# aws-samples/claude-prompt-generator

Repository: https://github.com/aws-samples/claude-prompt-generator
Canonical: https://ross.abutalabs.com/products/claude-prompt-generator
Language: Python
License: Apache-2.0
License Family: permissive
Archived: true
Last push: 2025-10-27T18:27:11+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 49, release rhythm 35, longevity 63
- inputs: {"age_days": 888, "days_push": 310, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1314, forks 122 (observed 2026-08-28T04:04:20.414519+00:00)

## What it is
A Python web application that generates, translates, and iteratively evaluates prompts for Anthropic Claude 3 via AWS Bedrock, including converting existing GPT prompts into Claude-style prompts with XML tags. It provides a Gradio-style UI for generating initial prompts, comparing outputs, and refining them with human-in-the-loop review.

## Use cases
- generate claude prompts from scratch
- convert gpt prompts to claude prompts
- evaluate and compare prompt outputs
- iterate on prompts until output quality is good
- learn claude 3 prompt engineering best practices
- test prompts against aws bedrock

## When to choose
- you use AWS Bedrock and want Claude-optimized prompts
- you are migrating prompts from OpenAI GPT to Claude
- you want automated plus manual prompt evaluation in one tool

## When to avoid
- you don't have an AWS account or Bedrock access
- you need prompt tooling for models other than Claude/GPT
- you want a fully automated pipeline with no human review

## Facets
- artifact type: application
- maturity: active
- function: prompt-engineering, llm-inference, llm-training, web-framework
- domain: large-language-models, artificial-intelligence, developer-tools
- platform: python, self-hosted
- tags: aws-bedrock, claude, prompt-evaluation, gradio, openai, meta-prompting, web-server

## Member repositories
- aws-samples/claude-prompt-generator (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:20.414519+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:48:45.511770+00:00, confidence not recorded.
  - readme: https://github.com/aws-samples/claude-prompt-generator (fetched 2026-08-28T04:04:20.414519+00:00, sha 756548075121)
- Data as of 2026-08-30T08:39:29.467469+00:00.