humanizer
Skill2 starsChanged 6 months agoMITView on GitHub
Remove signs of AI-generated writing from text. Use when editing, reviewing, or producing any public-facing text — blog posts, social media, UI copy, emails, landing pages, documentation. Detects and fixes AI patterns including inflated symbolism, promotional language, vague attributions, em dash overuse, rule of three, AI vocabulary, negative parallelisms, sycophantic tone, and filler phrases.
187 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- vgteam/vgtheir own version, first seen Nov 16, 2026
- fluxmailai/fluxmailtheir own version, first seen Nov 16, 2026
- pantheon-org/tekhnetheir own version, first seen Nov 15, 2026
- nodetool-ai/nodetooltheir own version, first seen Nov 15, 2026
- oberemokis/skillstheir own version, first seen Nov 15, 2026
- alexandreeberhardt/skillstheir own version, first seen Nov 15, 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 versions187 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- JustineDevs/premortem★ 213% same
Wrote their own version · 186
- NousResearch/hermes-agent★ 264ksame name
- blader/humanizer★ 69ksame 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★ 4.8ksame name
- github/squad★ 3.4ksame name
- compozy/compozy★ 2.9ksame name
- memohai/Memoh★ 2.8ksame name
176 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 repository40 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-skillsSkill
- analyze-localSkill
- analyze-prodSkill
- analyzeSkill
- architectureSkill
- asset-validationSkill
- blog-postSkill
- bugfixSkill
- cloud-platformsSkill
- code-reviewSkill
- content-creationSkill
- context-engineeringSkill
- create-prSkill
- deployment-proceduresSkill
- deploy-productionSkill
- deploy-stagingSkill
- docsSkill
- feature-devSkill
- geo-writerSkill
- infra-changeSkill
- marketing-operationsSkill
- marketingSkill
- ml-pipelineSkill
- planSkill
- pre-commitSkill
- productSkill
- project-initSkill
- prompt-engineeringSkill
- qaSkill
- releaseSkill
- run-testsSkill
- security-scanSkill
- seo-reviewSkill
- social-media-managerSkill
- test-localSkill
- test-strategySkill
- ui-ux-designSkill
- worktree-isolationSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 174 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 32
Every sentence same length and structure
- Distinctive: line 33
No opinions, just neutral reporting
- Distinctive: line 34
No uncertainty or mixed feelings acknowledged
- Distinctive: line 35
No first-person perspective when appropriate
- Distinctive: line 36
No humor, edge, or personality
- Distinctive: line 42
Use "I" when it fits — first person is honest, not unprofessional
- Distinctive: line 80
When humanizing text, provide:
“Common” is measured: kept by at least 6 in 10 of the 174 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
Humanizer
Identifies and removes signs of AI-generated text. Makes writing sound natural and human. Based on Wikipedia's "Signs of AI writing" guide maintained by WikiProject AI Cleanup.
When to Use
- Writing or editing blog posts, social media posts, emails, landing pages
- Writing UI copy, microcopy, error messages, onboarding text
- Reviewing any text before publication
- Any content that will be read by humans outside the team
Process
- 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 (formal, casual, technical)
- Add soul — inject actual personality, not just remove bad patterns
- Anti-AI audit — ask "What makes this obviously AI generated?", list remaining tells, then revise
Adding Soul
Avoiding AI patterns is half the job. Sterile, voiceless writing is just as obvious.
Signs of soulless writing:
- Every sentence same length and structure
- No opinions, just neutral reporting
- No uncertainty or mixed feelings acknowledged
- No first-person perspective when appropriate
- No humor, edge, or personality
How to fix:
- Have opinions — react to facts, do not just report them
- Vary rhythm — short punchy sentences mixed with longer ones
- Acknowledge complexity — "impressive but unsettling" beats "impressive"
- Use "I" when it fits — first person is honest, not unprofessional
- Let some mess in — tangents and asides are human
- Be specific about feelings — not "concerning" but "unsettling that agents churn away at 3am"
See ai-writing-patterns.md for the full pattern catalog with before/after examples.
Quick Reference — Pattern Categories
| # | Pattern | Signal Words |
| 1 | Inflated significance | stands as, testament, pivotal, vital role, broader, indelible mark |
| 2 | Notability inflation | independent coverage, active social media presence |
| 3 | Superficial -ing phrases | highlighting, ensuring, reflecting, symbolizing, showcasing |
| 4 | Promotional language | boasts, vibrant, profound, nestled, groundbreaking, renowned, stunning |
| 5 | Vague attributions | experts argue, industry reports, some critics |
| 6 | Formulaic challenges sections | despite challenges... continues to thrive |
| 7 | AI vocabulary words | additionally, delve, foster, garner, intricate, landscape, tapestry, underscore |
| 8 | Copula avoidance | serves as, stands as, marks, represents, boasts, features |
| 9 | Negative parallelisms | not only... but, not just about... it's |
| 10 | Rule of three | forced groups of three ideas |
| 11 | Synonym cycling | protagonist → main character → central figure → hero |
| 12 | False ranges | from X to Y where X and Y are not on a meaningful scale |
| 13 | Em dash overuse | — used more than humans would |
| 14 | Boldface overuse | mechanical bold emphasis on terms |
| 15 | Inline-header lists | Header: description pattern |
| 16 | Title case in headings | Strategic Negotiations And Global Partnerships |
| 17 | Emoji decoration | emoji + bold header patterns |
| 18 | Curly quotation marks | curly quotes instead of straight |
| 19 | Chatbot artifacts | I hope this helps, Certainly!, Would you like... |
| 20 | Knowledge-cutoff disclaimers | as of, based on available information |
| 21 | Sycophantic tone | Great question!, You're absolutely right! |
| 22 | Filler phrases | in order to, due to the fact that, it is important to note |
| 23 | Excessive hedging | could potentially possibly be argued |
| 24 | Generic positive conclusions | the future looks bright, exciting times |
| 25 | Hyphenated word pair overuse | cross-functional, data-driven, high-quality used uniformly |
Output Format
When humanizing text, provide:
- Draft rewrite — cleaned version
- AI tells audit — brief bullets listing remaining AI signals
- Final rewrite — revised after the audit
- Changes summary — what was fixed (optional, if helpful)
Integration
- Rule:
humanize-contentrule auto-activates this skill for all public-facing content - Used by workflows:
blog-postskill (step 4.5),marketingskill (all content operations),docsskill (public-facing content) - Used by skill:
content-creation(Gate 7: Humanization) - Companion resource:
ai-writing-patterns.md(full pattern catalog with examples)
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.

