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.
89
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
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.
This is an excellent skill description that hits all the marks. It provides specific capabilities (training, fine-tuning, inference, batch processing), key differentiators (zero-config, no SSH, no Docker, auto scale-to-zero), and a comprehensive 'Use when' clause with natural trigger terms. The Modal platform focus gives it clear distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: training, fine-tuning, inference, batch processing. Also specifies key characteristics like zero-config serverless, no SSH, no Docker, auto scale-to-zero. | 3 / 3 |
Completeness | Clearly answers both 'what' (run GPU workloads on Modal — training, fine-tuning, inference, batch processing with zero-config serverless) and 'when' (explicit 'Use when' clause with multiple trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'modal run', 'modal training', 'modal inference', 'deploy to modal', 'need a GPU', 'run on modal', 'serverless GPU', 'remote GPU compute'. These are highly natural phrases a user would actually type. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with the 'Modal' platform as a clear niche. The combination of Modal-specific terms and GPU compute creates a well-defined scope that is unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with excellent workflow structure and concrete, executable code patterns covering the major Modal use cases. Its main weakness is length — the pricing tables, benchmark comparisons, repeated security warnings, and six full code patterns make it quite long for a single SKILL.md, and some content (like the platform comparison in the overview) is unnecessary for Claude. The cost estimation requirement before every run is a particularly good safety mechanism.
Suggestions
Remove the duplicated cost protection/security warning (appears in both Authentication and bottom sections) — keep only one instance.
Trim the overview section: Claude doesn't need an explanation of what serverless means or comparisons to vast.ai/Lightning — just state 'Modal is a serverless GPU cloud: write Python, modal run, done.'
Consider splitting the six code patterns into a separate PATTERNS.md reference file, keeping only Pattern A (most common) inline in SKILL.md with references to the others.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary verbosity — the overview section explains what serverless means and compares to other platforms (Claude knows this), the pricing table is extensive, and the benchmark comparison table adds bulk. However, most content is reference-worthy and earns its place. The security warnings and cost protection notes are repeated twice, which is wasteful. | 2 / 3 |
Actionability | Excellent actionability — provides fully executable, copy-paste-ready code for six distinct patterns (one-shot, web API, vLLM, batch, LoRA, multi-GPU), concrete CLI commands for every step, specific GPU selection tables with VRAM requirements, and a cost estimation template. Every pattern includes real imports and working code. | 3 / 3 |
Workflow Clarity | Clear 6-step workflow (Analyze → Generate → Run → Verify → Collect → Cleanup) with explicit validation via `modal app logs` and `modal app list`. The cost estimation checkpoint before every run is a strong validation gate. Cleanup notes that auto-scale-to-zero handles most cases but provides explicit commands for volumes and deployed services. | 3 / 3 |
Progressive Disclosure | The content is a long monolithic file (~300 lines) with no bundle files to offload detail into. The six code patterns, pricing tables, benchmark tables, and CLI reference could be split into separate referenced files. However, sections are well-organized with clear headers, and external documentation links are provided at the bottom. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
2028ac4
- Reviewed
Table of Contents
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.