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

73%

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

Fix and improve this skill with Tessl

tessl review fix ./09-infrastructure/lambda-labs/SKILL.md

Quality

Content

65%

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

A highly actionable, well-sequenced guide with executable code throughout. Its weaknesses are verbosity from keeping reference-grade API/CLI detail inline rather than in bundle files, and missing validation checkpoints around destructive operations.

Suggestions

Move the detailed Python API and curl CLI sections into references/advanced-usage.md, keeping only a minimal quick-start snippet in SKILL.md to improve conciseness and progressive disclosure.

Add an explicit validation/confirmation checkpoint before terminating instances (e.g. list running instances, confirm the target ID, then terminate) to lift workflow clarity.

Trim informational lists like the Lambda Stack inventory and launch-time tables to the essentials a model would not already infer.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and avoids explaining concepts Claude already knows, but at ~535 lines it is verbose; the full Python API, curl CLI, SSH-config, and networking sections are reference-grade detail that could be tightened or moved to bundle files.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance: Python API snippets (list/launch/terminate/SSH keys), curl commands, torchrun/srun invocations, and ssh tunnel examples with clearly marked placeholders.	3 / 3
Workflow Clarity	Quick start and training workflows use clear numbered sequences and there is a verify-installation checkpoint, but the destructive 'terminate instance' operation and the launch flow lack explicit validation/feedback loops, which caps this dimension at 2.	2 / 3
Progressive Disclosure	A References section clearly signals two real, one-level-deep bundle files (advanced-usage.md, troubleshooting.md), but full Python API and curl reference material is inline and overlaps the 'API automation' topic moved to advanced-usage.md, matching the 'content that should be separate is inline' anchor.	2 / 3
	Total	9 / 12 Passed

Description

82%

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, well-formed description that clearly states capability and includes an explicit 'Use when' trigger with natural keywords. Its main weakness is provider-agnostic phrasing that raises conflict risk against other GPU-cloud skills.

Suggestions

Name the provider (e.g. 'Lambda Labs GPU cloud instances') in the description to reduce overlap with other GPU-cloud skills.

Reframe capability nouns as concrete actions where possible (e.g. 'Launch, configure, and terminate GPU instances') to lift specificity toward the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('Reserved and on-demand GPU cloud instances for ML training and inference') and concrete capabilities (SSH access, persistent filesystems, multi-node clusters), but lists features as noun phrases rather than the multiple specific concrete verb-actions of the anchor-3 example.	2 / 3
Completeness	Explicitly states what ('GPU cloud instances for ML training and inference') and when (an explicit 'Use when...' clause with concrete triggers), satisfying both halves.	3 / 3
Trigger Term Quality	The 'Use when you need dedicated GPU instances... multi-node clusters for large-scale training' clause covers natural terms a user would say (GPU instances, training, inference, SSH, multi-node clusters).	3 / 3
Distinctiveness Conflict Risk	It is specific to GPU cloud but does not name the provider, and the body lists four competing GPU-cloud platforms (Modal, RunPod, SkyPilot, Vast.ai), so a generic 'I need GPU instances for training' could overlap with sibling skills.	2 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (546 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Orchestra-Research/AI-Research-SKILLs
Path: 09-infrastructure/lambda-labs/SKILL.md
Commit: 773a529

Reviewed: about 12 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.