lambda-labs-gpu-cloud

Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

The canonical home for this skill is lambda-labs-gpu-cloud in Orchestra-Research/AI-Research-SKILLs

Quality

Content

65%

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

Highly actionable with abundant executable code, but the body is verbose and keeps reference-grade material inline instead of deferring it to bundle files. Workflow sequencing is clear but missing validation checkpoints for risky operations.

Suggestions

Move the Python API reference and curl CLI sections into a dedicated references file, keeping SKILL.md as a concise overview that links out.

Add explicit validation/confirmation steps before destructive operations such as terminating instances, and a verify step after multi-node launch (e.g., check Slurm/node health before training).

Tighten or trim inline tables and lists (GPU pricing, instance configs, networking) that duplicate Lambda's public docs, retaining only decision-relevant essentials.

Dimension	Reasoning	Score
Conciseness	The ~550-line body is mostly efficient and free of basic-concept padding, but inline API reference, curl CLI, SSH config, and networking sections are voluminous and could be tightened or moved to references.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance: Python API calls, curl commands, DDP/torchrun examples, and checkpoint code with concrete paths and parameters.	3 / 3
Workflow Clarity	Setup and launch steps are numbered and sequenced, but destructive (terminate) and batch (multi-node training) operations lack explicit validation checkpoints, capping this dimension at 2.	2 / 3
Progressive Disclosure	Real references (advanced-usage.md, troubleshooting.md) are clearly signaled one level deep, but the main body still inlines API reference and CLI content that would be better split into separate files.	2 / 3
	Total	9 / 12 Passed

Description

100%

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

A strong, third-person description that concisely states capabilities and gives an explicit trigger clause with natural terms. It clearly communicates both what the skill does and when to use it.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'Reserved and on-demand GPU cloud instances', 'dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters' — matching the score-3 anchor for multiple specific actions.	3 / 3
Completeness	Explicitly answers both 'what' (reserved/on-demand GPU instances for ML training and inference) and 'when' via a clear 'Use when you need...' trigger clause.	3 / 3
Trigger Term Quality	Natural user-facing terms are well covered: 'GPU cloud instances', 'ML training and inference', 'SSH access', 'multi-node clusters', 'large-scale training' — terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The dedicated-GPU-with-SSH, persistent-filesystems, multi-node-cluster niche is distinct from serverless/spot offerings and unlikely to trigger competing skills.	3 / 3
	Total	12 / 12 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (550 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	12 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/mlops/lambda-labs/SKILL.md
Commit: 4c9628e

Reviewed: about 14 hours 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.