Nutter Tools
Nutter Tools

A free toolbox that runs in your browser. A tool for every job.

Your files never leave your device

Images

  • Convert images
  • Compress images
  • Resize images
  • Crop
  • Watermark

PDF & files

  • Merge PDFs
  • Split a PDF
  • Images to PDF
  • PDF to images
  • Remove photo location

Video & audio

  • Compress video
  • Convert video
  • Video to GIF
  • Convert audio
  • Trim audio

Everyday

  • QR codes
  • Passwords
  • Time zones
  • Unit converter
  • Word count
  • Webcam test

Developer

  • JSON formatter
  • Base64
  • Regex tester
  • Hashes
  • JWT decoder

Site

  • About
  • Contact
  • Settings
  • Privacy
  • Terms
  • Site map
  • llms.txt

Everyday

  • Images
  • Video
  • Audio
  • PDF & files
  • Text
  • QR codes
  • Units & math
  • Time & dates
  • Color
  • Passwords & IDs
  • Device tests
  • Sun & moon

For developers

  • JSON
  • Encoding
  • Regex & cron
  • Web & auth
  • Hashing & encryption
  • Config files
  • Network
  • Browser
  • AI
  • Fake data
© Nutter Toolsnutter.tools
  1. Home
  2. AI
  3. System prompt linter
Your files stay on your device

System prompt linter

Check a system prompt with fixed rules for contradictions, vague wording, placeholders, credentials and missing output contracts, scored out of 100.

This tool is in beta

Still being tested. If a result looks wrong, tell us.

Report a problem

Paste a system prompt, then press Check prompt.

Nothing here is sent to any model; every rule is plain JavaScript running in this tab, which is what makes the score usable as a review gate between prompt versions. Know what the rules cannot see: contradictions only register when both sides share wording, so "always refund" against "reject every refund request" passes; legitimate exceptions are flagged until you merge them into one rule; and the score compares versions of the same prompt, not different prompts against each other.

Prompt

Up to 100,000 characters

The rules are fixed: contradictions and conflicting limits, vague wording, repeated rules, literal placeholders, embedded credentials, and a missing output contract. Score starts at 100 and loses 15 per problem, 6 per warning, 2 per note, floored at zero.

Runs on this device. Nothing is uploaded.

More AI tools

  • Prompt diff
  • Context fit
  • Tokenizer playground
All AI tools

Was this tool useful?