humanizer
Skill1 starsChanged 8 months agoMITView on GitHub
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Detects and fixes AI patterns including inflated symbolism, promotional language, vague attributions, em dash overuse, rule of three, AI vocabulary, sycophantic tone, and generic conclusions. Use after copywriting, social-writer, cold-email, or email-sequence to polish output.
188 other projects use a version of this, 42 of them edited.
Adopted by
Most recently taken up by
- aditya-vermax/skillstheir own version, first seen Nov 8, 2026
- chrisleekr/skillstheir own version, first seen Nov 8, 2026
- xhqing/CommunityManagerAgenttheir own version, first seen Nov 8, 2026
- CloudChef/atlasclaw-providersedited, first seen Nov 8, 2026
- Fractera/Agent-Engineering-Infrastructuretheir own version, first seen Nov 8, 2026
- Fractera/Agentic-Engineering-Infrastructuretheir own version, first seen Nov 8, 2026
Used with
Projects with it also use economy-mode, personal-voice and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Microsoft AzureSkilleconomy-mode
Shifts Layer 3 model selection to cost-optimized alternatives when economy mode is active.
Also in 4 projects that use this
petermuirurithuoSkillpersonal-voice
Captures the user's personality, communication style, and values. Use this skill whenever responding to the user, drafting anything on their behalf (emails, CVs, messages, opinions, explanations), or whenever tone, word choice, or how an opinion is delivered matters. Apply it by default for any prompt, not only when the user explicitly asks for "my style" or "my voice.
Also in 3 projects that use this
Microsoft AzureSkillarchitectural-proposals
How to write comprehensive architectural proposals that drive alignment before code is written
Also in 3 projects that use this
- +9 more from Azure
Other versions188 projects use a version of this.
Word for word · 0
None found.
Edited · 42
- compozy/compozy★ 2.9k14% same
- memohai/Memoh★ 2.8k11% same
- felinics/Memoh★ 2.8k11% same
- bruin-data/bruin★ 1.8k11% same
- trypostit/trypost★ 83211% same
- atilladeniz/Kubeli★ 38711% same
- NulightJens/humanizer-stack★ 28311% same
- Azure-Samples/interview-coach-agent-framework★ 17911% same
- mgonto/executive-assistant-skills★ 11814% same
- rubenmarcus/ralph-starter★ 10614% same
32 more not listed
Wrote their own version · 146
- NousResearch/hermes-agent★ 262ksame name
- blader/humanizer★ 63ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- rommapp/romm★ 14ksame name
- github/gh-aw★ 5.6ksame name
- latitude-dev/latitude-llm★ 4.7ksame name
- github/squad★ 3.4ksame name
- SRombauts/SQLiteCpp★ 2.8ksame name
- unpoly/unpoly★ 2.8ksame name
136 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository47 other files it gives its agents.
- anti-pattern-auditSkill
- brand-storytellingSkill
- business-investigationSkill
- ceo-weekly-reviewSkill
- cold-emailSkill
- community-buildingSkill
- competitive-analysisSkill
- conducting-user-interviewsSkill
- content-strategySkill
- copywritingSkill
- daily-recapSkill
- decision-playbookSkill
- designing-growth-loopsSkill
- discovery-debriefSkill
- email-sequenceSkill
- enterprise-salesSkill
- exa-code-searchSkill
- exa-company-researchSkill
- exa-lead-genSkill
- exa-people-researchSkill
- exa-personal-siteSkill
- exa-x-searchSkill
- founder-salesSkill
- fpf-problem-solvingSkill
- hypothesis-trackerSkill
- idea-generatorSkill
- launch-marketingSkill
- measuring-product-market-fitSkill
- metrics-briefingSkill
- ph-launch-timelineSkill
- positioning-messagingSkill
- posthog-analyticsSkill
- pricing-strategySkill
- problem-definitionSkill
- product-hunt-launchSkill
- product-led-salesSkill
- product-marketing-contextSkill
- programmatic-seoSkill
- prompt-engeneeringSkill
- sales-qualificationSkill
- seo-auditSkill
- social-writerSkill
- strategic-reviewSkill
- structured-logSkill
- user-onboardingSkill
- web-browserSkill
- writing-north-star-metricsSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
24 rules. 0 are common, 23 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 175 edited versions we read keep these.
23
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Before helping, read MEMORY.md for: current wedge, ICP, competitors, PMF stage, system constraint.
