vast-ai-gpu-cloud

Safely inspect and operate Vast.ai marketplace instances with the vastai CLI, live offer data, and explicit approval before paid or destructive actions.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%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, well-structured, and highly actionable with concrete CLI contracts and a numbered policy that includes validation checkpoints for destructive and paid operations. It is a strong, lean instruction-only skill.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding; it does not explain what Vast.ai or GPUs are and assumes Claude's competence, with every section earning its place.	5 / 5
Actionability	Provides concrete, executable CLI commands and an exact numbered policy with approval gates; minor gaps in worked filter-construction examples keep it just below fully copy-paste ready.	4 / 5
Workflow Clarity	The numbered marketplace policy sequences steps with explicit validation checkpoints and feedback loops (reconcile by ID before retry, verify SSH/workload health, copy and verify outputs before destruction) appropriate for destructive/paid operations.	5 / 5
Progressive Disclosure	A short, well-organized skill with clear section headers and a one-level-deep Sources-of-truth section; with no bundle files, the simple-skill exception applies.	5 / 5
	Total	19 / 20 Passed

Description

70%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 specific and clearly distinguishable, naming the domain, tool, and approval boundary. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness.

Suggestions

Add an explicit 'Use when...' clause naming the natural trigger phrases users would say (e.g. 'Use when renting GPU instances on the Vast.ai marketplace, comparing offers, or managing leased instances').

Broaden trigger-term coverage with common synonyms and extensions a user might say (e.g. 'GPU rentals', 'spot GPU', 'lease GPUs').

Dimension	Reasoning	Score
Specificity	Names concrete actions ('inspect and operate', 'explicit approval before paid or destructive actions') and a specific tool ('vastai CLI'), but the action list is not fully comprehensive across all marketplace operations.	4 / 5
Completeness	The 'what' is clearly stated, but there is no explicit 'Use when...' trigger clause, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('Vast.ai', 'marketplace instances', 'vastai CLI') but is missing common synonyms or explicit file/format extensions.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Vast.ai marketplace GPU instances) with distinct triggers and minimal risk of triggering the wrong skill.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/cloud-compute/vast-ai/SKILL.md
Commit: 4082a2e

Reviewed: 1 day 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.