ai-check

humanize

LLM-agnostic skills that make AI writing sound human and relatable.
Grounded in 50+ peer-reviewed sources through April 2026.

Works in any LLM agent: Claude Code, Codex CLI, ChatGPT, Gemini, Cursor, Aider, OpenCode, Continue, Copilot. The install paths differ; the skill content is identical.

---

Contents

Get started

• What's inside — the two skills, at a glance
• Installation — plugin marketplace for Claude Code and Codex, one command for everything else
• Usage — how to invoke each skill
• Benchmark — 25 inputs, two independent scorers

Why the skills work

• Background — the gap between AI and human writing
• The detection literature — perplexity, burstiness, stylometry, discourse
• Detection methodology taxonomy — zero-shot, classifier, watermarking, hybrid
• What the research shows about surface rewriting — why the same edits that read human also move the numbers
• The nine humanization levers — the rules the skill applies

Limits and what closes them

• Accuracy benchmarks from the literature — detector accuracy numbers from published research
• Known limitations — what this skill does not guarantee
• What this rule-based approach cannot do (the ceiling) — the learned-classifier ceiling and why it exists
• Complementary techniques — what closes the gap (cross-model paraphrase, base-model rewriting, manual edits)

Maintenance & references

• Updating · Uninstalling · Contributing · License · Citation · References

---

What's inside

Both are static rule-based skills (single SKILL.md per skill, zero runtime dependencies). Six advanced hybrid techniques are documented in the humanize skill for high-stakes use.

What "static" means here. No models trained, no API calls, no detector-in-the-loop. The skill is a rulebook the host LLM follows. The detection research is the measuring instrument, not the target: it tells us precisely where AI prose diverges from human prose, and closing those gaps is what makes the writing read as human. That the same edits also lower perplexity-based scores (ZeroGPT, QuillBot) is a consequence, not the goal. The "What this approach cannot do" section below is honest about the learned-classifier ceiling (Grammarly, GPTZero) and what additional steps close that gap.

---

Installation

This repo bundles two skills (humanize and ai-check) under plugins/. It doubles as a plugin marketplace for Claude Code and Codex, so those two can install the skills without cloning. Every other agent reads the skills from disk, which install.sh sets up.

Claude Code

This repo is a Claude Code plugin marketplace. Add it once, then install it:

claude plugin marketplace add harshaneel/humanize
claude plugin install humanize@humanize

That one plugin carries both skills.

Restart Claude Code and both skills are live. Update later with claude plugin update humanize.

Prefer a plain clone? The install script symlinks the skills into ~/.claude/skills/, so git pull updates apply automatically:

git clone https://github.com/harshaneel/humanize.git
cd humanize && ./install.sh

Codex CLI

Codex reads the same repo as a plugin marketplace:

codex plugin marketplace add harshaneel/humanize
codex plugin add humanize@humanize

Refresh the snapshot later with codex plugin marketplace upgrade.

Or install the skills straight into ~/.codex/skills/:

git clone https://github.com/harshaneel/humanize.git
cd humanize && ./install.sh codex

Install everywhere in one command

If you use multiple agents (Claude Code, Codex CLI, ChatGPT desktop), install to all three skill directories at once:

git clone https://github.com/harshaneel/humanize.git
cd humanize && ./install.sh all

This installs to ~/.claude/skills/, ~/.codex/skills/, and ~/.agents/skills/. Add --copy if you prefer self-contained files over symlinks.

ChatGPT desktop / OpenAI agents

ChatGPT desktop and several OpenAI agent harnesses read from ~/.agents/skills/.

git clone https://github.com/harshaneel/humanize.git
mkdir -p ~/.agents/skills
cp -R humanize/plugins/humanize/skills/humanize humanize/plugins/humanize/skills/ai-check ~/.agents/skills/

Or cd humanize && ./install.sh chatgpt to use the install script.

OpenCode

git clone https://github.com/harshaneel/humanize.git
mkdir -p ~/.config/opencode/skills
cp -R humanize/plugins/humanize/skills/humanize humanize/plugins/humanize/skills/ai-check ~/.config/opencode/skills/

Note: OpenCode also scans ~/.claude/skills/ for compatibility, so ./install.sh covers both tools. Cloning the repo straight into ~/.claude/skills/ no longer works, because the skills sit under plugins/.

Claude.ai / Claude Desktop

The web and desktop apps don't read from disk. Upload through the UI instead:

1. Open Settings → Capabilities → Skills.
2. Click Create skill and upload plugins/humanize/skills/humanize/SKILL.md.
3. Repeat with plugins/humanize/skills/ai-check/SKILL.md.
4. Toggle each skill on in conversations where you want it active.

Any other chat agent (ChatGPT, Gemini, Cursor, Aider, Cline)

No install needed. Open plugins/humanize/skills/humanize/SKILL.md, copy the raw contents, and paste into a new conversation prefaced with: "Use these instructions whenever I ask you to humanize text." Same for plugins/humanize/skills/ai-check/SKILL.md.

---

Usage

Humanize

/humanize:humanize

[paste your text here]

Installed from a clone rather than the marketplace? The skill is just /humanize.

Or ask the model directly:

Please humanize this text: [your text]

AI-check

/humanize:ai-check

[paste your text here]

From a clone, it is just /ai-check.

Or ask the model directly:

Does this sound AI? [your text]

ai-check returns a structured report: verdict (Human / Likely Human / Uncertain /