Name: modelscope
Rating: 59.2 (1 reviews)
Author: membranedev

modelscope

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

Quality

68%

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/modelscope/SKILL.md

Quality

Content

75%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 a strong, actionable CLI integration guide with concrete commands, a flag table, and a well-sequenced connection workflow featuring real feedback loops. Its main weaknesses are an unnecessary introductory concept paragraph and some loose step numbering plus minor section redundancy.

Suggestions

Remove or trim the opening paragraph explaining what ModelScope is; Claude already knows this and it adds no integration value.

Fix the step numbering so referenced 'Step 2' and '1b' map to clearly labeled steps in the connection workflow.

Merge the redundant 'Popular actions' section into 'Searching for actions' to avoid repeating the action-list command.

Dimension	Reasoning	Score
Conciseness	Most of the body is tight, executable command reference, but the opening paragraph explaining what ModelScope is ('an open-source platform for machine learning model sharing...') and phrasing like 'so you can focus on the integration logic rather than auth plumbing' are unnecessary explanation Claude does not need.	3 / 5
Actionability	The body provides copy-paste ready commands for every stage (install, login, connection ensure, action list/run, request proxy) plus a complete flag table, covering the common integration cases with concrete, executable guidance.	5 / 5
Workflow Clarity	The connect-and-poll flow has a clear sequence with explicit state checkpoints (READY, BUILDING, CLIENT_ACTION_REQUIRED, CONFIGURATION_ERROR) and a genuine feedback loop ('poll again after the user completes the action'), but step numbering is loose — it references 'Step 2' and '1b' without correspondingly labeled steps.	4 / 5
Progressive Disclosure	The body is well-organized with clear section headers and no nested external references (no bundle files exist), keeping everything one level deep; the only gap is minor redundancy where 'Popular actions' repeats the action-list command already shown in 'Searching for actions'.	4 / 5
	Total	16 / 20 Passed

Description

62%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 the ModelScope niche and includes an explicit 'Use when' trigger, but its capability list relies on generic verbs rather than concrete ModelScope-specific actions and lacks keyword synonyms. It is solid but could be sharpened with more specific actions and trigger terms.

Suggestions

Replace generic verbs with concrete ModelScope actions, e.g. 'Browse and download models, manage datasets, run model pipelines'.

Add natural trigger synonyms users might say, such as 'models', 'datasets', or 'model sharing', alongside 'ModelScope'.

Tighten the 'when' clause to name concrete scenarios, e.g. 'Use when the user wants to find, download, or share models and datasets on ModelScope'.

Dimension	Reasoning	Score
Specificity	Names the domain ('ModelScope integration') and a few actions ('Manage data, records, and automate workflows'), but the actions are generic verbs rather than concrete ModelScope capabilities like model sharing or datasets, so it is not comprehensive.	3 / 5
Completeness	Both 'what' ('Manage data, records, and automate workflows') and 'when' ('Use when the user wants to interact with ModelScope data') are present and explicit, though the 'when' clause is somewhat generic and could be more specific.	4 / 5
Trigger Term Quality	The natural keyword 'ModelScope' appears and the trigger phrase 'Use when the user wants to interact with ModelScope data' is present, but there are no synonyms or related natural terms (models, datasets, model sharing) users might say.	3 / 5
Distinctiveness Conflict Risk	The named platform 'ModelScope' gives it a clear niche with a distinct trigger and minimal conflict risk, but the generic 'manage data, records, automate workflows' wording creates minor overlap with other data-management skills.	4 / 5
	Total	14 / 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/modelscope/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.