agentleFS
Sign inStart free
StormixStormix/transcripts-mcp/.agents/skills/humanizer/SKILL.md

humanizer

Skill8 starsChanged 2 months agoMITView on GitHub

Remove AI tells from prose so it reads like a person wrote it.

188 other projects use a version of this.

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

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 2

    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:

    Read the whole thing once.

    line 37
  2. Distinctive:

    Read it out loud. If your mouth trips, the reader's eye trips.

    line 40

“Common” is measured: kept by at least 6 in 10 of the 175 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

Strip the visible signature of LLM-generated writing from a piece of text. Use when reviewing your own drafts, editing a teammate's, or rewriting AI output before it goes anywhere a reader will see it.

The point is not to be undetectable. The point is to be honest — text that reads like a real person made it because a real person made the calls.

When to use

  • You wrote a draft alongside an LLM and the seams show.
  • A doc, README, blog post, PR description or product copy needs a final pass.
  • You are reviewing someone else's writing and it feels off but you can't say why.

What to look for

  • Inflated symbolism. "X represents a paradigm shift in how we think about Y." Cut.
  • Promotional voice in neutral contexts. "Robust, scalable, cutting-edge." Replace with concrete claims or delete.
  • Superficial -ing analyses. "Highlighting", "showcasing", "emphasizing" stacked end to end. Pick verbs that do work.
  • Vague attribution. "Some experts argue" — name them or drop the claim.
  • Em dash flood. One per paragraph at most. Otherwise rewrite.
  • Rule of three. Three-item lists where two would do, especially when items are near-synonyms. Compress.
  • AI vocabulary. "Delve", "leverage", "tapestry", "underscores", "in the realm of", "navigate the complexities of". Replace.
  • Negative parallelism. "Not just X, but Y." Most of the time Y alone is the actual sentence.
  • Filler. "It's important to note that…", "In conclusion…", "Ultimately…". Cut.
  • Hedging without commitment. "May potentially be able to help in some cases." Pick a side.

How to apply

  1. Read the whole thing once. Mark anything that triggers the list above.
  2. Rewrite for voice: shorter sentences, concrete subjects, working verbs.
  3. Cut anything that does not advance the argument.
  4. Read it out loud. If your mouth trips, the reader's eye trips.

Output should feel like

  • Specific. Names, numbers, examples.
  • Slightly uneven cadence — humans do not write to a metronome.
  • Comfortable saying "I think" or "I don't know".

Related

  • [[frontend-design]] — same instinct, applied to UI.
  • [[skills-index]] — vault catalog.

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.

Check your setup, free