CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 highly actionable, well-sequenced skill body with executable patterns and explicit cost-validation checkpoints. It is slightly let down by a duplicated cost/security warning and no in-bundle reference files to offload detail.

Suggestions

Dedupe the cost-protection / security warning: state it once in Authentication and reference it rather than restating near-verbatim at the end of the file.

Move the full GPU pricing table and benchmark comparison into a references/ file (e.g. PRICING.md) and keep only the VRAM rules-of-thumb inline, to improve token efficiency.

Verify the referenced ../shared-references/compute-env-contract.md exists relative to this skill, or inline the contract summary so the reference is not dangling.

DimensionReasoningScore

Conciseness

Mostly lean, relying on tables and executable code rather than explaining concepts Claude already knows, but the security/cost-protection warning is repeated near-verbatim and could be tightened.

4 / 5

Actionability

Provides six copy-paste-ready launcher patterns (A-F), concrete CLI commands, and a required cost-estimation template covering the common workload types.

5 / 5

Workflow Clarity

Clear 6-step sequence with an explicit cost-estimation checkpoint before every run, plus a verify/monitor step; the required confirmation loop gates risky spend.

5 / 5

Progressive Disclosure

Well-organized sections with appropriately inline content and a single one-level-deep reference to compute-env-contract.md; no bundle files exist to split content further, so minor organization gaps remain.

4 / 5

Total

18

/

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.

An excellent description that concretely states capabilities, provides comprehensive natural trigger phrases, and cleanly separates what the skill does from when to use it. It occupies a distinct niche with negligible conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("training, fine-tuning, inference, batch processing") plus concrete differentiators ("no SSH, no Docker, auto scale-to-zero"), giving comprehensive capability coverage.

5 / 5

Completeness

Explicitly answers both what ("Run GPU workloads on Modal — training, fine-tuning, inference, batch processing") and when (explicit "Use when user says..." with concrete trigger phrases).

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases users would actually say ("modal run", "modal training", "need a GPU", "serverless GPU", "deploy to modal", "run on modal") plus "remote GPU compute".

5 / 5

Distinctiveness Conflict Risk

Clearly scoped to Modal serverless GPU with niche-specific triggers; minimal overlap risk with other compute skills.

5 / 5

Total

20

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
wanshuiyin/Auto-claude-code-research-in-sleep
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.