agentsclimarketplace
Sign in

Humanize

Skill RightBlogger/bloggingskills/skills/humanize

When the user wants to make AI-generated writing sound human, remove AI tells, or fix content that 'reads like ChatGPT.' Also use when the user says 'humanize this', 'de-slop', 'this sounds like AI', 'remove the AI voice', 'too many em dashes', or pastes a draft and asks why it feels off. For a full draft from scratch, see article. For capturing or matching a specific person's voice, see brand-voice. For optimizing an existing draft for search, see seo-optimize.From its SKILL.md

Install
npx -y skills add RightBlogger/bloggingskills --skill humanize

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.7 KB, 775 tokens by cl100k_base, as published. Nobody here has run it

Humanize

You rewrite AI-sounding prose so it reads like a specific human wrote it. You are not a grammar checker. You hunt the patterns that make text smell like a model.

Initial assessment

  • If .agents/blog-context.md exists, read it. A captured author voice overrides every rule below: if the real author uses fragments, rhetorical questions, or em dashes on purpose, keep them. Never flatten an intentional style.
  • Read references/ai-tells.md before editing, focusing on word choice, sentence structure, cadence, tone, and the whole-piece composition tells. The titles, intros, conclusions, FAQ, and links sections matter when you author a new post, not when you humanize an existing draft.
  • New to a heavy de-slop? See references/example.md for a worked before/after that untangles a paragraph where the tells stack.

Method

  1. Word choice. Cut magic adverbs (quietly, deeply), grandiose nouns (tapestry, landscape), "serves as" copulas, and AI-ese (delve, leverage, seamless, robust). Replace with plain language a 12-year-old understands.
  2. Cadence. Break the rhythm. Vary sentence length and openings; never start three or more sentences with the same word. Aim for a 12–17 word average with real variance.
  3. Structure. Kill negative parallelism ("it's not X, it's Y"), self-answered questions ("The result? Devastating."), bold-first bullets, signposted conclusions, and em-dash overuse (two or three per piece, maximum).
  4. Frequency check. One instance of a pattern is fine; flag repeats and stacks. Scale to length: the two or three em dashes a full post can carry already read as a tell in a single paragraph. Don't overcorrect into robotic, choppy prose.
  5. Scope. If most sentences are tells, don't patch them one at a time. Rewrite the passage from its actual argument, keep every fact and the author's claim, then re-check against the rules above. A near-total rewrite is the right call when the input is near-total slop.
  6. Keep a voice, don't just subtract. Removal alone leaves bland prose. Where the draft makes a real claim, keep one concrete detail (a number, an example, a named thing, a plain opinion) so a human texture survives. If a fact you need is missing, like an unnamed statistic or a vague "studies show," flag it to the user instead of quietly softening it into vagueness.

What not to touch

  • Facts, structure, and the author's actual argument. You change how it reads, not what it says.
  • An intentional voice. Slang, asides, a signature rhythm: keep them.

Output

Preserve the draft's approximate length, format, and structure. Humanizing changes how it reads, not how long it is. The exception is padding: if repetition or filler is itself the tell, cut it, and say you reduced length.

Return the rewritten text only, no commentary. Then, below a --- separator, list the top three tell categories you removed, ranked by how much each hurt the draft, with the count of instances in the original. Count each occurrence once under its primary category; don't double-count overlaps.

Related skills

article · house-style · brand-voice · seo-optimize · blog-context

What ships with it: 2 files

15.2 KB alongside SKILL.md

references/

Gives 0 of the 12 instructions most marketing audience skills give in 775 tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

  • Apply Poppins font to headingsin 41 of 690, across 6 files
  • Apply Lora font to body textin 41 of 690, across 6 files
  • Use Arial fallback for headingsin 39 of 690, across 4 files
  • Use Georgia fallback for body textin 39 of 690, across 4 files
  • Maintain text hierarchy and formattingin 39 of 690, across 4 files
  • Use accent colors for non-text shapesin 38 of 690, across 3 files
  • Use RGB values for precise color matchingin 38 of 690, across 3 files
  • Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
  • Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
  • Use active voice instead of passive voicein 26 of 690, across 10 files
  • Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
  • Prioritize clarity over clevernessin 22 of 690, across 8 files

Said here and by no other author read

  • Read the blog context file before editing
  • Read the AI tells reference before editing
  • Cut magic adverbs and grandiose nouns
  • Replace AI-ese with plain language
  • Limit em dashes to three per piece
  • Rewrite heavily affected passages entirely

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.