Name: roboflow-universe
Rating: 81 (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

74%

Does it follow best practices?

Impact

89%

1.23x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/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 tidy, table-driven reference skill that is actionable and well-organized, with clear workflows for forking and inference. The main opportunity is splitting dense reference tables into bundle files for deeper progressive disclosure.

Suggestions

Move the licenses table and the full query-operator reference into a references/ file (e.g. REFERENCE.md) and link from SKILL.md to improve progressive disclosure.

Tighten the opening source-of-truth blockquote to one or two lines to reduce token overhead.

Add a brief validation note after the fork/download steps (e.g. confirm the dataset appears in the workspace) to harden the workflow.

Dimension	Reasoning	Score
Conciseness	Content is delivered mostly as compact reference tables (URL patterns, query operators, licenses, MCP params) that assume Claude's competence; the leading source-of-truth blockquote and a few prose notes could be trimmed, keeping it just short of lean.	4 / 5
Actionability	Concrete, specific guidance throughout — exact query operators with examples, MCP tool params with types/defaults, and numbered UI steps for forking and inference — with only minor gaps (UI-click steps lack copy-paste equivalents).	4 / 5
Workflow Clarity	Forking, downloading, and inference are laid out as clear numbered sequences with prerequisites noted (e.g. 'Requires: Logged-in Roboflow account'); these are non-destructive UI flows so absent validation checkpoints are acceptable, leaving minor gaps.	4 / 5
Progressive Disclosure	No bundle files exist, but the body is well-structured into clearly headed sections and tables with a 'Related Skills' cross-reference; some inline reference material (licenses, full operator table) could be split out, so it is not a 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 well-targeted description with a clear trigger and distinct niche, weakened only by slightly thin action coverage in the 'what' clause. It is specific enough to fire reliably for the intended use case.

Suggestions

Add one or two more concrete actions (e.g. 'fork, download, or run inference on') to lift specificity from 1-2 actions toward comprehensive coverage.

Expand the 'what' clause beyond a repository description to state the skill's capability directly (e.g. 'Find, evaluate, fork, and download datasets, and run pre-trained models').

Dimension	Reasoning	Score
Specificity	Names the domain (Roboflow Universe) with two concrete actions ('searching for or using public datasets/models'), but coverage is narrow and not comprehensive, matching the '1-2 concrete actions' anchor.	3 / 5
Completeness	Both 'what' (the open repository of datasets/models) and 'when' ('Use when searching for or using...') are present; the trigger is concrete but the 'what' could be slightly more action-oriented, so it sits just below a 5.	4 / 5
Trigger Term Quality	Strong natural keywords — 'datasets/models', 'computer vision datasets', 'pre-trained models', 'Roboflow Universe', and the universe.roboflow.com URL — give good coverage, though a few synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Scoped to a single named platform (Roboflow Universe) with distinct triggers, giving a clear niche and minimal conflict 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/universe/SKILL.md
Commit: f3b2cbd

Reviewed: 10 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.