Name: roboflow-data-management
Rating: 65.60000000000001 (1 reviews)
Author: roboflow

roboflow-data-management

Use when uploading images, labeling, organizing datasets, creating Roboflow projects (detection/segmentation/keypoint/classification), tags, splits, versions, or RoboQL search.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

68%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, token-efficient reference whose tables and concrete examples make it highly actionable. Its main weakness is workflow_clarity: destructive and batch operations carry warnings but no explicit validation feedback loops.

Suggestions

Add an explicit validate-before-proceed checkpoint for irreversible class operations (e.g., confirm the change, suggest using version-level 'Modify Classes' first, verify the result).

For version generation, document a verification step after 'Generate' (e.g., inspect the version with versions_get and confirm split/augmentation settings before exporting).

Replace the MCP URI references in 'Related Pages' with markdown links where local plugin files are available, to make navigation clearer when the plugin is loaded.

Dimension	Reasoning	Score
Conciseness	Dense table-driven reference that avoids explaining concepts Claude already knows, but the overall length means a few sections could be trimmed further.	4 / 5
Actionability	Provides executable CLI ('roboflow import ...'), Python SDK export code, concrete RoboQL filter syntax, and specific UI navigation paths, with only minor gaps.	4 / 5
Workflow Clarity	The version creation pipeline is clearly sequenced, but destructive/batch operations (irreversible class changes, version generation) lack explicit validate-then-proceed feedback loops, capping this dimension.	3 / 5
Progressive Disclosure	Well-organized sections with one-level-deep references in 'Related Pages' (labeling, cloud-storage skills); no bundle files exist, and content is appropriately split, though navigation relies on MCP URIs.	4 / 5
	Total	15 / 20 Passed

Description

87%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 strong, trigger-first description that pairs an explicit 'Use when' clause with a broad list of concrete Roboflow data-management actions. It is distinct and comprehensive, with only minor generic phrasing ('organizing datasets') and missing synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'uploading images, labeling, ... tags, splits, versions, or RoboQL search' — but 'organizing datasets' is generic, leaving minor coverage gaps.	4 / 5
Completeness	Explicit 'Use when...' clause supplies the trigger while the enumerated actions answer 'what', matching the anchor for clearly answering both with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural terms a user would say (uploading, labeling, splits, versions, RoboQL) are well covered, though synonyms and file extensions are absent.	4 / 5
Distinctiveness Conflict Risk	The Roboflow-specific vocabulary (Roboflow projects, RoboQL, splits, versions) carves a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	18 / 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-data-management/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.