLOW\treferences/language-style-patterns.md\n18. Chatbot artifacts\tHIGH\treferences/communication-crypto-soul-patterns.md\n19. Knowledge cutoff disclaimers\tHIGH\treferences/communication-crypto-soul-patterns.md\n20. Sycophantic tone\tMEDIUM\treferences/communication-crypto-soul-patterns.md\n21. Excessive hedging\tMEDIUM\treferences/communication-crypto-soul-patterns.md\n22. Filler phrases\tMEDIUM\treferences/communication-crypto-soul-patterns.md\n23. Crypto hype language\tHIGH\treferences/communication-crypto-soul-patterns.md\n24. Vague \"ecosystem\" claims\tMEDIUM\treferences/communication-crypto-soul-patterns.md\n25. Unsubstantiated stats\tHIGH\treferences/communication-crypto-soul-patterns.md\n26. \"Seamless\" and \"frictionless\"\tMEDIUM\treferences/communication-crypto-soul-patterns.md\n27. Abstract \"empowerment\" language\tMEDIUM\treferences/communication-crypto-soul-patterns.md\n28. Fake decentralization claims\tHIGH\treferences/communication-crypto-soul-patterns.md\n29. Meta-narration\tHIGH\treferences/communication-crypto-soul-patterns.md\n30. False audience range\tMEDIUM\treferences/communication-crypto-soul-patterns.md\n31. Parenthetical definitions\tMEDIUM\treferences/communication-crypto-soul-patterns.md\n32. Sequential numbering\tMEDIUM\treferences/communication-crypto-soul-patterns.md\n33. \"It's worth noting\" filler\tMEDIUM\treferences/communication-crypto-soul-patterns.md\n34. Identical paragraph structure\tHIGH\treferences/communication-crypto-soul-patterns.md\nSoul and personality guide\t—\treferences/communication-crypto-soul-patterns.md\nSeverity reference\nSeverity\tPatterns\tAction\nHIGH\tNegative parallelism, em dash overuse, chatbot artifacts, vague attributions, copula avoidance, crypto hype, unsubstantiated stats, meta-narration, identical paragraph structure, fake decentralization, knowledge cutoff disclaimers\tMust fix\nMEDIUM\tRule of three, significance inflation, promotional language, -ing analyses, AI vocabulary, sycophantic tone, hedging, filler phrases, ecosystem claims, false audience range, parenthetical definitions, sequential numbering, \"it's worth noting\" filler, inline-header lists, \"seamless\"/\"frictionless\", abstract empowerment\tShould fix\nLOW\tTitle case, curly quotes, excessive bold, false ranges\tFix if time permits\nQuick reference: find and replace\nFind\tReplace\n— (em dash, multiple)\t, or .\nserves as / stands as\tis\nisn't X. It's Y\tRewrite as single statement\ncrucial / vital / pivotal\timportant or key or delete\nFurthermore, / Moreover,\tAlso, or delete\nIt is important to note\tDelete\nResearch shows\tAdd specific source\nlandscape (abstract)\tBe specific\nrevolutionizing / game-changing\tDescribe what it actually does\nseamless / frictionless\tDescribe the actual UX\nIn this article, we'll explore\tDelete\nLet's dive in / Let's take a look\tDelete\nFirst,... Second,... Third,...\tVary transitions\nIt's worth noting / Notably,\tDelete\ndelve\t\"look at\" / \"examine\"\nAdditionally\tDelete\nBatch mode\n\nTo humanize multiple files:\n\n# Scan all markdown files in drafts/\n/humanizer --scan drafts/*.md\n\n# Fix all files (with confirmation)\n/humanizer --batch drafts/\n\n\nOutput format for batch:\n\n## Batch humanization report\n\ndrafts/post-1.md\n HIGH 3 | MEDIUM 5 | LOW 2\n\ndrafts/post-2.md\n HIGH 1 | MEDIUM 3 | LOW 4\n\ndrafts/post-3.md\n Clean! No issues found.\n\nTotal: 3 files, 18 issues\n\nSources\n\nBased on:\n\nWikipedia: Signs of AI writing\nGitHub: blader/humanizer\nOriginal research on crypto/Web3 AI patterns\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.\"\n\nVersion 1.2.0 | Created for 0G Labs content team" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/dorukardahan/humanizer-enhanced", "publisherUrl": "https://clawhub.ai/dorukardahan/humanizer-enhanced", "owner": "dorukardahan", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/humanizer-enhanced", "downloadUrl": "https://openagent3.xyz/downloads/humanizer-enhanced", "agentUrl": "https://openagent3.xyz/skills/humanizer-enhanced/agent", "manifestUrl": "https://openagent3.xyz/skills/humanizer-enhanced/agent.json", "briefUrl": "https://openagent3.xyz/skills/humanizer-enhanced/agent.md" } }