# LouisShark/chatgpt_system_prompt

A collection of GPT system prompts and various prompt injection/leaking knowledge.

Repository: https://github.com/LouisShark/chatgpt_system_prompt
Canonical: https://ross.abutalabs.com/products/chatgpt_system_prompt
Language: HTML
License: MIT
License Family: permissive
Topics: gpt, prompt, prompt-engineering
Last push: 2026-08-14T14:21:50+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 35, longevity 74
- inputs: {"age_days": 1036, "days_push": 19, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 10745, forks 1459 (observed 2026-08-28T04:10:43.974554+00:00)

## What it is
A curated collection of system prompts extracted from ChatGPT, other AI products, and custom GPTs, along with knowledge about prompt injection and leaking techniques. It serves as an educational resource for learning prompt writing and protecting GPT instructions.

## Use cases
- study real-world chatgpt system prompts
- learn how to write better system prompts
- understand prompt injection and leaking techniques
- protect my custom gpt instructions from extraction
- find system prompts for a specific gpt
- learn how to create custom gpts

## When to choose
- you want to study real system prompts from popular AI products and custom GPTs
- you want to learn prompt engineering by example
- you want to understand and defend against prompt injection attacks

## When to avoid
- you need a tool or library to programmatically run prompts
- you want production-ready prompt management software
- you expect polished documentation rather than a browsable prompt archive

## Facets
- artifact type: learning-resource
- maturity: active
- function: prompt-engineering, security, documentation
- domain: large-language-models, artificial-intelligence, security, tutorials
- platform: -
- tags: system-prompts, chatgpt, custom-gpts, prompt-injection, prompt-leaking, collection, web-server

## Member repositories
- LouisShark/chatgpt_system_prompt (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:43.974554+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 2026-08-29T17:17:55.110067+00:00, confidence not recorded.
  - readme: https://github.com/LouisShark/chatgpt_system_prompt (fetched 2026-08-28T04:10:43.974554+00:00, sha b8642319a567)
- Data as of 2026-08-30T08:39:29.467469+00:00.