modal-serverless-gpu

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

65%

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

The body is highly actionable with executable examples and real, clearly-linked reference files, but it carries substantial inline reference detail and lacks explicit validation checkpoints in its deployment/batch workflows, keeping conciseness, workflow clarity, and progressive disclosure at the mid anchor.

Suggestions

Add explicit validation checkpoints to deployment and batch workflows (e.g., test with .local() and verify output before `modal deploy`; confirm batch results before committing a Volume) to create clear feedback loops.

Move detailed API-reference sections (GPU configuration, container images, web endpoints, secrets, scheduling) into a reference file so SKILL.md stays a leaner overview plus quick-start with clearly signaled links.

Trim promotional/advisory prose such as the Key features marketing bullets and the Use-alternatives list to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is code-dense and teaches Modal-specific API Claude doesn't already know, but it is lengthy (~330 lines) and includes advisory/promotional prose ("Sub-second cold starts: Rust-based infrastructure", "Scale to 100+ GPUs instantly") plus an alternatives section that could be tightened.	2 / 3
Actionability	It provides fully executable, copy-paste-ready Python and bash examples across deployment, storage, endpoints, batching, secrets, and scheduling, with concrete GPU specs and commands.	3 / 3
Workflow Clarity	A sequence is implied via the execution-modes table (run -> serve -> deploy) and quick start, but there are no explicit validation checkpoints or feedback loops, and batch/deployment operations lack verification steps, which caps the score at 2.	2 / 3
Progressive Disclosure	Two real reference files (advanced-usage.md, troubleshooting.md) are clearly signaled in a dedicated References section and the body is well-sectioned, but a large volume of API reference material (GPU config, images, web endpoints, secrets, scheduling) remains inline that could be split into reference 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.

The description is specific, uses natural trigger phrasing, and clearly pairs a what-statement with an explicit Use-when clause, hitting the top anchor across all four dimensions.

Dimension	Reasoning	Score
Specificity	It lists multiple concrete capabilities—"on-demand GPU access without infrastructure management", "deploying ML models as APIs", and "running batch jobs with automatic scaling"—rather than vague abstractions, matching the multiple-specific-actions anchor.	3 / 3
Completeness	It states what ("Serverless GPU cloud platform for running ML workloads") and gives an explicit "Use when..." clause with concrete triggers, clearly answering both what and when.	3 / 3
Trigger Term Quality	Phrases like "GPU access", "deploy ML models as APIs", and "batch jobs with automatic scaling" are natural things a user would say when needing this skill, giving good trigger coverage.	3 / 3
Distinctiveness Conflict Risk	The serverless-GPU-for-ML niche with on-demand/deploy-as-API/batch triggers is a distinct scope unlikely to fire for unrelated skills, fitting the clear-niche anchor.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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	13 / 16 Passed

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

Reviewed: about 7 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.