Name: mosaicml
Rating: 50.4 (1 reviews)
Author: membranedev

mosaicml

MosaicML integration. Manage data, records, and automate workflows. Use when the user wants to interact with MosaicML data.

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/mosaicml/SKILL.md

Quality

Content

58%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 command-heavy and largely actionable with a sensible auth/connection flow, but it bloats with unnecessary product backstory, lacks verification checkpoints for destructive batch operations, and relies on a single inlined document where deeper references would help. Adding validation steps and trimming preamble would raise workflow_clarity and conciseness.

Suggestions

Remove the product-backgrounder line ('MosaicML is a platform for training and deploying large AI models...') since Claude already knows this; lead with the integration mechanics.

Add a verify/validate checkpoint after action runs and proxy requests (e.g. check the output/error field before proceeding) to lift workflow clarity for batch/destructive operations.

Move the enumerated API areas (Runs, Clusters, Jobs, Files, etc.) and proxy flag table into a separate reference file referenced one level deep, keeping SKILL.md a concise overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with command-driven sections, but it includes a few unnecessary explainers Claude already knows (e.g. 'MosaicML is a platform for training and deploying large AI models' and restated flag descriptions), so it sits between lean (4) and noticeably padded (2), closer to the score-3 anchor.	3 / 5
Actionability	Concrete, copy-paste-ready CLI commands with --json flags and parameter examples cover the common cases; only minor gaps (e.g. the proxy and action-run examples use placeholders like CONNECTION_ID / /path/to/endpoint without a fully worked example) keep it below 5.	4 / 5
Workflow Clarity	The connection flow is sequenced with state checks (READY/BUILDING/CLIENT_ACTION_REQUIRED), but for batch/destructive operations (action run, proxy requests) there is no validation or verify-after-run checkpoint, so per the guideline a destructive/batch skill missing validation is capped at 3.	3 / 5
Progressive Disclosure	No bundle files exist and the content is a single overview listing many API areas (Runs, Clusters, Jobs, etc.) inline without deeper reference files; it is organized into sections but the long API-surface list and inlined reference-like material could be split out, fitting the score-3 'some structure, could be better organized' anchor.	3 / 5
	Total	13 / 20 Passed

Description

51%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 clearly identifies a named product (MosaicML) and includes a 'Use when' clause, but its action verbs are generic ('manage', 'automate workflows') and it lacks concrete natural trigger keywords beyond the product name. Tightening the action list and adding specific user phrases would lift specificity and trigger_term_quality.

Suggestions

Replace generic verbs with concrete actions, e.g. 'Manage training runs, clusters, jobs, files, and models' rather than 'Manage data, records, and automate workflows'.

Add natural trigger phrases users would say, such as 'Use when the user asks to start, monitor, or inspect MosaicML training runs, jobs, or clusters'.

Drop the redundant 'MosaicML integration' lead-in or merge it into the action list to avoid repetition and save tokens.

Dimension	Reasoning	Score
Specificity	Phrases 'Manage data, records, and automate workflows' name the domain (MosaicML data) but the actions are generic ('manage', 'automate workflows') rather than concrete, matching the score-2 anchor of named domain with minimal/generic actions.	2 / 5
Completeness	It answers both 'what' (manage data, records, automate workflows) and 'when' ('Use when the user wants to interact with MosaicML data'), but the 'when' clause is somewhat generic and could be more specific, fitting the score-4 anchor.	4 / 5
Trigger Term Quality	The only natural keyword is 'MosaicML data'; the term 'records'/'workflows' are generic, and the explicit trigger phrase ('Use when the user wants to interact with MosaicML data') repeats 'interact' rather than enumerating natural phrases users would say.	2 / 5
Distinctiveness Conflict Risk	'MosaicML integration' tied to a named product creates a clear niche with minimal conflict risk against other skills, though the generic 'data/records' wording leaves slight overlap with other data-platform skills.	4 / 5
	Total	12 / 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: membranedev/application-skills
Path: skills/mosaicml/SKILL.md
Commit: f484c82

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.