Skip to content
SkillCheatSheet Sign in

humanizer

An AI agent skill from blader/humanizer, scored 69 out of 100 by code.

69/ 100C

Code score by group

  • Spec20/20
  • Description12/20
  • Procedure15/15
  • Done criteria4/15
  • Resources3/10
  • Scripts3/8
  • Safety7/7
  • Upkeep5/5

It loses the most points in Done criteria (11), the group that checks whether there is a checklist and a step that verifies the work.

What the author says it does

Rewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes everywhere, inflated claims, sales language, stock AI words, bold labels, or filler.

This is the description in the skill's own SKILL.md, written by its author, not by SkillCheatSheet.

Repository
blader/humanizer
Folder
(repository root)
License
MIT
GitHub stars
68,193
SKILL.md lines
499
Other files
14

Add humanizer to your agent

npx skills add blader/humanizer --skill humanizer

The command uses the open skills CLI. A skill is instructions and scripts your agent will follow, so read it first: open the folder on GitHub at the commit that was scored.

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.