content-humanizer

rewrite AI-sounding content (store copy, emails, social posts) so it reads like a person wrote it, not a committee — use when content feels robotic, generic…

Skill by Hugofsco

IndexedMIT

Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/hugofsco-content-humanizer

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

rewrite AI-sounding content (store copy, emails, social posts) so it reads like a person wrote it, not a committee — use when content feels robotic, generic, or reads like "delve into the landscape"

Use cases: writing

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found
Runs as: Python package

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/content-humanizer

What's inside

Skill name: content-humanizer
Description: rewrite AI-sounding content (store copy, emails, social posts) so it reads like a person wrote it, not a committee — use when content feels robotic, generic, or reads like "delve into the landscape"
License: MIT
Instructions: 23 lines in SKILL.md · view on GitHub

Before installing

Ships executable scripts

Files (2)

SKILL.md
humanizer_scorer.py · scripts/

SKILL.md (first lines)

# Content humanizer

Score first, don't guess: `python3 skills/content-humanizer/scripts/humanizer_scorer.py <draft.md> --json`
→ 0-100. **80+** light polish only. **60-79** targeted pattern removal. **Below 60**
the AI fingerprint is too dense for a patch job — rewrite it, don't edit it. Re-score
after; the number has to move.

Kill on sight: "delve," "landscape," "crucial/vital/pivotal," "leverage," "furthermore/
moreover," "robust/comprehensive/holistic," "it's important to note that," any sentence
starting with a hedge. Replace, never just delete — "leverage" → "use," "robust" →
the actual number it handles.

Fix rhythm: AI writes uniform 18-22 word sentences. Vary it — short after long, a
one-word fragment for emphasis, a parenthetical aside.

Replace vague with specific: "many companies saw improvements" → name the company, the
year, the number. If you don't have one, say so honestly rather than inventing it —
"I haven't seen a controlled study on this, but in practice..." beats a fabricated stat.

If there's a brand voice on file, match it instead of writing generic-human. Otherwise
ask for one example of writing the user actually likes, then extract sentence length,
formality, and whether it uses humor — don't guess a voice and get it wrong.

From Hugofsco/oceano, MIT.

Signals

Stars: 0
Forks: 0
Open issues: 0
Last commit (this folder): Jul 5, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/Hugofsco/oceano
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from Hugofsco

Cite this page

content-humanizer skill. Agent Mart. https://agentmart.dev/skills/hugofsco-content-humanizer (last updated 2026-10-24)