aris-serverless-modal

Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "modal training", "modal inference", "deploy to modal", "need a GPU", "run on modal", "serverless GPU", or needs remote GPU compute.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

71%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.

Highly actionable with executable code patterns and a clear sequenced workflow, but it is a monolithic file whose length and duplicated warnings leave room for conciseness and progressive-disclosure improvements.

Suggestions

De-duplicate the card/spending-limit security warning (currently stated verbatim at lines 45 and 321) into a single Authentication/Cost-protection section.

Move the pattern library (A–F) and/or the full pricing table into references/ files, keeping SKILL.md an overview with one-level-deep links to improve progressive disclosure.

Trim the marketing-style 'Key advantages over SSH-based platforms' Overview bullets to the decision-relevant facts (zero-config, scale-to-zero, when Modal is cheaper vs. vast.ai).

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational content (code patterns, CLI, VRAM rules), but the Overview markets Modal advantages, the security/card warning is repeated verbatim at lines 45 and 321, and the large pricing table adds padding that could be tightened.	3 / 5
Actionability	Six complete, copy-paste-ready launcher patterns (A–F), a full CLI reference, a cost-estimation template, and VRAM rules give fully executable guidance covering the common cases.	5 / 5
Workflow Clarity	A clear 6-step sequence (Analyze → Generate → Run → Verify → Collect → Cleanup) with a cost-estimation confirmation checkpoint and a verify/monitor step; minor gap is the lack of an explicit error-recovery feedback loop.	4 / 5
Progressive Disclosure	Well-sectioned single file, but at ~318 lines with no references/scripts/assets bundle, content that could live in separate files (the pattern library, pricing table) is inlined rather than split for progressive disclosure.	3 / 5
	Total	15 / 20 Passed

Description

100%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, third-person description that clearly states capabilities and provides abundant natural trigger phrases. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions — 'training, fine-tuning, inference, batch processing' — giving comprehensive coverage of GPU workload types rather than vague language.	5 / 5
Completeness	Explicitly answers both 'what' (run GPU workloads on Modal: training/fine-tuning/inference/batch) and 'when' (a 'Use when user says...' clause with concrete trigger phrases), matching the top anchor.	5 / 5
Trigger Term Quality	Eight natural trigger phrases users would actually say ('modal run', 'modal training', 'need a GPU', 'serverless GPU', etc.) with synonyms and variations, matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	Targets a clearly named platform (Modal) with Modal-specific trigger phrases, creating a distinct niche with minimal overlap risk against other GPU skills.	5 / 5
	Total	20 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/aris-serverless-modal/SKILL.md
Commit: 4b35756

Reviewed: 5 days 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.