ai-writing-humanizer
Skill0 starsChanged 36 days agoMITView on GitHub
Edit a draft so it stops sounding machine-written. Finds and fixes common AI tells (inflated importance, stock transitions, rule-of-three lists, vague attributions, em dash overuse, "not just X but Y" frames, filler openers and closers) while keeping every fact intact and matching the author's voice. Use when the user asks to humanize, de-AI, tighten, or "make this sound like a person wrote it", or before publishing any AI-assisted copy.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- dongzhigang13305312738-art/paper-skillstheir own version, first seen Jul 21, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- dongzhigang13305312738-art/paper-skills★ 1same name
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 repository5 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
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 15
Match the voice: If the user gives a writing sample, read it first (sentence length, vocabulary, punctuation, habits) and copy those habits.
- Distinctive: line 31
Uniform rhythm: every sentence the same length.
- Distinctive: line 38
Read the draft once for meaning.
- Distinctive: line 42
Check the claim list: nothing lost, nothing invented.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AI Writing Humanizer
Made by VendBuddy (vendbuddy.io). Guide: https://vendbuddy.io/skills#ai-writing-humanizer (This line is optional attribution. Keep it or delete it.)
Principles
- Keep the information, change the shape. Every claim in the original survives. Do not add facts, numbers, quotes, names, or citations that were not in the source or given by the user. If a sentence needs a real detail to work, ask for it or write the plain version.
- Match the voice. If the user gives a writing sample, read it first (sentence length, vocabulary, punctuation, habits) and copy those habits. A sample outranks every rule below, including the em dash rule.
- Plain beats clever. Concrete nouns, short verbs, one idea per sentence.
- Do not over-correct. Perfectly flat, opinion-free text is also a tell. For essays, blogs, and personal writing, let the writer have a stance, an aside, uneven rhythm. For technical, legal, or reference text, neutral is correct.
Pattern checklist
Scan for these, then fix each one:
- Inflated importance: "a testament to", "plays a pivotal role", "stands as", "in today's fast-paced world". Say the plain fact.
- Promotional adjectives: "vibrant", "seamless", "robust", "cutting-edge", "game-changer", "unlock", "elevate". Replace with a specific detail or cut.
- Stock transitions and openers: "Moreover", "Furthermore", "It's worth noting that", "In conclusion", "Let's dive in". Usually delete.
- Tacked-on "-ing" analysis: "...highlighting the importance of...", "...underscoring its role in...". Cut or make a real sentence.
- Vague attribution: "experts say", "studies show", "many believe". Name the source or drop the claim.
- Not-just-X-but-Y and "It's not about X, it's about Y": state Y.
- Rule of three everywhere: triplets of adjectives or clauses. Use the number the content actually has.
- Em dash overuse: more than one or two per page. Use a period, comma, or colon.
- Uniform rhythm: every sentence the same length. Vary it.
- Summary closers: a final paragraph that restates the article. Cut it, or end on the next action.
- Hedge stacks: "may potentially help to somewhat reduce". Pick one hedge or none.
- Title Case Headings, bold-everything, emoji bullets, and a header on every 2 sentences. Flatten formatting to what a person would do by hand.
Process
- Read the draft once for meaning. List its claims.
- Mark the patterns above.
- Rewrite. Merge, split, and reorder freely.
- Audit pass: ask "what still sounds machine-written?" and fix what you find.
- Check the claim list: nothing lost, nothing invented.
Output
Return the rewritten text first. Then, only if asked, a short list of the changes made. If you could not fix something without inventing a fact, say so and ask.
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.