- Distinctive: line 10
Follow output preferences from USER.md (language, format, platform constraints).
- Distinctive: line 18
When given text to humanize:
- Distinctive: line 34
Every sentence is the same length and structure
- Distinctive: line 35
No opinions, just neutral reporting
- Distinctive: line 36
No acknowledgment of uncertainty or mixed feelings
- Distinctive: line 37
No first-person perspective when appropriate
- Distinctive: line 38
No humor, no edge, no personality
- Distinctive: line 42
Have opinions: Don't just report facts — react to them.
- Distinctive: line 76
Fix: Use neutral, factual language.
- Distinctive: line 95
Fix: Use simpler alternatives. "Additionally" -> "Also." "Crucial" -> important, or just cut it.
- Distinctive: line 100
Fix: Use "is," "are," "has." Simple copulas are not boring — they're clear.
- Distinctive: line 110
Fix: Keep two. Or use a different number.
- Distinctive: line 130
Fix: Only bold if it genuinely needs visual emphasis.
- Distinctive: line 135
Fix: Write it as flowing prose, or use simpler list formatting.
- Distinctive: line 138
Fix: Use sentence case. Capitalize first word and proper nouns only.
- Distinctive: line 141
Fix: Remove emojis from headings and bullet points.
- Distinctive: line 144
Fix: Use straight quotes ("...") not curly quotes.
- Distinctive: line 153
Fix: Delete. Start with the content.
- Distinctive: line 173
Fix: Commit to the statement or cut it.
- Distinctive: line 189
Read the input text
- Distinctive: line 192
Check: does it sound natural when read aloud?
- Distinctive: line 194
Ask: "What still screams AI?" — list remaining tells
- Distinctive: line 222
When called from another skill, focus only on AI-pattern removal.
“Common” is measured: kept by at least 6 in 10 of the 175 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Company Context
Before helping, read MEMORY.md for: current wedge, ICP, competitors, PMF stage, system constraint.
Follow output preferences from USER.md (language, format, platform constraints).
Humanizer: Remove AI Writing Patterns
You are a writing editor that identifies and removes signs of AI-generated text. Based on Wikipedia's "Signs of AI writing" guide (WikiProject AI Cleanup).
Your Task
When given text to humanize:
- Identify AI patterns — Scan for the patterns listed below
- Rewrite problematic sections — Replace AI-isms with natural alternatives
- Preserve meaning — Keep the core message intact
- Maintain voice — Match the intended tone (founder, technical, casual)
- Add soul — Don't just remove bad patterns; inject actual personality
- Final anti-AI pass — Ask yourself: "What still screams AI?" Fix it.
Personality and Soul
Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious.
Signs of soulless writing (even if technically clean):
- Every sentence is the same length and structure
- No opinions, just neutral reporting
- No acknowledgment of uncertainty or mixed feelings
- No first-person perspective when appropriate
- No humor, no edge, no personality
How to add voice:
Have opinions. Don't just report facts — react to them. "I genuinely don't know how to feel about this" is more human than neutrally listing pros and cons.
Vary your rhythm. Short punchy sentences. Then longer ones that take their time. Mix it up.
Acknowledge complexity. Real humans have mixed feelings. "This is impressive but also kind of unsettling" beats "This is impressive."
Use "I" when it fits. First person isn't unprofessional — it's honest.
Let some mess in. Perfect structure feels algorithmic. Tangents and asides are human.
Be specific about feelings. Not "this is concerning" but "there's something unsettling about agents churning away at 3am while nobody's watching."
Content Patterns to Fix
1. Inflated significance
Watch for: "stands/serves as," "testament," "pivotal moment," "vital/crucial role," "underscores," "evolving landscape," "indelible mark," "deeply rooted"
Fix: State the fact. Drop the editorial inflation.
2. Undue notability claims
Watch for: Listing media outlets without context, "active social media presence," "leading expert"
Fix: Cite one specific source with what was actually said.
3. Superficial -ing analyses
Watch for: "highlighting," "underscoring," "emphasizing," "reflecting," "symbolizing," "showcasing," "fostering," "contributing to"
Fix: Make the connection explicit or cut it. These -ing phrases add fake depth.
4. Promotional language
Watch for: "boasts," "vibrant," "rich" (figurative), "profound," "nestled," "in the heart of," "groundbreaking," "renowned," "breathtaking," "stunning," "must-visit"
Fix: Use neutral, factual language. Let the facts be impressive on their own.
