# AI Check

Use when someone asks "does this sound AI?", "check if this is AI-written", "what gives...

- Repository: https://github.com/harshaneel/humanize (597 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-09-22
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add harshaneel/humanize --skill ai-check -g -a claude-code -y`
Codex: `npx skills add harshaneel/humanize --skill ai-check -g -a codex -y`
Cursor: `npx skills add harshaneel/humanize --skill ai-check -g -a cursor -y`
Gemini CLI: `npx skills add harshaneel/humanize --skill ai-check -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add harshaneel/humanize`

## Description

Use when someone asks "does this sound AI?", "check if this is AI-written", "what gives this away as AI", "run ai-check on this", or "score this text". Also use when reviewing a draft for AI tells before publishing, or when a piece of text reads as suspiciously polished, generic, or pattern-y and the user wants a forensic breakdown of why.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# AI-Check Skill

Forensic analysis of text for AI-generation signals. Grounded in the published detection
literature (Wu et al. 2025, Mitchell et al. 2023, Kujur 2025, AAAI 2025 shared task).

The output is a structured report, not a vague judgment. Every fired signal cites evidence.

---

## The nine signal categories

Score each category 0, 3:
- 0 = No signal detected (human-consistent)
- 1 = Weak signal (possible AI, could be human)
- 2 = Moderate signal (likely AI pattern)
- 3 = Strong signal (near-certain AI pattern)

**Severity-to-score mapping (use for every category):**

| Evidence in category | Score |
|---|---|
| No flagged instances | 0 |
| One weak instance, or vague unease without a specific quote | 1 |
| One moderate instance, or two or more weak instances | 2 |
| One strong instance, or two or more moderate instances, or four or more weak instances | 3 |

**Double-counting policy:** a single phrase can fire at most two distinct signals when the phrase is genuinely diagnostic for both. Example: "it is important to note that" is both Signal A (banned vocabulary) and Signal C (institutional hedge). Log it under both, but the same phrase cannot count as two separate weak instances inside the same category.

**Total score cap:** 9 categories × 3 = 27 maximum.

### Signal A: Perplexity (word predictability)

Look for vocabulary that is maximally safe and expected, words that are technically correct
but never the most precise or interesting choice a knowledgeable human would make.

The rest: https://github.com/harshaneel/humanize/blob/HEAD/plugins/humanize/skills/ai-check/SKILL.md