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

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 dense, highly actionable reference with copy-paste code across Modal's main features and well-signaled bundle references. Its main weakness is the absence of validation/feedback loops for its batch and deploy workflows, which caps workflow clarity.

Suggestions

Add an explicit validate-then-proceed step for batch/deploy workflows (e.g., after `modal deploy`, verify the endpoint responds with a sample request before declaring success).

Remove the redundant 'Comprehensive guide...' opener and trim the 'When to use Modal' section to avoid re-stating the description.

Move the inline 'Common issues' table into references/troubleshooting.md to eliminate overlap with that reference.

Dimension	Reasoning	Score
Conciseness	Mostly lean, built from tables and executable code with little concept explanation, but the redundant 'Comprehensive guide...' opener and a 'When to use Modal' section that re-treads the description add minor padding.	4 / 5
Actionability	Copy-paste-ready Modal code spans the common cases — hello-GPU, inference endpoint, images, volumes, web endpoints, batching, secrets, scheduling, and parallel map — with specific commands and decorators throughout.	5 / 5
Workflow Clarity	Organized as topical sections rather than a sequenced workflow, and the batch/deploy operations (map fan-out, deploy) lack any explicit validation or verification checkpoint, capping this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	Clear section structure with one-level-deep, real references to references/advanced-usage.md and references/troubleshooting.md, but the body is long and the inline 'Common issues' table overlaps with the troubleshooting reference, a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

88%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, concrete description with an explicit 'Use when' clause and multiple specific trigger phrases. Minor keyword synonym gaps and some overlap risk with adjacent GPU-cloud tools keep it just below perfect.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'running ML workloads', 'deploying ML models as APIs', 'running batch jobs with automatic scaling', 'on-demand GPU access without infrastructure management' — giving comprehensive coverage of the platform's use cases.	5 / 5
Completeness	Explicitly answers both what ('Serverless GPU cloud platform for running ML workloads') and when ('Use when you need on-demand GPU access... deploying ML models as APIs, or running batch jobs with automatic scaling') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('GPU access', 'ML models as APIs', 'batch jobs', 'automatic scaling'), but misses common synonyms a user might say like 'inference', 'training', or 'GPU instances'.	4 / 5
Distinctiveness Conflict Risk	The 'Serverless GPU cloud platform for running ML workloads' niche is mostly distinct, but trigger terms overlap with closely related GPU-cloud skills (e.g. RunPod, Lambda Labs) which the body itself lists as alternatives.	4 / 5
	Total	18 / 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: OpenLAIR/dr-claw
Path: skills/infrastructure/modal/SKILL.md
Commit: 4b35756

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.