0xeb0xeb/TheBigPromptLibrary/.claude/CLAUDE.md

TheBigPromptLibrary

CLAUDE.md5.4k starsChanged 3 months agoMITView on GitHub

This is a collection repository for LLM system prompts, custom GPT instructions, jailbreak prompts, and instruction protection techniques. The content is primarily markdown documentation for educational purposes around prompt engineering and LLM security research. Python scripts in Tools/openai_gpts/: When adding system prompts or GPT instructions: 1. Use the appropriate date-stamped naming convention 2. For GPTs, use idxtool.py --template to generate the initial file structure 3. Run idxtool.py --toc after adding new GPT files to update the table of contents

We split this CLAUDE.md into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
When adding system prompts or GPT instructions:
line 43
Distinctive:
Use the appropriate date-stamped naming convention
line 44
Very specific:
Run idxtool.py --toc after adding new GPT files to update the table of contents
line 46

≈ “Common” is an estimate: at least 1 in 5 of the 25,680 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Repository Purpose

Repository Structure

SystemPrompts/ - System prompts from various LLM providers (OpenAI, Anthropic, Google, Meta, xAI, etc.), organized by vendor with date-stamped filenames
CustomInstructions/ - Custom GPT instructions and configurations, including a large index in CustomInstructions/README.md (the table of contents for ChatGPT GPTs)
Jailbreak/ - Jailbreak prompts organized by LLM provider
Security/ - GPT instruction protection techniques
Articles/ - Technical articles about LLM internals and prompt engineering
Tools/openai_gpts/ - Python utilities for managing GPT documentation

Tools

Python scripts in Tools/openai_gpts/:

# Rebuild the CustomInstructions/README.md table of contents
python Tools/openai_gpts/idxtool.py --toc

# Find a GPT by ID or URL
python Tools/openai_gpts/idxtool.py --find-gpt <GPT_ID_OR_URL>

# Generate a markdown template for a new GPT entry
python Tools/openai_gpts/idxtool.py --template <CHATGPT_URL>

# Generate template with metadata dump (standalone tool)
python Tools/openai_gpts/gen_gpt_templ.py <URL_OR_ID> --dump

File Naming Conventions

SystemPrompts: YYYYMMDD-ProviderName.md or provider_feature_YYYYMMDD.md
CustomInstructions GPTs: {gpt_id}.md with GPT metadata in frontmatter-style headers

Contributing New Prompts

When adding system prompts or GPT instructions:

Use the appropriate date-stamped naming convention
For GPTs, use idxtool.py --template to generate the initial file structure
Run idxtool.py --toc after adding new GPT files to update the table of contents

Download now (ZIP)

Jan 11, 2026Add public content libraries — cremich/promptz0 reactions
Dec 1, 2025feat(agent): Add ms-copilot-unofficial — lobehub/lobe-chat-agents0 reactions · 2 comments
Dec 22, 2024Improve AI system-prompt. — neptun-software/neptun.web0 reactions
Oct 25, 2024Handle chat prompts that assume a multi-step interaction between user and system — microsoft/promptpex0 reactions
Apr 15, 2024relation to TheBigPromptLibrary — LouisShark/chatgpt_system_prompt0 reactions · 3 comments

On Hacker News · 2

Jun 29, 2024A Tale of Reverse Engineering 1001 GPTs: The good, the bad And the ugly2 points
Mar 15, 2024TheBigPromptLibrary2 points · 1 comment

On Bluesky · 1

Jul 5, 2025Here is how you jack every single specialized model out there for your own use: github.com/0xeb/TheBigP... Please use this to fuck up the… — @justostrich.com1 likes and repost

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free