Robotic AI tone
Removes polished but empty prose, mechanical transitions, repetitive sentence shapes, and language that sounds generated rather than written.
A free editorial standard for AI writing, across Claude, ChatGPT, Gemini, Copilot, and more
Make AI writing sound precise, direct, and natural.
Clean Language removes the habits that make generated prose irritating: robotic tone, filler, fake enthusiasm, contrast framing, repeated conclusions, business jargon, excessive bullets, em dashes, en dashes, and predictable vocabulary such as delve, unlock, and transformative.
It preserves facts, figures, qualifications, quotations, defined terms, and useful domain terminology, and it protects legal, standards, and technical meaning. Its precedence rules require style changes to preserve the original meaning, certainty, accountability, and required action.
No dash theatreRemove unnecessary em dashes and en dashes.
No fake contrastStop the repeated “not X, but Y” pattern.
No corporate fogReplace filler and vague jargon with the actual point.
Meaning over styleFacts, figures, obligations, and technical meaning outrank any style change.
What Clean Language fixes
The writing patterns people notice.
Contrast framing
Rewrites formulas such as “it is not X, it is Y,” “not because X, but because Y,” and “this is not merely X.”
Em dash and en dash overuse
Uses commas, colons, parentheses, or complete sentences where they communicate the idea more cleanly.
AI filler words
Challenges phrases such as “it is important to note,” “at its core,” “in today’s landscape,” “delve,” “tapestry,” “leverage,” and “unlock.”
Fake enthusiasm
Removes automatic praise, reassurance, validation, inspirational framing, and unsupported claims that something is critical or transformative.
Over-explaining
Cuts repeated conclusions, unnecessary summaries, obvious implications, long introductions, and paragraphs that announce what the next paragraph will say.
Bullet list abuse
Uses lists when they improve comprehension and keeps connected reasoning in paragraphs.
Hidden ownership
Names the person, team, system, control, consequence, or required action when vague language would conceal responsibility.
Artificial balance
Stops forcing a positive counterpoint after every criticism. Findings remain clear unless mitigating evidence changes the conclusion.
Designed for real work
Writing that stays precise.
Clean Language focuses on meaning, clarity, accountability, and natural cadence. It does not use AI-detector scores as its editorial objective.
It supports executive communication, technical documentation, governance material, policies, incident updates, reports, email, Teams, Slack, LinkedIn, and general prose.
Example prompt
Apply Clean Language to this draft.
Preserve every fact and technical term.
Remove filler, contrast framing,
unnecessary dashes, and generic AI tone.Before and after
Less ceremony. More information.
Generic AI prose
It is important to note that the implementation requires additional testing before it can be considered fully ready for production. This is not merely a technical exercise, but a critical step that will help ensure a robust and seamless deployment.
Clean Language
The implementation requires additional testing before production deployment.
Questions
What Clean Language is for.
Is Clean Language an AI humanizer?
Clean Language makes generated text more natural by improving the writing itself. It preserves correctness and does not target AI-detector scores.
Does it ban every em dash, en dash, adverb, or passive sentence?
No. Clean Language keeps punctuation and constructions that carry precise meaning, including dashes, and removes only the decorative ones. You can instruct it to prohibit dashes entirely when that is your preference.
Can it clean writing produced by Claude, ChatGPT, Gemini, Copilot, or another model?
Yes. The rules are model-independent and can be used as a skill, project instruction, system prompt, Gem, or editorial checklist.
Is it suitable for technical and policy writing?
Yes. The precedence rules protect commands, identifiers, legal language, obligations, standards terminology, factual qualifications, and domain-specific vocabulary.
Is it free?
Yes. Clean Language is licensed under Creative Commons Attribution-ShareAlike 4.0 International.
Why did Jeff create Clean Language?
Too many of the documents people send are AI-generated slop: padded, generic, and several times longer than the point deserves. After one ten-page draft too many that should have been two paragraphs, Jeff wrote the standard he wished people would run first. It took about an hour, drawing on his GRC Library project (source on GitHub), and it exists to make everyone's AI output a little less infuriating to read.
Stop publishing generic AI prose.
Set up the skill, apply it to your next draft, and keep the meaning intact.
Detailed installation instructions