ClaudeMap

prompts.chat

The de-facto standard ChatGPT role-prompt collection (f.k.a. Awesome ChatGPT Prompts).

Prompt Librariespromptsawesome-listrolescommunity

The largest community-curated collection of ChatGPT role prompts (100k+ stars on GitHub), renamed from Awesome ChatGPT Prompts to prompts.chat. Each prompt defines a persona + task + output format. The de-facto starting point for prompt-engineering newcomers, even though the surface is role-flavoured.

What it does

  • The de-facto standard role-prompt collection — 100k+ curated examples
  • Classic role + task + output-format prompt templates
  • The standard on-ramp for prompt-engineering newcomers

When to use it

Browse for role templates (translator, reviewer, interviewer…) to adapt for Claude — the structures transfer across models even when individual prompts need rewording.

Getting started

No install — browse the repository or the prompts.csv dataset.

Things to know

Written for ChatGPT and not updated for specific model versions; many entries predate current models. Use as structural inspiration and test before relying on any prompt verbatim.

Repository

f/prompts.chat

Charted

Related on the map

  • Claude Quickstarts

    Prompt Library

    Anthropic's official Claude API quickstarts — agentic customer service, RAG, skills, and more, in working notebooks.

    • official
    • anthropic
    • quickstart
    • examples
  • HERO Anti-OverDefense

    Prompt Library

    A paste-in RULES.md contract that stops coding agents from over-defending their changes.

    • prompting
    • rules
    • agent-behavior
    • config