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

84%

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

76%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.

A thorough, highly actionable reference skill with executable code and clear sequencing. The main gap is the absence of explicit validation/feedback loops for destructive and batch operations, and some inline reference content that could be offloaded to the existing bundle files.

Suggestions

Add explicit validation checkpoints to destructive/batch workflows — e.g., after launching an instance, verify it is running before proceeding; before terminating, confirm the instance ID and that checkpoints are persisted to a filesystem.

Move the full Python API and curl CLI reference sections into a dedicated reference file (or advanced-usage.md), keeping only a minimal quick-start example inline in SKILL.md.

Tighten the intro and Lambda Stack sections to remove explanatory padding Claude already knows (e.g., 'Comprehensive guide to...'), relying on the description for framing.

Dimension	Reasoning	Score
Conciseness	Largely efficient with concrete tables, commands, and code blocks that earn their place, though the ~550-line body inlines several sections (full Python API, curl CLI, networking, cost optimization) that could be trimmed or moved to references.	4 / 5
Actionability	Fully executable, copy-paste-ready guidance throughout — SSH commands, Python API snippets (launch/list/terminate/SSH keys), curl examples, and torchrun multi-GPU commands covering the common cases.	5 / 5
Workflow Clarity	Quick start and training workflows are sequenced with numbered steps, but destructive and batch operations (instance termination, batch inference) lack explicit validation checkpoints or validate-fix-retry feedback loops, capping this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	Good overall structure with clear section headers and two one-level-deep references (advanced-usage.md, troubleshooting.md) clearly signaled in a References section, though a fair amount of API/CLI reference content is inlined that could live in separate files.	4 / 5
	Total	16 / 20 Passed

Description

92%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.

A strong description that clearly states capabilities and provides an explicit 'Use when' trigger clause with concrete, natural terms. Minor room to add a few more synonyms, but it is comprehensive and distinctive.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'Reserved and on-demand GPU cloud instances for ML training and inference', 'dedicated GPU instances with simple SSH access', 'persistent filesystems', 'high-performance multi-node clusters' — giving comprehensive coverage of what the skill provides.	5 / 5
Completeness	Explicitly answers both 'what' (reserved and on-demand GPU cloud instances for ML training and inference) and 'when' via a clear 'Use when you need...' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good coverage of natural terms users would say ('GPU instances', 'ML training', 'inference', 'multi-node clusters', 'SSH access', 'persistent filesystems'), though a few natural variations like 'GPU cloud' or specific GPU names are absent.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (Lambda Labs GPU cloud) with distinct, specific triggers (SSH access, persistent filesystems, multi-node clusters) and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 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 (559 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: synthetic-sciences/openscience
Path: backend/cli/skills/cloud-compute/lambda-labs/SKILL.md
Commit: 3a6c3a9

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.