CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 strong, information-dense skill body: concrete operators, tool parameters, and step-by-step workflows with almost no padding. The only real improvements are removing the fork/download duplication and deciding whether the operator and license tables belong in reference files.

DimensionReasoningScore

Conciseness

The body is dense and table-driven with no explanations of concepts Claude already knows. It falls short of anchor 5 due to minor duplication — fork/clone is described in both 'Forking a Dataset' and 'Downloading a Dataset', the license location is stated twice, and the 'For agents' blockquote is housekeeping overhead.

4 / 5

Actionability

Guidance is fully concrete and copy-paste ready: exact operator syntax with worked queries ('pothole road damage class:pothole images>100 sort:stars'), a complete universe_search parameter table with return fields, numbered UI steps, and the model ID format '{owner}/{project}/{version}'. This matches anchor 5.

5 / 5

Workflow Clarity

Forking (4 numbered steps) and Workflows inference (5 numbered steps) are clearly sequenced, and 'Evaluating a Dataset' acts as a pre-flight checklist. Not anchor 5 because there are no explicit post-operation validation or feedback loops.

4 / 5

Progressive Disclosure

No bundle files exist, and the skill is self-contained at ~150 lines with clean section headers and clearly signaled one-level-deep 'skill://' links under 'Related Skills'. Not anchor 5 because some reference-grade tables (full query operators, license matrix) could live in separate files.

4 / 5

Total

17

/

20

Passed

Description

70%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-formed description with an explicit 'Use when' trigger, a concrete domain, and a distinguishing URL. Its main weakness is thin action coverage — 'searching for or using' undersells the fork/download/evaluate/deploy guidance the body actually provides.

Suggestions

Enumerate the skill's concrete actions in the description, e.g. 'Search, evaluate, fork, download, and run inference with public computer vision datasets and pre-trained models on Roboflow Universe'.

Add one or two natural user synonyms (e.g. 'labeled vision data', 'pretrained model') to broaden trigger coverage beyond 'datasets/models'.

Tighten the what/when split so the 'what' clause describes the skill's capabilities rather than restating what the Universe website is.

DimensionReasoningScore

Specificity

The description names the domain ('public datasets/models on Roboflow Universe', '1M+ computer vision datasets and 50K+ pre-trained models') with only two actions — 'searching for or using' — where 'using' is generic. It does not reach anchor 4 because concrete capabilities the skill covers (forking, downloading, license evaluation, model inference) are absent.

3 / 5

Completeness

Both parts are explicit: what ('the open repository of 1M+ computer vision datasets and 50K+ pre-trained models') and when ('Use when searching for or using public datasets/models'). Not anchor 5 because the 'what' describes the site more than the skill's actions, and trigger phrases are narrow.

4 / 5

Trigger Term Quality

Natural phrases like 'searching for', 'public datasets/models', 'computer vision datasets', 'Roboflow Universe' plus the explicit URL give good trigger coverage. It falls short of anchor 5 because common user synonyms such as 'vision dataset', 'pretrained model', 'labeled data', or 'YOLO' are missing.

4 / 5

Distinctiveness Conflict Risk

The niche is clear and site-specific ('Roboflow Universe (universe.roboflow.com)'), but the broad 'using public datasets' trigger overlaps closely related sibling skills (roboflow-data-management, roboflow-training-and-evaluation), matching anchor 4 rather than 5.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

Reviewed

Table of Contents

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.