AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Modal Serverless GPU Deployment Skill

Helps Claude write and deploy Python to Modal's serverless cloud with on-demand GPUs, volumes, web endpoints and cron jobs.

Dev & CodingIntermediate★ 33,030⑂ 3,248AI score 9/10Last updated: Aug 9, 2026

What it does

Gives Claude an accurate, current map of the Modal SDK (>=1.0) so it can generate working deployment code:

  • Remote functions and stateful classes (@app.function(), @app.cls(), @modal.enter())
  • GPU requests as strings (gpu="H100", "H100:4", fallback chains) with selection guidance
  • Container images built in Python (uv_pip_install, apt_install, build-time weight downloads)
  • Volumes for persistent weights/datasets, Secrets, FastAPI/ASGI endpoints, modal.Cron schedules
  • Autoscaling knobs, @modal.concurrent, .map() fan-out batch processing
  • modal.Sandbox for running untrusted or agent-generated code with CIDR allowlists

Who it's for

  • ML engineers serving LLMs or diffusion models without managing GPU servers
  • Researchers running scheduled fine-tuning or inference jobs
  • Data engineers scaling Python batch pipelines to the cloud

Examples

  1. "Serve Llama 3 70B with vLLM on an H100 behind a POST endpoint" → @app.cls + @modal.fastapi_endpoint scaffold
  2. "Run an ETL job every 6 hours pulling DB creds from a Modal Secret" → modal.Cron + modal.Secret script
  3. "Process 100 parquet chunks in parallel and store output in a Volume" → .map() + modal.Volume pipeline

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/modal/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/modal folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/modal/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/sas && mkdir -p ~/.claude/skills && cp -r /tmp/sas/skills/modal ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  2. Create the skills directory: mkdir -p ~/.claude/skills
  3. Copy just this skill: cp -r scientific-agent-skills/skills/modal ~/.claude/skills/
  4. Install the SDK: pip install modal (or uv pip install modal; Python 3.10–3.14)
  5. Create tokens at https://modal.com/settings, then run modal setup or export MODAL_TOKEN_ID and MODAL_TOKEN_SECRET
  6. Restart Claude Code and ask something like "deploy a GPU inference endpoint on Modal" to trigger the skill.
View source on GitHub ↗License: MIT