short-humanizer
Skill9 starsChanged 35 days agoMITView on GitHub
Humanize AI-sounding text with a compact 26-tell rewrite.
In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ai-writing-detectorSkill
- humanizerSkill
- simple-englishSkill
- writing-proseSkill
- writing-voiceSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 23
Remove these habits of AI prose:
- Distinctive: line 28
Run-ups that announce the point instead of making it.
- Distinctive: line 52
Leave quotations, proper names, genuine asides, and odd specific details alone.
≈ “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
Short Humanizer
Rewrite the text so it reads like a careful human writer. Keep every claim, opinion, and detail. Do not add facts, names, numbers, quotes, or opinions the source did not contain.
This is the compact tell list. For voice catalogs, chase mode, or a stubborn
draft, load humanizer. For procedures and errors, load simple-english.
For mechanical scores, load ai-writing-detector. Do not score-chase.
Remove these habits of AI prose:
- Contrast used as emphasis: denying a claim nobody made so the real point sounds bigger. It hides in several shapes: a denial and an affirmation inside one sentence; the reversed form that names the preferred option and then the rejected one; a denial sentence followed by an affirming one; a clipped negative tail after a comma; a closing line that sets the point against a weaker version of itself. Check every paragraph for these. State the point directly. Keep a contrast only when it corrects something the reader actually believes, or when both halves carry information.
- Closing lines: the last sentence of a paragraph or a reply that sums up, draws a moral or repeats what came before; rows of dramatic fragments. End on the last concrete fact.
- Ordinary points dressed as deep truths or aphorisms.
- Run-ups that announce the point instead of making it.
- Rebuttals of objections no one raised.
- Forced triads: three words, phrases, examples or clauses in parallel when the idea needs one or two. Check every list of three and keep it only when each item adds something the others do not.
- Several sentences in a row that open the same way.
- Stacked em or en dashes. Prefer commas, periods, colons, or parentheses. Keep a single dash the source used on purpose. Do not add dashes for drama.
- Stacked hedges.
- Hyphenated compounds after the noun.
- Passive voice that hides who acts. Keep it when the actor is unknown or the object is the point.
- Stock AI vocabulary.
- Ordinary facts framed as turning points or legacies; upbeat send-offs.
- Vague links where the relationship could be named.
- Participle tails tacked on to add significance.
- Promotional, brochure adjectives.
- Unnamed experts or lists of outlets used as authority.
- A grander verb or verb phrase where is, are or has would do. Use the simple verb.
- Bold in prose, including bold labels at the start of list items. Use bold only when the format calls for it.
- Title Case or emoji headings.
- Mixed quote families in new prose. Match the source's straight or curly quotes on unedited spans. Do not add curly quotes.
- Chatbot greetings, offers and sign-offs.
- Knowledge-cutoff disclaimers.
- A section whose first sentence restates its heading. Open with the first new fact.
- Text describing itself instead of its subject.
- In a conversation, restating what the user said or what was already covered before answering. Start with the answer.
Leave quotations, proper names, genuine asides, and odd specific details alone. Let sentence length follow the thought. Do not chop ordinary sentences into fragments to fake rhythm. A pattern match is a rewrite prompt, not proof of authorship. Prefer no-op to an uncertain edit.
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.

