# xai-org/grok-prompts

Prompts for our Grok chat assistant and the `@grok` bot on X.

Repository: https://github.com/xai-org/grok-prompts
Canonical: https://ross.abutalabs.com/products/grok-prompts
Language: Jinja
License: AGPL-3.0
License Family: copyleft
Last push: 2025-11-17T20:40:23+00:00

## Health v2 (maintenance only)
Score: 42/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 52, release rhythm 35, longevity 33
- inputs: {"age_days": 475, "days_push": 289, "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 4391, forks 493 (observed 2026-08-28T04:08:47.233203+00:00)

## What it is
An official xAI repository publishing the system prompts used for the Grok chat assistant, the @grok bot on X, and xAI API safety prefixes. The prompts are provided as Jinja templates and text files and are updated regularly.

## Use cases
- study how a production LLM system prompt is written
- compare Grok 3 and Grok 4 system prompts
- learn prompt engineering from real-world examples
- see safety prompt prefixes used by an AI provider
- research how chat assistants handle tools and thinking modes

## When to choose
- you want to inspect or learn from actual production system prompts for Grok models
- you are researching prompt design, safety instructions, or tool-use behavior of commercial chatbots

## When to avoid
- you need runnable software or a library - this is only a collection of prompt files
- you need prompts for models other than Grok
- you cannot comply with the AGPL-3.0 license

## Facets
- artifact type: dataset
- maturity: active
- function: prompt-engineering, llm-inference, chatbot
- domain: large-language-models, artificial-intelligence, chatbots
- platform: cross-platform
- tags: system-prompts, grok, jinja-templates, xai, prompt-collection

## Member repositories
- xai-org/grok-prompts (main) score 42

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:47.233203+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 2026-08-29T18:21:12.296912+00:00, confidence not recorded.
  - readme: https://github.com/xai-org/grok-prompts (fetched 2026-08-28T04:08:47.233203+00:00, sha d1bd1d00346c)
- Data as of 2026-08-30T08:39:29.467469+00:00.