# Send Humanizer Enhanced to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text 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. ``` ### Upgrade existing ```text 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. ``` ## Machine-readable fields ```json { "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": { "downloadUrl": "/downloads/humanizer-enhanced", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=humanizer-enhanced", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "references/communication-crypto-soul-patterns.md", "references/content-patterns.md", "references/language-style-patterns.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "humanizer-enhanced", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-01T21:25:25.777Z", "expiresAt": "2026-05-08T21:25:25.777Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=humanizer-enhanced", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=humanizer-enhanced", "contentDisposition": "attachment; filename=\"humanizer-enhanced-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "humanizer-enhanced" }, "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/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." ] } }, "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" } } ``` ## Documentation ### Humanizer enhanced: remove AI writing patterns 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. ### Quick start /humanizer # Humanize current file or selection /humanizer path/to/file.md # Humanize specific file /humanizer --scan # Scan only, don't edit (show issues) /humanizer --batch drafts/ # Process all .md files in directory ### Step 1: Scan for patterns Identify all AI patterns in the text, categorize by severity: HIGH — Obvious AI tells, must fix (negative parallelism, chatbot artifacts, em dash overuse, vague attributions, copula avoidance) MEDIUM — Common AI patterns, should fix (rule of three, significance inflation, synonym cycling) LOW — Minor tells, fix if time permits (title case headings, excessive bold) ### Step 2: Report findings Show user a summary: ## Humanizer scan results HIGH (3 issues) - Line 45: Negative parallelism "isn't X. It's Y" - Line 89: Em dash overuse (5 instances) - Line 120: "Research shows" without attribution MEDIUM (5 issues) - Line 23: Rule of three pattern - Line 67: Copula avoidance "serves as" ... LOW (2 issues) - Line 12: Title case heading ... Total: 10 issues found Estimated humanization: ~15 edits needed ### Step 3: Fix (with user approval) Ask user: "Fix all issues? Or review one by one?" ### Step 4: Add soul 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. ### Step 5: Readability check 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. ### Step 6: Em dash regression scan 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. ### Pattern routing table All 34 patterns are documented with before/after examples in the reference files below. PatternsSeverityReference 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 ### Severity reference 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 ### Quick reference: find and replace 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 ### Batch mode To humanize multiple files: # Scan all markdown files in drafts/ /humanizer --scan drafts/*.md # Fix all files (with confirmation) /humanizer --batch drafts/ Output format for batch: ## Batch humanization report drafts/post-1.md HIGH 3 | MEDIUM 5 | LOW 2 drafts/post-2.md HIGH 1 | MEDIUM 3 | LOW 4 drafts/post-3.md Clean! No issues found. Total: 3 files, 18 issues ### Sources Based on: Wikipedia: Signs of AI writing GitHub: blader/humanizer Original research on crypto/Web3 AI patterns Key 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." Version 1.2.0 | Created for 0G Labs content team ## Trust - Source: tencent - Verification: Indexed source record - Publisher: dorukardahan - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-01T21:25:25.777Z - Expires at: 2026-05-08T21:25:25.777Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/humanizer-enhanced) - [Send to Agent page](https://openagent3.xyz/skills/humanizer-enhanced/agent) - [JSON manifest](https://openagent3.xyz/skills/humanizer-enhanced/agent.json) - [Markdown brief](https://openagent3.xyz/skills/humanizer-enhanced/agent.md) - [Download page](https://openagent3.xyz/downloads/humanizer-enhanced)