Name: roboflow-data-management
Rating: 88.6 (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.

1.45x

Quality

—

Does it follow best practices?

Impact

99%

1.45x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

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

A well-organized, token-efficient reference for Roboflow data management, but it is a monolithic inline manual rather than an overview with progressive disclosure, and its main programmatic surface (MCP tools) and destructive workflows lack executable examples and validation checkpoints.

Suggestions

Add executable MCP tool examples with key parameters (e.g. a projects_create and a versions_generate call) instead of a names-only table, so the primary API surface is copy-paste ready.

Insert validation checkpoints for destructive and batch operations: before bulk class changes, confirm use of version-level 'Modify Classes' for non-destructive edits, and verify split percentages before generating a version.

Move the large reference tables (preprocessing options, augmentation options, RoboQL filters) into files under references/ and link to them from a leaner SKILL.md overview to apply proper progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is a dense, table-driven reference with no concept explanations Claude already knows; every row is a distinct factual option, so tokens earn their place despite the breadth. It is not below 3 because there is no padding or generic tutorial prose.	3 / 3
Actionability	Concrete guidance exists (CLI 'roboflow import', SDK 'project.version(1).download("yolov8")', RoboQL syntax, UI paths), but the primary programmatic interface — the MCP tools table — lists only names and one-line purposes with no parameters or call examples, leaving key details missing.	2 / 3
Workflow Clarity	The version creation pipeline is a clear 5-step sequence, but destructive/batch operations (bulk class rename noted as 'irreversible', version generation, export) lack validation checkpoints or verify-before-proceed feedback loops, which caps this at 2 per the batch-operations guideline.	2 / 3
Progressive Disclosure	Sections and headers are well organized and references are only one level deep (a single Related Pages link), but at ~215 lines with no bundle files the large option tables (preprocessing, augmentation, RoboQL filters) are inline rather than split into reference files, so it is not a clean overview pointing to detail.	2 / 3
	Total	9 / 12 Passed

Description

100%

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, third-person description with an explicit 'Use when' trigger and a comprehensive, concrete list of capabilities and project-type variants. It is distinctive and low-conflict, with no padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'uploading images, labeling, organizing datasets, creating Roboflow projects (detection/segmentation/keypoint/classification), tags, splits, versions, or RoboQL search' — matching the score-3 anchor of several specific concrete actions rather than vague language.	3 / 3
Completeness	Opens with an explicit 'Use when ...' trigger clause and enumerates the actions that constitute what the skill does, clearly answering both what and when; it is not below 3 because the trigger guidance is explicit rather than implied.	3 / 3
Trigger Term Quality	Covers natural user terms across the domain ('uploading images', 'labeling', 'tags', 'splits', 'versions', 'RoboQL search') plus the four project-type variants, giving good coverage of phrases a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Scoped tightly to Roboflow data management with product-specific triggers (Roboflow projects, RoboQL), occupying a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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 12 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.