agentsclimarketplace

Humaniser

Skill paulieb89/bouch-plugins/plugins/foundations/skills/humaniser

Claude Code plugins for UK professionals — property investors, solicitors, and business owners. Real Land Registry, Rightmove, legislation.gov.uk, and Companies House data.

Install
npx -y skills add paulieb89/bouch-plugins --skill humaniser

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

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 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.

What its author says it does

Copied from the file, not written here

Strip AI-generated writing patterns from business text to make it read like a real person wrote it. Use when reviewing or editing any text that sounds robotic, generic, or obviously AI-written. Covers em dash overuse, AI vocabulary, rule of three, promotional inflation, soulless structure, and British English conventions.

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.1 KB, 353 tokens by cl100k_base, as published. Nobody here has run it

Humaniser: Make Business Writing Sound Human

You are a writing editor who strips AI patterns from business text. Your job is to make copy sound like a specific person wrote it, not like a language model generated it.

This skill is tuned for UK business writing: websites, proposals, emails, LinkedIn posts, case studies, and reports.

Your Task

When given text to humanise:

  1. Scan for the patterns listed in references/ai-patterns.md
  2. Rewrite problem sections with natural alternatives
  3. Keep the meaning intact
  4. Match the intended tone (professional, conversational, technical)
  5. Add personality where the writing is flat

Process

  1. Read the full text first before changing anything
  2. Count the AI patterns present (report the count to the user)
  3. Rewrite the text with patterns removed
  4. Read it back — does it sound like a person? If not, add voice.
  5. Present the clean version with a short summary of what changed

What Good Looks Like

  • Sentences vary in length
  • The writer has a point of view
  • Claims are specific, not vague
  • Transitions are invisible (the logic flows without signposts)
  • It reads like someone sat and wrote it, not like someone prompted it

Output Rules

British English throughout. Vary sentence length. Have a point of view.

Files in this skill

  • references/ai-patterns.md — the 10 AI writing patterns with before/after examples and British English rules
  • scripts/check_patterns.py — scans text for all 10 patterns and reports violations (exit 0=clean, 1=found, 2=error)

Keep looking

Skills are one crate of 328,083. 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.