Does it rewrite my prompt or critique it?

It critiques and gives targeted fixes. For a full rewrite from a rough idea, use the Prompt Optimizer instead; use the reviewer when you already have a prompt to improve.

Which prompt types does it handle?

ChatGPT, Claude, and Gemini prompts, plus production system prompts, developer prompts, support-bot prompts, and agent prompts.

What model powers it, and is my prompt stored?

It uses Amazon Nova on AWS Bedrock. Your prompt is sent only to generate the review and is not stored; only aggregate usage counters are kept.

Yes, with a daily cap to keep it free for everyone.

Improve My Prompt

Reviews your prompt (Claude, ChatGPT, Gemini, or any LLM) against 12 rules: explicit role, context ordering, section delimiters, output format, few-shot examples, positive instructions, reasoning behind constraints, step breakdown, quantitative constraints, named audience, structured output, and grounding. Returns a numbered list of specific fixes and an overall score — does NOT rewrite your prompt. Powered by Amazon Nova Micro.

Review your prompt against 12 best-practice rules from Anthropic, OpenAI, and Google. Returns specific fixes, not a rewrite.

Paste your prompt0 / 8,000

Numbered feedback

The 12 rules checked

01 Explicit role/persona (You are a...)
02 Context before instruction
03 Section delimiters (XML / headers)
04 Output format specified
05 Few-shot examples for non-trivial tasks
06 Positive instructions over negative
07 Reasoning behind constraints
08 Multi-step tasks broken into steps
09 Quantitative constraints (5 bullets, not 'a few')
10 Audience or goal named
11 Structured output for extraction
12 Grounding for long-context prompts

Based on Anthropic's prompt engineering guide, OpenAI's best practices, and Google's Gemini prompting strategies.

Prompt review guides

Start with the specific prompt problem, then review the full prompt against the checklist.

ChatGPT ChecklistReview a ChatGPT prompt for role, context, task, constraints, output format, examples, audience, and grounding before testing it again.System PromptReview a production system prompt for scope, tool rules, refusal behavior, output contract, private-data handling, and eval coverage.Prompt DiagnosisDiagnose the common reasons an AI prompt fails: vague goals, missing context, conflicting constraints, no output format, and weak examples.Review vs RewriteDecide whether to critique an existing prompt with Improve My Prompt or rewrite a rough idea with the AI Prompt Optimizer.

Common Workflows

Use these patterns when you need this tool for a real publishing, documentation, or developer workflow.

Find why a ChatGPT or Claude prompt is underperforming

Builders who have a prompt that works sometimes but produces inconsistent, vague, or poorly formatted output.

Paste the prompt exactly as used
Review the score and numbered issues
Apply the specific fixes before testing again on real inputs

A clearer prompt with better role, context, constraints, examples, and output format.

Search intent: why is my ChatGPT prompt not working

Review a system prompt before shipping

Product teams adding an LLM prompt to a workflow, agent, support tool, or content generator.

Paste the system or developer prompt
Check for missing audience, delimiters, examples, and failure constraints
Update the prompt and run a small eval set

A production prompt that is easier to test and less likely to drift.

Search intent: system prompt review checklist

Turn a vague prompt into an actionable edit list

People who want critique and specific fixes rather than a full automatic rewrite.

Paste the rough prompt
Read the numbered improvement list
Apply the edits you agree with while preserving your intent

A prompt improvement checklist that keeps you in control of the final wording.

Search intent: improve my AI prompt with specific fixes

Next useful step

Test your AI fundamentals next

If this tool is part of your AI or developer workflow, the free CloudYeti diagnostic shows which AWS AI concepts you already know and where you are weak.

Take the AI diagnostic

Frequently Asked Questions

What does the prompt reviewer check?: It scores an existing prompt against prompt-quality rules — role, context, task, constraints, output format, examples, audience, and grounding — and returns specific edits instead of a vague rating.
Does it rewrite my prompt or critique it?: It critiques and gives targeted fixes. For a full rewrite from a rough idea, use the Prompt Optimizer instead; use the reviewer when you already have a prompt to improve.
Which prompt types does it handle?: ChatGPT, Claude, and Gemini prompts, plus production system prompts, developer prompts, support-bot prompts, and agent prompts.
What model powers it, and is my prompt stored?: It uses Amazon Nova on AWS Bedrock. Your prompt is sent only to generate the review and is not stored; only aggregate usage counters are kept.
Is it free?: Yes, with a daily cap to keep it free for everyone.

Related Tools

CLAUDE.md Reviewer

Paste your existing CLAUDE.md and get specific, numbered suggestions for vague rules, missing commands, repo boundaries, and token waste.

Word & Character Counter

Count words, characters, sentences, and reading time in Markdown. Free online Markdown-aware word counter.

Link Extractor

Extract all URLs and links from Markdown text. Free online Markdown link extractor.

Heading Extractor

Extract all headings from a Markdown document as a structured outline. Free online heading extractor.

About Improve My Prompt

Paste any LLM prompt and get specific, actionable fixes against 12 best-practice rules from Anthropic, OpenAI, and Google. Free, no login. This AI-backed tool sends your input to MarkdownMe's capped Amazon Bedrock endpoint to generate the result. No account is required. MarkdownMe provides free, fast, and reliable Markdown tools for developers, writers, and anyone who works with Markdown.