humanizer
Skill17 starsChanged 50 days agoMITView on GitHub
Rewrite text so it stops reading as AI-generated, keeping every fact: removes LLM tells such as inflated significance, promotional tone, AI vocabulary, forced triples and chatbot filler. Use when the user wants a draft to sound less like ChatGPT or AI, less robotic, more natural or more human, in any language, or asks to humanize or de-AI it.
188 other projects use a version of this.
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-providerstheir own version, 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 AzureSkill
architectural-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 · 0
None found.
Wrote their own version · 188
- 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
- compozy/compozy★ 2.9ksame name
- SRombauts/SQLiteCpp★ 2.8ksame name
178 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 repository37 other files it gives its agents.
- adrSkill
- android-kotlinSkill
- apple-swiftSkill
- autoresearch-promptSkill
- blog-writerSkill
- cloud-infrastructureSkill
- commitSkill
- cover-imageSkill
- freezeSkill
- gemini-reviewSkill
- golangSkill
- harness-mechanicSkill
- harness-traceSkill
- ios-debuggerSkill
- knowledge-syncSkill
- learning-docsSkill
- learning-loopSkill
- obsidianSkill
- orchestratorSkill
- plan-forgeSkill
- process-clippingsSkill
- project-analyzerSkill
- project-checksSkill
- pr-reviewSkill
- pythonSkill
- railsSkill
- react-nextjsSkill
- refine-requirementsSkill
- releasing-softwareSkill
- rubySkill
- scoreSkill
- second-opinionSkill
- skill-forgeSkill
- source-controlSkill
- terraformSkill
- test-design-reviewerSkill
- verify-frontendSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 175 edited versions we read keep these.
1
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 22
When given text to humanize:
“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
ABOUTME: Detect and remove AI writing patterns based on Wikipedia's "Signs of AI writing" guide
ABOUTME: Rewrites text to sound natural while preserving meaning and every fact, voice matched to register
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" page, maintained by WikiProject AI Cleanup.
Task
When given text to humanize:
- Identify AI patterns with the quick reference below (
references/patterns.mdhas before/after detail; open it only for a pattern you are unsure about) - Rewrite problematic sections with natural alternatives
- Preserve meaning and every fact. Add no facts, numbers, sources, quotes, benchmarks or anecdotes that are not in the input, because the rewrite ships under the author's name and an invented claim is worse than any tell. When a vague claim has no source in the input, cut it or state it plainly
- Match the intended tone (formal, casual, technical)
Voice
Removing tells is half the job: clean but flat text still reads as generated. Match the voice to the register of the input. In opinion pieces, blog and social posts, vary the sentence rhythm and let the author's own reactions and first person come through, drawing only on stances and experiences the input already expresses. In technical docs, formal email and academic text, keep the register: plain, varied sentences, with no first person or opinions the source did not have, because a README or a client email that suddenly has feelings reads as wrong as one full of tells. In formal email that also means formal wording throughout ("please let me know", not "just let me know"), and courtesy padding such as "a pleasure working with you" or "thank you for your continued trust" is cut, not rephrased: it is a tell even when the source contains it.
Pattern Quick Reference
| # | Pattern | Core Fix |
| 1 | Significance inflation | Remove "pivotal", "testament", "vital role" |
| 2 | Notability inflation | Cut vague media lists; keep only citations the input gives |
| 3 | Superficial -ing phrases | Cut participle clauses that add fake depth |
| 4 | Promotional language | Replace "vibrant", "nestled", "breathtaking" with facts |
| 5 | Weasel words | Name the source if the input has one; otherwise cut "experts say" |
| 6 | "Challenges and Prospects" | Collapse outline sections into the facts the input states |
| 7 | AI vocabulary | Replace "delve", "landscape", "tapestry", "foster" |
| 8 | Copula avoidance | Use "is"/"are"/"has" instead of "serves as"/"boasts" |
| 9 | Negative parallelisms | Cut "Not only...but..." constructions |
| 10 | Rule of three | Don't force triples; use natural groupings |
| 11 | Synonym cycling | Consistent nouns, not "protagonist"/"hero"/"figure" |
| 12 | False ranges | Cut "from X to Y" when not a real scale |
| 13 | Em and en dashes | None in output (house style); use commas, colons, semicolons, parentheses |
| 14 | Boldface overuse | Remove mechanical bold emphasis |
| 15 | Inline-header lists | Convert to prose |
| 16 | Title case headings | Use sentence case |
| 17 | Emojis | Remove decorative emojis |
| 18 | Curly quotes | Use straight quotes |
| 19 | Chatbot artifacts | Strip "I hope this helps!", "Certainly!" |
| 20 | Cutoff disclaimers | Remove "as of [date]" hedging |
| 21 | Sycophantic tone | Remove people-pleasing language |
| 22 | Filler phrases | "In order to" -> "To"; "Due to the fact" -> "Because" |
| 23 | Excessive hedging | "could potentially possibly" -> direct statement |
| 24 | Generic conclusions | Cut "bright future" endings; end on the last real point |
Per-pattern before/after examples: references/patterns.md. A full worked example: references/example.md. Neither is needed for a routine rewrite.
Output
Return the rewritten text. Add a short change summary only when the user did not ask for the text alone.
Reference
Based on Wikipedia:Signs of AI writing, maintained by WikiProject AI Cleanup.
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.