dstack-presets

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.

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/dstack-presets/SKILL.md

Quality

Content

51%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-structured with clean external references, but it offers little actionable or workflow guidance — it points to documentation rather than teaching the concrete `dstack preset` commands and steps it claims to cover.

Suggestions

Add 2–3 concrete `dstack preset` command examples (e.g. `dstack preset list`, `dstack preset export <name>`, `dstack preset delete <name>`) so Claude can act without fetching external docs.

Include a minimal preset YAML skeleton or a pointer to a local reference file showing the serving/benchmark/hardware fields mentioned in the overview.

Provide a short sequenced workflow with a validation checkpoint for destructive management operations (e.g. list → confirm → delete, verifying the preset no longer exists after deletion).

Dimension	Reasoning	Score
Conciseness	Lean and free of padding or over-explanation of concepts Claude already knows; the overview mildly restates the description but stays tight, leaving only minor trimming opportunities.	4 / 5
Actionability	Delegates almost entirely to external doc URLs with no executable guidance — no `dstack preset` commands, no YAML example, no concrete steps for the stated management tasks (list/export/delete/watch).	2 / 5
Workflow Clarity	No sequenced workflow; "Follow the [presets documentation]" is a rough pointer with steps poorly defined and no validation checkpoints for the batch/destructive operations (export, delete) the skill mentions.	2 / 5
Progressive Disclosure	A short, well-organized skill under 50 lines with no local bundle files needed; references to external docs are clearly signaled and one level deep, satisfying the simple-skill exception.	5 / 5
	Total	13 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong: third-person, specific about capabilities, with explicit trigger and anti-trigger guidance that cleanly separates it from the sibling dstack skill. It fully answers both what and when.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete capabilities — "a toolkit that streamlines model inference optimization with agents", "a portable preset format", and "manage existing presets" — going beyond 1–2 actions, though not a fully enumerated action list.	4 / 5
Completeness	Explicitly answers both what (create/manage presets; inference-optimization toolkit + portable format) and when ("only when the user explicitly asks to create a preset or manage existing presets"), with a concrete negative boundary for when not to use it.	5 / 5
Trigger Term Quality	Includes natural user phrases ("create a preset", "manage existing presets", "optimize model inference via a preset") plus an explicit anti-trigger; missing synonyms/extensions but those are largely inapplicable here.	4 / 5
Distinctiveness Conflict Risk	Clearly scoped niche explicitly disambiguated from the sibling dstack skill ("Use together with the dstack skill", "not for deploying or serving a model: use a service"), giving minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: dstackai/dstack
Path: skills/dstack-presets/SKILL.md
Commit: 87e2fd6

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.