Agent Skill

Dstack Prototyping skill

dstack-prototypingdstackai/dstackskills/dstack-prototyping/SKILL.md

Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven. Guides task-first prototyping on real hardware, choosing fleets/backends that can reuse idle instances and caches, checking vLLM/SGLang sources, and verifying the final dstack service with a model request.

2.3kMPL-2.0

always on

80 tokname + description

once used

1,358 tokSKILL.md body

bundled files

repo stars

2.3kGitHub

Install the Dstack Prototyping skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/dstackai/dstack --skill dstack-prototyping

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/dstackai/dstack.git /tmp/dstack
mkdir -p ~/.claude/skills
cp -R /tmp/dstack/skills/dstack-prototyping ~/.claude/skills/dstack-prototyping

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

When	What loads	Cost
Every session	Name and description	80 tok
When the agent uses it	The SKILL.md instructions	1,358 tok
Only if opened	No bundled files	—

Until it is used, dstack-prototyping costs about 17× less than the median MCP server we measured (1,363 tokens on every turn). Installing all 3 skills from dstackai/dstack would load 169 tokens of descriptions. Skills vs MCP study

Checks

Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

dstack Prototyping
Goal
Choose Where To Run
Check Serving Sources
Use A Task Before Service
Verify As A Service
Router
PD disaggregation

More skills from dstackai/dstack

All skills in this repo

dstackdstackai/dstack
dstack is an open-source control plane for GPU provisioning and orchestration across GPU clouds, Kubernetes, and on-prem clusters.
2.3k28 tok idle · 6,116 in use
dstack-presetsdstackai/dstack
Create and manage dstack presets: a toolkit that streamlines model inference optimization with agents, and a portable preset format. Use together with the dstack skill, and only when the user explicitly asks to create a preset or manage existing presets, not for deploying or serving a model.
2.3k61 tok idle · 277 in use