Skip to content
mcp/skillhub

Agent Skill

Humanizer skill

humanizerblader/humanizerSKILL.md

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. Based on Wikipedia's "Signs of AI writing."

59kMIT

always on

81 tokname + description

once used

6,948 tokSKILL.md body

bundled files

11 scripts

repo stars

59kGitHub

Install the Humanizer skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/blader/humanizer --skill humanizer

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/blader/humanizer.git /tmp/humanizer
mkdir -p ~/.claude/skills
cp -R /tmp/humanizer ~/.claude/skills/humanizer

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description81 tok
When the agent uses itThe SKILL.md instructions6,948 tok
Only if opened1 bundled files (5 KB)varies

Until it is used, humanizer costs about 17× less than the median MCP server we measured (1,362 tokens on every turn). Skills vs MCP study

Checks

  • Ships scripts the agent can run. Read them before installing.
  • The instructions are over 5,000 tokens, the Agent Skills specification's guideline for SKILL.md.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Humanizer: remove AI writing patterns
  • Why AI text sounds the way it does
  • How to work
  • Voice
  • What to return
  • A. Staging instead of stating
  • 1. Not X but Y
  • 2. One-line closers and dramatic fragments
  • 3. Sayings that sound deep
  • 4. Staged run-up before the point
  • 5. Arguing with no one
  • B. Rhythm by rule
  • 6. Forced triads
  • 7. Repeated sentence openings
  • 8. Dashes as the universal connector
  • 9. Stacked qualifiers
  • 10. Hyphenated pairs everywhere
  • 11. Passive voice and missing subjects
  • C. Inflation and borrowed authority
  • 12. Overused AI words
  • 13. Inflated significance
  • 14. Vague connection or association
  • 15. Shallow -ing riders
  • 16. Sales language