Name: roboflow-universe
Rating: 63.2 (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.

Quality

79%

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/roboflow-universe/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.

A well-structured, information-dense reference body that assumes domain competence and provides concrete operator syntax, tool parameters, and sequenced UI workflows. The main gaps are the absence of explicit validation checkpoints and no use of external reference files for the denser lookup tables.

Suggestions

Add brief verification steps to the forking/download/model-inference workflows (e.g., "confirm the dataset appears in your workspace" or "verify the model block resolves") to reach the checkpoint anchor.

Move the large query-operator and license tables into reference files (e.g. references/query-operators.md, references/licenses.md) and keep SKILL.md as an overview with one-level-deep links to improve progressive disclosure.

Include at least one full example `universe_search` invocation (with a sample query and expected returned fields) to make the tool guidance copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly tabular (URL patterns, query operators, licenses, tool params) with little concept-explanation padding; minor meta-guidance and a few phrasings could be trimmed, so it sits above the midpoint but not at the fully-lean anchor of 5.	4 / 5
Actionability	Concrete executable guidance is present via the `universe_search` parameter table, query-operator syntax with examples, and numbered UI steps; it is not copy-paste code and lacks a full example tool-call invocation, so it falls short of the 5-anchor.	4 / 5
Workflow Clarity	Multi-step flows (Forking, Using a Universe Model via Workflows, Downloading) are clearly numbered with concrete actions; no explicit validation/verification checkpoints appear, but the operations are non-destructive copies/UI flows so the destructive-cap does not apply, placing this above the checkpoint-missing anchor of 3 but below 5.	4 / 5
Progressive Disclosure	Content is well-organized under clear section headers with one-level-deep references in Related Skills and no bundle files present; some dense inline reference tables (operators, licenses) could be split into reference files, so it does not reach the cleanly-split anchor of 5.	4 / 5
	Total	16 / 20 Passed

Description

73%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.

A concise, well-targeted description that names a clear niche (Roboflow Universe) with explicit "Use when" trigger guidance and natural keywords. Its main weakness is that the action list (search/use) is generic and not a comprehensive enumeration of concrete capabilities.

Suggestions

Expand the action verbs beyond "searching for or using" to concrete capabilities (e.g., search, fork, download, and run inference with public datasets/models) to lift specificity and completeness.

Add a couple of natural synonym/extension terms (e.g., "computer vision datasets", "model zoo", "public CV models") to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (Roboflow Universe datasets/models) and two actions ("searching for or using"), but "using" is generic and the action coverage is not comprehensive, matching the domain-plus-1-2-actions anchor rather than the multiple-specific-actions anchors above.	3 / 5
Completeness	The "Use when searching for or using..." clause supplies both a when and an embedded what, but the what (search/use) is less explicit and exhaustive than the 5-anchor's full enumeration of concrete actions with trigger phrases.	4 / 5
Trigger Term Quality	Natural terms a user would say are present ("datasets", "models", "computer vision", "Roboflow Universe", "pre-trained models"), giving good keyword coverage; a few synonyms/variations are missing, so it is not the comprehensive anchor of 5.	4 / 5
Distinctiveness Conflict Risk	"Roboflow Universe" and "universe.roboflow.com" name a specific platform niche with distinct triggers, giving minimal overlap risk with other skills.	5 / 5
	Total	16 / 20 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
Path: skills/roboflow-universe/SKILL.md
Commit: d23cb74

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.