toololis
✨

Prompt Quality Score

Paste prompt — get rating + improvements

📚
Learn more — how it works, FAQ & guide
Click to expand

Prompt Quality Score — 7-Dimension Heuristic

Heuristic prompt grader: clarity, specificity, role-prompting, output format, examples, constraints, edge-case handling. Concrete improvements per dimension.

How to use this tool

  1. 1

    Paste prompt

    Any prompt — chatbot, agent, system.

  2. 2

    Get score + flags

    7 dimensions assessed.

  3. 3

    Apply suggestions

    Concrete fixes per gap.

Frequently Asked Questions

What makes a good prompt?
Best practices (Anthropic, OpenAI guides): clear role, specific task, output format spec, examples, constraints, edge cases. Vague prompt = vague output. Specific prompt = ~3× better outputs.
How long should prompts be?
Depends. Simple: 1-2 sentences. Complex agent: 200-2000 tokens system prompt. Modern frontier models reward longer + more structured prompts up to ~5K tokens.
XML tags really help?
Yes for Claude (trained on them) and helpful for GPT. Wrapping examples in , instructions in , output spec in tags improves adherence ~15-25%.

You might also like

AI Team Cost Calculator

Estimate monthly AI API costs for teams of any size

Open

EU AI Act Risk Classifier

Classify your AI system — Prohibited, High, Limited, Minimal risk

Open

AI Budget Burn Predictor

Predict when your API budget runs out — month by month

Open
🔒
100% Privacy. This tool runs entirely in your browser. Your data is never uploaded to any server.