modal

Serverless GPU cloud for ML jobs and model APIs.

Quality

66%

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

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/mlops/modal/SKILL.md

Quality

Content

80%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.

The content is highly actionable with broad, executable code coverage and well-structured one-level-deep references. Its main weakness is the absence of explicit validation/feedback-loop checkpoints for the batch and persistent-storage operations the skill teaches.

Suggestions

Add explicit validation checkpoints for destructive/persistent operations (e.g., verify a volume commit succeeded, confirm a deployment is live before declaring success).

Provide a fix-retry feedback loop for batch .map() jobs (e.g., how to inspect partial failures and re-run failed shards).

Trim framing intros and the 'Use alternatives instead' comparison to tighten the overview further toward the lean anchor.

Dimension	Reasoning	Score
Conciseness	The body is dense and largely free of basic-concept padding, relying on code blocks and tables and assuming Claude's competence; a few framing lines and the comparative 'Use alternatives' table add length that keeps it just below the lean, every-token-earns-its-place anchor 5.	4 / 5
Actionability	Extensive copy-paste-ready, executable Python and bash covering quick start, inference endpoints, GPU config, images, volumes, web endpoints, batching, secrets, scheduling, and parallel processing, with specific examples for the common cases.	5 / 5
Workflow Clarity	A clear quick-start sequence and execution-mode guidance exist, but persistent/destructive operations (volume.commit, deploy) and batch fan-out (.map) lack explicit validation checkpoints or fix-retry feedback loops, which per the rubric caps workflow clarity at 3 for batch/destructive workloads.	3 / 5
Progressive Disclosure	SKILL.md is an overview pointing to two real, verified, one-level-deep references (references/advanced-usage.md and references/troubleshooting.md) with descriptive link text and a dedicated References section, yielding clear and easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

53%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.

The description is concise and names a clear niche, but it omits any 'Use when...' trigger guidance and lists only two high-level capability areas. It is specific enough to avoid most conflicts but falls short of the trigger-rich, complete anchor examples.

Suggestions

Add an explicit 'Use when...' clause naming concrete user triggers (e.g., deploying ML models as APIs, running GPU batch jobs without managing servers).

Expand the capability list beyond 'ML jobs and model APIs' to concrete actions like training, inference, auto-scaling endpoints, and scheduled jobs.

Include natural synonyms and file/format cues users actually say (deploy, inference, training, GPU instances, cron jobs) to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Serverless GPU cloud') and two concrete capability areas ('ML jobs and model APIs'), but does not enumerate multiple specific actions, fitting the '1-2 concrete actions' anchor rather than the 'several specific actions' anchor above.	3 / 5
Completeness	The description gives a clear 'what' but no explicit 'Use when...' trigger clause; per the rubric, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords ('Serverless GPU', 'ML jobs', 'model APIs') are present, but common natural synonyms (deploy, inference, training, GPU instances) and extension cues are missing, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The serverless-GPU-for-ML/APIs combination is a distinct niche with only minor overlap risk against general ML or deployment skills, matching 'mostly distinct; minor overlap risk' rather than the fully-conflict-free 5 anchor.	4 / 5
	Total	13 / 20 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: 6680afb

Reviewed: about 3 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.