Todos los casos de uso

Ingeniería

Escape Pod skill: build a local TensorFold assistant, then prove it offline

Cloud agents are great until the network drops — and you still want a local brain on the laptop.

Compartir

Qué dolía

Ash Hart (@ashxhart) asked Grok Bot to fire itself off the machine and stand up a private AI with TensorFold, then switched off Wi-Fi — the local model kept running. He posted the reusable 'Grok Escape Pod' skill prompt: detect hardware without asking for secrets, check TensorFold compatibility, require approval before installs or downloads, serve an open-weight model, verify online then offline, write an AI Independence Receipt with measured tokens/sec, and save the workflow as a skill. Grok Bot itself still needs connectivity; the local assistant does not after setup. Not affiliated with xAI.

Qué instalar o crear

Author-quoted skill with approval gates, offline proof, and a measured receipt.

Bots

  • Escape Pod guide

    Walks the TensorFold offline setup and writes the receipt.

Plugins

  • Ninguno el primer día. Sigue los pasos del primer uso.

Rutinas

  • Ninguna en el primer uso. Mira primero una pasada manual.

El prompt

Grok Escape Pod skill (author-quoted)

Quoted from @ashxhart — as published. Do not invent a second system prompt.

Create a reusable skill called Grok Escape Pod.

Goal: Help a user build a fully offline AI assistant on their compatible Mac or NVIDIA GPU using TensorFold (https://tensorfold.dev).

1. Determine operating system, GPU, memory and available disk space without requesting passwords or secrets.

2. Check actual TensorFold hardware and model compatibility.

3. Explain downloads and request explicit approval before any installation, shell execution, or model download. Never execute fetched installation scripts without the user's review.

4. Provide the official TensorFold installation path and guide the user through serving a compatible open-weight model.

5. Create or configure a simple local chat interface using TensorFold's documented local API.

6. Verify online functionality, then instruct the user to disconnect their internet and test again.

7. Collect measured tokens per second, model, GPU, test conditions and whether offline execution passed.

8. Create a shareable AI Independence Receipt using only verified measurements. Do not claim that Grok itself is running locally.

9. Explain that Grok Bot requires connectivity, but the separate local TensorFold assistant does not after setup.

10. Save this workflow as a reusable skill and provide setup instructions suitable for a public Grok Bot template.

Primer uso

  1. 1Read https://x.com/ashxhart/status/2110860076403536289 (credit @ashxhart).
  2. 2Paste the author's Escape Pod skill prompt into your bot.
  3. 3Approve each install and model download after you review the commands.
  4. 4Test chat online, then disconnect Wi-Fi and test again.
  5. 5Keep the measured Independence Receipt; save the workflow as a skill.

Valla de aprobación

No installs, shell runs, or model downloads without your review. Don't claim Grok itself is local.

Qué ajustar

Steal the Escape Pod checklist and the offline proof step.

Fuente

Ash Hart @ashxhart · Publicación original

Sin afiliación con xAI. No escribimos este prompt. Siguen aplicando las condiciones de las plantillas de terceros.

Explorar plantillas

Explorar planos de equipo

Paquete Pro

¿Quieres la configuración completa, no solo la idea?

Los paquetes Pro te dan el texto de la tarea, los prompts, los horarios y los tropiezos de los casos de uso más populares.

Ver Pro