Skip to content
mcp/skillhub

Agent Skill

Dstack skill

dstackdstackai/dstackskills/dstack/SKILL.md

dstack is an open-source control plane for GPU provisioning and orchestration across GPU clouds, Kubernetes, and on-prem clusters.

2.3kMPL-2.0

always on

28 tokname + description

once used

6,116 tokSKILL.md body

bundled files

0

repo stars

2.3kGitHub

Install the Dstack skill

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

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

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 ~/.claude/skills/dstack

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.

WhenWhat loadsCost
Every sessionName and description28 tok
When the agent uses itThe SKILL.md instructions6,116 tok
Only if openedNo bundled files—

Until it is used, dstack costs about 49× 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

  • Contains text that matches a prompt-injection pattern. In the skills we checked by hand this was security teaching material or a test fixture; read the file before you install it.
  • The instructions are over 5,000 tokens, the Agent Skills specification's guideline for SKILL.md.
  • The instructions are over 500 lines; the specification suggests moving detail into reference files.

Checked 2026-10-22 · method

What's inside

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

  • dstack
  • Overview
  • How it works
  • Quick agent flow (detached runs)
  • Agent execution guidelines
  • Output accuracy
  • Verification before execution
  • Command timing and confirmation handling
  • Detached run follow-up (after -d)
  • Attaching behavior (blocking vs non-blocking)
  • Interpreting user requests
  • Multi-node tasks and multi-replica services
  • Configuration types
  • files and repos intent policy
  • 1. Dev environments
  • 2. Tasks
  • 3. Services
  • 4. Fleets
  • 5. Volumes
  • 6. Gateways
  • Essential CLI commands
  • Apply configurations
  • Fleet management
  • Monitor runs

More skills from dstackai/dstack

All skills in this repo
  1. 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
  2. dstack-prototypingdstackai/dstack

    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.

    2.3k80 tok idle · 1,358 in use