agentleFS
alex-voloshin-devalex-voloshin-dev/ai-skills/.agents/skills/humanizer/SKILL.md

humanizer

Skill2 starsChanged 6 months agoMITView on GitHub

Remove signs of AI-generated writing from text. Use when editing, reviewing, or producing any public-facing text — blog posts, social media, UI copy, emails, landing pages, documentation. Detects and fixes AI patterns including inflated symbolism, promotional language, vague attributions, em dash overuse, rule of three, AI vocabulary, negative parallelisms, sycophantic tone, and filler phrases.

187 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

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 AzureSkill

    economy-mode

    Shifts Layer 3 model selection to cost-optimized alternatives when economy mode is active.

    Also in 4 projects that use this

  • petermuirurithuoSkill

    personal-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

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 174 edited versions we read keep these.

  • 7

    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
  1. Distinctive:

    Every sentence same length and structure

    line 32
  2. Distinctive:

    No opinions, just neutral reporting

    line 33
  3. Distinctive:

    No uncertainty or mixed feelings acknowledged

    line 34
  4. Distinctive:

    No first-person perspective when appropriate

    line 35
  5. Distinctive:

    No humor, edge, or personality

    line 36
  6. Distinctive:

    Use "I" when it fits — first person is honest, not unprofessional

    line 42
  7. Distinctive:

    When humanizing text, provide:

    line 80

“Common” is measured: kept by at least 6 in 10 of the 174 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Humanizer

Identifies and removes signs of AI-generated text. Makes writing sound natural and human. Based on Wikipedia's "Signs of AI writing" guide maintained by WikiProject AI Cleanup.

When to Use

  • Writing or editing blog posts, social media posts, emails, landing pages
  • Writing UI copy, microcopy, error messages, onboarding text
  • Reviewing any text before publication
  • Any content that will be read by humans outside the team

Process

  1. Identify AI patterns — scan for the patterns listed below
  2. Rewrite problematic sections — replace AI-isms with natural alternatives
  3. Preserve meaning — keep the core message intact
  4. Maintain voice — match the intended tone (formal, casual, technical)
  5. Add soul — inject actual personality, not just remove bad patterns
  6. Anti-AI audit — ask "What makes this obviously AI generated?", list remaining tells, then revise

Adding Soul

Avoiding AI patterns is half the job. Sterile, voiceless writing is just as obvious.

Signs of soulless writing:

  • Every sentence same length and structure
  • No opinions, just neutral reporting
  • No uncertainty or mixed feelings acknowledged
  • No first-person perspective when appropriate
  • No humor, edge, or personality

How to fix:

  • Have opinions — react to facts, do not just report them
  • Vary rhythm — short punchy sentences mixed with longer ones
  • Acknowledge complexity — "impressive but unsettling" beats "impressive"
  • Use "I" when it fits — first person is honest, not unprofessional
  • Let some mess in — tangents and asides are human
  • Be specific about feelings — not "concerning" but "unsettling that agents churn away at 3am"

See ai-writing-patterns.md for the full pattern catalog with before/after examples.

Quick Reference — Pattern Categories

#PatternSignal Words
1Inflated significancestands as, testament, pivotal, vital role, broader, indelible mark
2Notability inflationindependent coverage, active social media presence
3Superficial -ing phraseshighlighting, ensuring, reflecting, symbolizing, showcasing
4Promotional languageboasts, vibrant, profound, nestled, groundbreaking, renowned, stunning
5Vague attributionsexperts argue, industry reports, some critics
6Formulaic challenges sectionsdespite challenges... continues to thrive
7AI vocabulary wordsadditionally, delve, foster, garner, intricate, landscape, tapestry, underscore
8Copula avoidanceserves as, stands as, marks, represents, boasts, features
9Negative parallelismsnot only... but, not just about... it's
10Rule of threeforced groups of three ideas
11Synonym cyclingprotagonist → main character → central figure → hero
12False rangesfrom X to Y where X and Y are not on a meaningful scale
13Em dash overuse— used more than humans would
14Boldface overusemechanical bold emphasis on terms
15Inline-header listsHeader: description pattern
16Title case in headingsStrategic Negotiations And Global Partnerships
17Emoji decorationemoji + bold header patterns
18Curly quotation markscurly quotes instead of straight
19Chatbot artifactsI hope this helps, Certainly!, Would you like...
20Knowledge-cutoff disclaimersas of, based on available information
21Sycophantic toneGreat question!, You're absolutely right!
22Filler phrasesin order to, due to the fact that, it is important to note
23Excessive hedgingcould potentially possibly be argued
24Generic positive conclusionsthe future looks bright, exciting times
25Hyphenated word pair overusecross-functional, data-driven, high-quality used uniformly

Output Format

When humanizing text, provide:

  1. Draft rewrite — cleaned version
  2. AI tells audit — brief bullets listing remaining AI signals
  3. Final rewrite — revised after the audit
  4. Changes summary — what was fixed (optional, if helpful)

Integration

  • Rule: humanize-content rule auto-activates this skill for all public-facing content
  • Used by workflows: blog-post skill (step 4.5), marketing skill (all content operations), docs skill (public-facing content)
  • Used by skill: content-creation (Gate 7: Humanization)
  • Companion resource: ai-writing-patterns.md (full pattern catalog with examples)

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.