DGX Station AI Skills for Coding Agents

Install your coding agent

Pick whichever agent you prefer — the rest of this playbook works the same regardless. Install commands:

Verify with claude --version, codex --version, gemini --version, or by launching Cursor.

Install the skills into your project

Navigate to the project where you want DGX Station expertise, then run the installer with the harness you use:

cd ~/your-project

# Pick one:
/path/to/this/playbook/assets/install.sh claude
/path/to/this/playbook/assets/install.sh codex
/path/to/this/playbook/assets/install.sh gemini
/path/to/this/playbook/assets/install.sh cursor

# Or install for all four at once:
/path/to/this/playbook/assets/install.sh all

If you downloaded the playbook as a zip, the path is relative to the extracted directory:

station-ai-skills/assets/install.sh claude ~/your-project

The installer is additive for skill directories (won't clobber existing skills you've written) and refuses to overwrite an existing context file (AGENTS.md, CLAUDE.md, GEMINI.md) unless you pass --force.

Resulting layout (per harness):

your-project/
  AGENTS.md   or  CLAUDE.md   or  GEMINI.md      # context file (named for your agent)
  .claude/skills/<name>/SKILL.md                  # claude
  .codex/prompts/<name>.md                        # codex
  .gemini/commands/<name>.md                      # gemini
  .cursor/rules/<name>.mdc                        # cursor

Where <name> is each of vllm-setup, sglang-setup, mig-configure, dgx-diagnose.

Verify the setup

Start your agent in the project directory and ask a question that requires constraint knowledge:

Can I use --gpus all to run my CUDA workload on DGX Station?

The agent should immediately warn about the mixed-coherency constraint and recommend --gpus '"device=N"' targeting. If you don't get the warning, the context file isn't being loaded — see Troubleshooting.

Then verify the skills are discoverable:

Use vllm-setup to deploy an inference server

Invoke the skill in your agent:

The agent will walk you through deploying a vLLM server with a validated container image, correct GPU targeting, and recommended parameters. It will check your GPU index, ask which model you want to serve, and generate the full docker run command.

Use sglang-setup to deploy SGLang

Same invocation pattern, but for SGLang with the cu130 container, RadixAttention prefix caching, and structured JSON output support.

Use mig-configure to partition the GB300

The agent will query your current MIG state, show available profiles, help you choose a layout for your workloads, and execute the partitioning commands.

Use dgx-diagnose to troubleshoot issues

If you encounter problems, invoke dgx-diagnose. The agent will check GPU status, driver version, running processes, MIG state, and Fabric Manager to identify the issue.

Customize

Both the AGENTS.md and the skills are plain markdown — extend them freely.

Add project-specific constraints to AGENTS.md (or your harness-specific context file):

## Project-specific

- Our production MIG layout is 3g.139gb + 2g.70gb + 2g.70gb
- Always use port 8080 for inference (nginx proxy on 443)
- Model weights are cached at /data/models, mount with -v /data/models:/root/.cache/huggingface/hub

Create new skills by adding a directory and SKILL.md to assets/skills/, then re-run install.sh:

mkdir -p assets/skills/run-benchmarks
cat > assets/skills/run-benchmarks/SKILL.md << 'EOF'
---
name: run-benchmarks
description: Run our standard inference benchmark suite against the running vLLM or SGLang server and compare against the baseline.
---

# Run benchmarks

1. Check which inference server is running (vLLM on port 8000 or SGLang on port 30000)
2. Run the appropriate benchmark script from ./benchmarks/
3. Report throughput (tokens/sec), latency (TTFT, ITL), and memory utilization
4. Compare against the baseline in ./benchmarks/baseline.json
EOF