dstack-prototyping
Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven.
Install / Use
npx skills add dstackai/dstack --skill dstack-prototypingInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
AI & Machine LearningSupported Platforms
Our assessment of dstack-prototyping
dstack-prototyping scores 91/100 on our quality scale, 327th of 947 AI & Machine Learning skills we index (top 35%).
Its SKILL.md is 6.3 KB long, well organised into 8 sections with 2 code examples: a thorough specification that gives an agent plenty to work with.
With 2,259 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so dstack-prototyping is actively maintained.
- Our last check on 2026-10-29 found the source still online.
- It is released under MPL-2.0, a copyleft license: you can use it, but modified versions you distribute must carry the same license.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-09-30. Automated pattern scan on 2026-09-29. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
dstack-prototyping compared with similar skills
All 4 of these similar skills score higher than dstack-prototyping; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| dstack-prototyping (this skill)by dstackai | 91 | 2.3k | 53d ago | SKILL.md |
| claude-memby thedotmack | 100 | 117.6k | today | CLAUDE.md |
| taste-skillby Leonxlnx | 100 | 116.8k | 8d ago | CLAUDE.md |
| Understand-Anythingby Egonex-AI | 100 | 92.8k | 1d ago | CLAUDE.md |
| headroomby headroomlabs-ai | 100 | 79.8k | today | CLAUDE.md |
Frequently asked questions
- How do I install dstack-prototyping?
- Run
npx skills add dstackai/dstack --skill dstack-prototyping. The install tabs above show the steps for each supported agent. - Which AI agents does dstack-prototyping work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is dstack-prototyping safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MPL-2.0-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is dstack-prototyping still maintained?
- The repository was last updated about 2 months ago, so dstack-prototyping is actively maintained.
Skill content
View source on GitHubname: dstack-prototyping description: | 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.
dstack Prototyping
Use /dstack for CLI commands, YAML fields, apply/attach behavior, service URLs,
and other dstack syntax. This skill explains how to use dstack runs while the
model-serving configuration is still unknown.
Goal
Find a working dstack service configuration for the requested model.
Before submitting a service, use a task on real hardware to test the serving image, install/runtime assumptions, model download, cache path, command, port, launch flags, resources, env vars, backend/fleet choice, and local model request. Then submit the same configuration as a service and verify the model through the dstack service URL.
Choose Where To Run
Pick the offer whose hardware best fits the goal at hand. Only when several offers fit comparably, choose a VM-based backend, an SSH fleet, or a Kubernetes fleet: they support idle instances and/or instance volumes, so later runs reuse the provisioned/idle instance or instance volumes for caching model weights (and possibly other writes), while container-based backends start clean on every run.
Fetch https://dstack.ai/docs/concepts/backends.md and classify backends
from the fetched document, not from memory.
If the intention is to use PD disaggregation, the fleet must use placement: cluster. Since PD disaggregation implies running a router, unlike workers that must run on GPUs, the router normally should run on a CPU instance. Use dstack fleet to see existing fleets and dstack fleet get <fleet name> --json to inspect a specific fleet.
Check Serving Sources
Check serving-framework sources early enough to choose the image, command, launch flags, resources, cache paths, request format, and expected model behavior.
For vLLM and SGLang, use these as credible sources:
- vLLM recipes and model index:
https://recipes.vllm.ai/andhttps://recipes.vllm.ai/models.json - SGLang docs:
https://docs.sglang.io/(fetch/llms.txtfor the page index) - SGLang model recipes:
https://docs.sglang.io/cookbook/autoregressive/intro - Release notes:
https://github.com/vllm-project/vllm/releasesandhttps://github.com/sgl-project/sglang/releases - Performance-loop methodology (profiling, benchmark contracts):
https://www.lmsys.org/blog/2026-07-02-agent-assisted-sglang-development
Use A Task Before Service
Before submitting a service, start a long-lived task:
commands:
- sleep infinity
or an equivalent idle command.
Submit the task detached, attach or SSH into it when available, and run commands inside the live environment. Test the image, installs, model download and cache path, serving command, port, launch flags, local model request, and expected model behavior.
When starting a long-running command in the background from a non-interactive
SSH command, use nohup, redirect stdin from /dev/null, and redirect
stdout/stderr to a log file so the SSH command returns while the process keeps
running. For example (the command can be any long-running command):
nohup vllm serve ... </dev/null > /tmp/vllm.log 2>&1 &
If the image, hardware choice, or major install path changes, submit another task so the changed setup is tested before service verification.
Do not move to a service after checking only GPU visibility, imports, logs, or a health endpoint. Start the server inside the task and send a request that uses the requested model. For a chat or reasoning model, check the response behavior the endpoint is expected to support, such as reasoning output when that model is supposed to expose it.
Follow /dstack structured status guidance when polling task or service status.
After requesting a task or service stop before another submission, wait until
that run reaches a terminal status. This allows dstack to reuse its instance or
instance volumes when available.
Verify As A Service
Submit the service after the task has verified the configuration: image, command, port, resources, env vars, cache mounts if used, backend/fleet choice, and model request.
Use the service as a duplicate check of the same configuration under dstack service runtime. The model request that worked locally in the task must also work through the dstack service URL.
If service verification fails because the image, install, model download, command, resources, cache, or model behavior needs to change, go back to a task. If the tested serving setup is still right and only the dstack service configuration is wrong, fix the configuration and submit the service again.
Router
If a fleet has placement: cluster and a CPU-only instance, you must use a
configuration with the router on the CPU-only instance, regardless of whether
the workers are aggregated or PD disaggregated.
Whenever possible, connect the workers over gRPC, not HTTP: with a gRPC
router, request parsing, serialization, and tokenization move from the
serving engine to the router, so latency improves just by introducing it.
When using a router:
- Use node groups for the task and replica groups for the service: tasks' node groups are the equivalent of services' replica groups.
- With tasks, still use
sleep infinityeven when usinggroups(set it in each group'scommands; top-levelcommandsis not allowed withgroups), and run the actual commands on each node interactively over SSH. - When testing inference, call the router endpoint, not the workers directly (unless you want to test if they are alive).
- Look for "Prototyping services" in
https://dstack.ai/docs/concepts/tasks.mdand "Router" inhttps://dstack.ai/docs/concepts/services.md.
PD disaggregation
If the intention is to use PD disaggregation:
- Follow
## Router: the router and the prefill/decode workers run as separate groups, and the fleet needs an interconnect (placement: cluster). - Look for "Node groups" and "PD disaggregation" in
https://dstack.ai/docs/concepts/tasks.mdand "Replica groups" and "PD disaggregation" inhttps://dstack.ai/docs/concepts/services.md.
Related Skills
claude-mem
117.6kPersistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
taste-skill
116.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
Understand-Anything
92.8kGraphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
headroom
79.8kCompress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
