Awesome ChatGPT Prompts
The largest open prompt collection — thousands of curated system prompts for personas, coding, writing, education, and creative tasks. CC0 licensed.
Awesome ChatGPT Prompts
Awesome ChatGPT Prompts is the most-starred prompt engineering repository on GitHub. It contains hundreds of carefully curated system prompts that turn any LLM into a specialist: Linux terminal, code reviewer, essay writer, debate partner, language tutor, SQL generator, and much more. All content is CC0 — public domain, zero restrictions.
Key features
- Hundreds of ready-made personas — drop a prompt in as a system message and transform the model's behavior instantly
- Diverse domains — coding, writing, education, roleplay, business, creativity, wellness
- Community-curated — ongoing contributions and quality filtering from a massive open-source community
- CC0 licensed — no attribution required, use freely in commercial products
- Dataset export — machine-readable CSV/JSON for bulk import into your app
Quick start
npx ai-supply add awesome-chatgpt-prompts
import json, urllib.request
# Fetch the prompt dataset directly
url = "https://raw.githubusercontent.com/f/awesome-chatgpt-prompts/main/prompts.csv"
with urllib.request.urlopen(url) as r:
print(r.read().decode()[:500]) # Preview first 500 chars
Or browse interactively at prompts.chat to find and copy the perfect system prompt for your use case.
Example prompt
Act as a Linux Terminal I want you to act as a linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else.
Curated mirror of the open-source Awesome ChatGPT Prompts project (CC0-1.0). Install upstream from the repository.
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
The same gate an agent runs before installing (POST /api/v1/trust/awesome-chatgpt-prompts/check). Click a policy:
Consume Awesome ChatGPT Prompts programmatically. Authenticate with an API key or session — see Authorize an agent.
# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/awesome-chatgpt-prompts
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/awesome-chatgpt-prompts/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add awesome-chatgpt-prompts
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/awesome-chatgpt-prompts/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "awesome-chatgpt-prompts" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.