# dontriskit/awesome-ai-system-prompts

🧠 Curated collection of system prompts for top AI tools. Perfect for AI agent builders and prompt engineers. Incuding: ChatGPT, Claude, Perplexity, Manus, Claude-Code, Loveable, v0, Grok, same new, windsurf, notion, and MetaAI.

Repository: https://github.com/dontriskit/awesome-ai-system-prompts
Canonical: https://ross.abutalabs.com/products/awesome-ai-system-prompts
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2026-02-20T19:10:13+00:00

## Health v2 (maintenance only)
Score: 51/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 68, release rhythm 35, longevity 39
- inputs: {"age_days": 546, "days_push": 194, "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 6176, forks 904 (observed 2026-08-28T04:09:37.671356+00:00)

## What it is
A curated collection of leaked and documented system prompts from popular AI tools like ChatGPT, Claude, Perplexity, Manus, v0, and Claude Code, accompanied by a guide on crafting effective agentic prompts. It analyzes real-world prompts to extract patterns and best practices for building AI agents.

## Use cases
- study how ChatGPT or Claude structure their system prompts
- learn best practices for writing agentic AI system prompts
- find reference prompts when building my own AI agent
- understand how tools like v0 and Manus define tool usage in prompts
- research prompt engineering patterns for role definition and safety protocols
- compare system prompt conventions across different AI coding assistants

## When to choose
- you are building an AI agent and want real-world system prompt examples to model
- you are a prompt engineer studying how top AI products structure instructions
- you want a curated, organized reference of agentic prompt patterns

## When to avoid
- you need a runnable prompt management or evaluation library
- you want guaranteed up-to-date official prompts, since leaked prompts may change or be outdated
- you need production prompt tooling rather than reference material

## Facets
- artifact type: learning-resource
- maturity: active
- function: prompt-engineering, agent-framework, documentation
- domain: large-language-models, tutorials, awesome-lists
- platform: cross-platform
- tags: system-prompts, awesome-list, prompt-collection, agentic-ai, chatgpt, claude, cursor, v0, manus, ai-agents

## Member repositories
- dontriskit/awesome-ai-system-prompts (main) score 51

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:37.671356+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 2026-08-29T17:47:25.686012+00:00, confidence not recorded.
  - readme: https://github.com/dontriskit/awesome-ai-system-prompts (fetched 2026-08-28T04:09:37.671356+00:00, sha 9c9adf643b0d)
- Data as of 2026-08-30T08:39:29.467469+00:00.