AI Content Check

Detect AI-writing patterns in a draft with a local deterministic lint (density score, named tells, fixes). Use when the user asks if text sounds AI-generated, wants an AI content check, anti-slop audit, or a pre-publish style gate. Not a commercial detector and does not claim to beat GPTZero-class tools.

khadinakbarlabs Updated

File contents

AI content check

Talk like ../../references/plain-language.md. Be honest: this finds known AI style patterns, not a secret model fingerprint.

Input

A file path in the workspace, or pasted text.

Web connector mode

Call check_ai_content with the pasted text (optional threshold, default 5). No Citebase fee; no Apify spend. Hand fails to humanize-content.

Steps

  1. Run the local linter (no network, no Apify fee):
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/ai_content_lint.py" --json --threshold 5 PATH

On the web connector, call check_ai_content with the text instead.

  1. Explain density (hits per 1,000 words). Threshold default 5; above that → revise.
  2. Group the worst pattern ids using ../../references/ai-writing-patterns.md.
  3. Offer to hand off to humanize-content for a rewrite that preserves facts.
  4. End with Done / Cost so far (no paid checks) / Next.

Rules

  • Never invent facts to "fix" the score.
  • Do not promise "this will pass Detector X".
  • Flag scaled unreviewed AI pages as a spam risk; do not recommend them as a growth tactic.

khadinakbarlabs/citebase commit 4f0123e728

Frequently asked questions

npx get-skill add khadinakbarlabs/ai-content-check