Name: roboflow-universe
Rating: 90.6 (1 reviews)
Author: roboflow

roboflow-universe

Use when searching for or using public datasets/models on Roboflow Universe (universe.roboflow.com), the open repository of 1M+ computer vision datasets and 50K+ pre-trained models.

1.23x

Quality

—

Does it follow best practices?

Impact

89%

1.23x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, highly actionable reference skill with concrete syntax and step-by-step procedures; the main gap is the absence of explicit validation/error-recovery checkpoints in the fork and download workflows.

Suggestions

Add a validation step to the Forking/Downloading workflows (e.g., confirm the dataset copied successfully and verify class/image counts before proceeding).

Include a brief error-recovery hint for common fork/download failures (logged-out state, missing license, export format issues).

Consider adding a one-line checkpoint after each numbered step in the Using a Universe Model workflow so failures surface early.

Dimension	Reasoning	Score
Conciseness	The body is dense reference material in compact tables (URL patterns, query operators, licenses, MCP params) that assumes Claude's competence and avoids explaining basics, so every token earns its place.	3 / 3
Actionability	Provides concrete, executable guidance — exact URL patterns, full query-operator syntax with examples, MCP tool parameters, model ID format, and step-by-step fork/download paths — that is copy-paste ready.	3 / 3
Workflow Clarity	Forking, downloading, and using-model workflows are listed as numbered steps, but they lack explicit validation checkpoints or error-recovery feedback loops for operations (fork/download) that could fail or produce bad data, capping clarity at 2.	2 / 3
Progressive Disclosure	A single well-organized SKILL.md with clearly headed sections and one-level-deep 'Related Skills' links; with no external bundle files needed, the clean section structure earns the top score.	3 / 3
	Total	11 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A clear, well-triggered description with explicit 'Use when' guidance and strong natural keyword coverage; its only weakness is that the stated actions ('searching for or using') are relatively general rather than enumerating multiple concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ('searching for or using public datasets/models on Roboflow Universe') and quantifies scope ('1M+ datasets', '50K+ models'), but the actions 'searching for or using' are somewhat general rather than a list of multiple concrete actions, matching the anchor for naming domain and some actions but not comprehensive.	2 / 3
Completeness	Explicitly answers what (search/use public datasets and models on the Universe repository) and when via the 'Use when searching for or using...' trigger clause, satisfying both halves.	3 / 3
Trigger Term Quality	Covers natural terms users would actually say — 'public datasets/models', 'Roboflow Universe', 'computer vision datasets', 'pre-trained models' — giving good coverage of likely phrasings.	3 / 3
Distinctiveness Conflict Risk	Scoped specifically to Roboflow Universe with a distinct URL and trigger, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: roboflow/computer-vision-skills
Commit: bf3aefb

Reviewed: about 9 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.