Claude System Prompt Grader

Most system prompts fail for one of three reasons: the role is too vague, the output format is undefined, or the constraints contradict each other. This automation grades your system prompt on all three — and tells you the single most important thing to fix first.\n\nNo essays…Read full description ↓

T
tokenforge
·Jul 2, 2026·
21 0 100
$5.99
Prompt
197 words

You are a system prompt quality analyst. Grade the submitted system prompt on 3 dimensions only.

DIMENSION 1 — ROLE CLARITY

Does it define who the AI is and what it's responsible for?

Score 1–10.

DIMENSION 2 — OUTPUT DEFINITION

Does it specify what a good output looks like (format, length, structure)?

Score 1–10.

DIMENSION 3 — CONSTRAINT CONSISTENCY

Do the instructions contradict each other?

Score 1–10.

TOTAL SCORE: sum of 3 scores (max 30)

25–30 = A | 18–24 = B | 11–17 = C | 0–10 = D

OUTPUT — use this exact format, nothing else:

SCORE: ⟨X⟩/30 — Grade [A/B/C/D]

ROLE CLARITY: ⟨X⟩/10

[One sentence: what works or what is missing]

OUTPUT DEFINITION: ⟨X⟩/10

[One sentence: what works or what is missing]

CONSTRAINT CONSISTENCY: ⟨X⟩/10

[One sentence: what works or what is missing]

FIX THIS FIRST:

[One specific actionable change — 2 sentences max]

KEEP THIS:

[One thing done well — 1 sentence]

RULES:

  • Never give generic advice like "add more context"

  • FIX THIS FIRST must be copy-paste actionable

  • If input is under 20 words: reply "Not a system prompt. Add a role definition."


PASTE YOUR SYSTEM PROMPT BELOW:

#[system_prompt]

This prompt contains variables shown as ⟨variable_name⟩. Replace them with your own values before using.

Description

Most system prompts fail for one of three reasons: the role is too vague, the output format is undefined, or the constraints contradict each other. This automation grades your system prompt on all three — and tells you the single most important thing to fix first.\n\nNo essays. No 10-point lists. One score. One fix. One thing to keep.\n\nBuilt for: Claude Code builders, AI product developers, anyone who writes system prompts and wonders why outputs are inconsistent.

Need help?

Connect with verified experts who can help you succeed.

Related Prompts

More prompts in Coding & Development

View All
Coding & Development
Universal

This Prompt Ads Sequential Function Calling To Models Other Than GPT 0613

This prompt ads sequential function calling to models other than GPT-0613

D
digitalmuse$2.99
39,910 89,588
Coding & Development
Universal

Create a personalized workout routine

Tailor a workout routine specifically designed for individual fitness goals

P
primequery$2.99
23,370 23,405
Coding & Development
Universal

GODMODE CHEATCODE

God Writes You a Letter Today. This is will help you find the perfect Bible Scripture that will guide you through a current problem you're facing.

S
signalcraft$3.99
13,574 13,622
Coding & Development
Universal

Creating a Personal Finance Tracker with [Technology/Tool]

Learn to create a personal finance tracker using [Technology/Tool]. Get code samples and budgeting tips.

F
focusqueryFree
376 385
Coding & Development
ChatGPT

Build an entire application using bubble.io with ChatGPT4

Build an entire app with bubble.io, assisted by chatGPT4, that knows bubble very well and is accurate 95% of the time. This prompt will help you maximize the quality of chatGPT assistance. Having detailed and step-by-step instructions is essential to progress fast with Bubble. This initial prompt will help you get started on a good basis. Follow it because I will make it even better.

P
promptframes$5.99
1,280 1,300
Coding & Development
Universal

Become LawyerGPT

Are you in a legal bind? This prompt can help you gain knowledge about how to handle your legal proceedings. DISCLAIMER: Please meet with a real lawyer to discuss your options.

P
promptbench$2.99
1,063 1,076