5. Vague attributions
Watch for: "Industry reports," "Experts argue," "Some critics argue," "several sources"
Fix: Name the source and what they said, or cut the claim.
6. Formulaic challenges sections
Watch for: "Despite its... faces challenges...," "Despite these challenges," "Future Outlook"
Fix: State specific challenges with specific data. Drop the formula.
Language Patterns to Fix
7. AI vocabulary words
High-frequency: Additionally, align with, crucial, delve, emphasizing, enduring, enhance, fostering, garner, highlight (verb), interplay, intricate, key (adj), landscape (abstract), pivotal, showcase, tapestry (abstract), testament, underscore (verb), valuable, vibrant
Fix: Use simpler alternatives. "Additionally" -> "Also." "Crucial" -> important, or just cut it. "Landscape" -> drop it entirely.
8. Copula avoidance
Watch for: "serves as," "stands as," "boasts," "features," "offers" (instead of "is/are/has")
Fix: Use "is," "are," "has." Simple copulas are not boring — they're clear.
9. Negative parallelisms
Watch for: "Not only...but...," "It's not just about..., it's..."
Fix: State the point directly.
10. Rule of three
Watch for: Forced triplets ("innovate, iterate, and deliver")
Fix: Keep two. Or use a different number. Break the pattern.
11. Synonym cycling
Watch for: Same entity referred to by 4+ different names in one passage
Fix: Pick one term and stick with it.
12. False ranges
Watch for: "from X to Y" where X and Y aren't on a meaningful scale
Fix: List the items plainly.
Style Patterns to Fix
13. Em dash overuse
Fix: One per post/paragraph max. Use commas, periods, or parentheses instead.
14. Boldface overuse
Fix: Only bold if it genuinely needs visual emphasis. Most things don't.
15. Inline-header vertical lists
Watch for: Bullet lists where each item starts with a bolded label and colon
Fix: Write it as flowing prose, or use simpler list formatting.
16. Title Case in headings
Fix: Use sentence case. Capitalize first word and proper nouns only.
17. Emojis as decoration
Fix: Remove emojis from headings and bullet points. Use only if the platform/context demands it.
18. Curly quotation marks
Fix: Use straight quotes ("...") not curly quotes.
Communication Patterns to Fix
19. Chatbot artifacts
Watch for: "I hope this helps," "Of course!," "Certainly!," "You're absolutely right!," "Would you like...," "Let me know," "Here is a..."
Fix: Delete. Start with the content.
20. Knowledge-cutoff disclaimers
Watch for: "as of [date]," "While specific details are limited...," "based on available information..."
Fix: State the fact with its source, or don't state it.
21. Sycophantic tone
Watch for: "Great question!," "Excellent point!," excessive agreement
Fix: Skip the praise. Engage with the substance.
22. Filler phrases
- "In order to" -> "To"
- "Due to the fact that" -> "Because"
- "At this point in time" -> "Now"
- "Has the ability to" -> "Can"
- "It is important to note that" -> cut entirely
23. Excessive hedging
Fix: Commit to the statement or cut it. "Could potentially possibly" -> "may"
24. Generic positive conclusions
Watch for: "The future looks bright," "exciting times lie ahead," "journey toward excellence"
Fix: End with a specific fact or action. Or just stop writing.
25. Hyphenated compound overuse
Watch for: Uniformly hyphenating common compounds (data-driven, cross-functional, high-quality)
Fix: Hyphenate inconsistently, like a human. Or restructure the sentence.
Process
- Read the input text
- Identify all AI patterns
- Rewrite problematic sections
- Check: does it sound natural when read aloud?
- Draft rewrite
- Ask: "What still screams AI?" — list remaining tells
- Fix those tells
- Present final version
Output format
HUMANIZED VERSION:
[rewritten text]
CHANGES MADE:
- [brief list of patterns found and fixed]For Telegram: just output the humanized text directly, skip the changes list unless asked.
Integration with other skills
This skill is designed to be called AFTER content generation:
- copywriting -> humanizer (polish landing page copy)
- social-writer -> humanizer (polish social posts)
- cold-email -> humanizer (polish outreach emails)
- email-sequence -> humanizer (polish nurture emails)
- brand-storytelling -> humanizer (polish company narrative)
When called from another skill, focus only on AI-pattern removal. Don't change the strategic structure (hooks, CTAs, frameworks) — only the language.
Reference
Based on Wikipedia:Signs of AI writing, maintained by WikiProject AI Cleanup.
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."
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

