aboudjem/humanizer-skill

English | 简体中文

Make AI text sound like a real person wrote it. One Markdown file. 53 patterns, 5 voices, zero setup, and nothing leaves your machine.

Try it in your browser  ·  Install in 5 seconds  ·  Read the source

Same idea, two writers. The AI line stays flat. The human line jumps around. That jumpiness is the tell.

---

AI writing has a fingerprint. Every sentence runs about the same length. It reaches for the same safe words, and it pads with filler like “in today’s landscape.” Two bits of jargon worth knowing: how much your sentence lengths vary is called burstiness (people mix short and long, AI keeps them all one size), and those little giveaway habits are called AI tells.

Humanizer knows 53 of them. It finds them, scores the text, and rewrites it in a voice you pick. All from a single file your editor reads on your own machine.

Quickstart

Install once. It works in Claude Code, Cursor, Codex, opencode, and 70+ other AI editors (vercel-labs/skills):

npx skills add Aboudjem/humanizer-skill

Now score any text right in your editor. This just scans, it doesn’t rewrite:

/humanizer "In today's rapidly evolving landscape, AI is reshaping how we think about creativity." --mode detect --score

You get a number you can quote and the reasons behind it:

[Score: 84/100, Pure AI smell]

Patterns found: 5
| P4  | Promotional          | "rapidly evolving landscape" |
| P7  | AI Vocabulary        | "reshaping"                  |
| P22 | Filler               | "In today's"                 |
| P29 | Comprehensive Opening| meta-commentary              |
| P30 | Uniform Length       | sentences avg 19 words       |

The score runs 0 to 100. Lower is more human. Drop the flags and it rewrites instead of scanning: /humanizer "your text" --voice casual hands back the same idea in a real voice, and the score falls to single digits.

[!TIP] This is about writing better, not tricking detectors. Clean writing doesn’t set off AI detectors, because it skips the lazy habits they look for. Fix the writing and the detection sorts itself out.

---

Features

• 53 named patterns, from travel-brochure adjectives to invisible unicode tricks. The biggest open list of its kind.
• 5 voices: casual, professional, technical, warm, blunt. Each one changes the rhythm, not just a few words.
• 3 modes: detect (score it), rewrite (fix it), edit (change a Markdown file in place).
• A 0 to 100 AI-tell score on demand, so you can measure before and after.
• A guard against over-editing, so it sharpens real writing instead of flattening it.
• One Markdown file. No dependencies. No network calls. It runs standalone.
• Optional metrics CLI and CI check if you want a computed score in your pipeline.

---

Usage

/humanizer "text"                                rewrite it with the default voice
/humanizer "text" --voice casual                 pick a voice
/humanizer "text" --mode detect --score          scan only, add a 0 to 100 score
/humanizer --file docs/README.md --voice technical   fix a file in place
/humanizer "text" --aggressive --iterate 3       heavy rewrite, loop until the score bottoms out

Rewrite is the default, so you never have to name it.

Other flags: --mode picks detect, rewrite, or edit. --purpose layers on rules for an essay, email, marketing copy, technical doc, or general text. --iterate N runs the scan-rewrite loop up to 3 times. --aggressive uses a heavier hand. Drop a humanizer-context.md file in your project root with your own writing samples and banned words, and the skill folds it into whichever voice you chose.

---

More

---

Documentation

• Skill source and full pattern catalog: skills/humanizer/SKILL.md
• Pattern deep dives, triggers, and examples: references/patterns.md
• A full docs site (Docusaurus, ready to deploy) lives in docs-site/: npm --prefix docs-site install && npm --prefix docs-site run build

Contributing

Found a new AI pattern, or a cleaner fix? PRs welcome. Add a short entry to SKILL.md, put the deep dive and a before/after example in references/patterns.md, and keep the badge count, CI threshold, and CHANGELOG in sync. See CONTRIBUTING.md.

---

Built by Adam Boudjemaa · MIT License · No telemetry · No data collection