Agent skill · software engineering · aiskillstore
fiftyone-dataset-inference
Create a FiftyOne dataset from a directory of media files (images, videos, point clouds), optionally import labels in common formats (COCO, YOLO, VOC), run model inference, and store predictions. Use when users want to load local files into FiftyOne, apply ML models for detection, classification, or segmentation, or build end-to-end inference pipelines.
Why this skill is useful
Adds executable scripts for creating FiftyOne datasets, importing media and labels, and running model inference that are not commonly found in public documentation.
What it needs
Requires fiftyone installed locally. About 5k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
Create Dataset and Run Inference Overview Create FiftyOne datasets from local directories, import labels in standard formats, and run model inference to generate predictions. Use this skill when: Loading images, videos, or point clouds from a directory Importing labeled datasets (COCO, YOLO, VOC, CVAT, etc.) Running model inference on media files Building end-to-end ML pipelines Prerequisites FiftyOne MCP server installed and running @voxel51/io plugin for importing data @voxel51/zoo plugin for model inference @voxel51/utils plugin for dataset management Key Directives ALWAYS follow these rules: 1. Explore directory first Scan the user's directory before importing to detect media types and label formats. 2. Confirm with user Present findings and get confirmation before creating datasets or running inference. 3. Set context before operations 4. Launch App for inference 5. User specifies field names Always ask the user for: Dataset name Label field for predictions 6. Close app when done Workflow Step 1: Explore the Directory Use Bash to scan the user's directory: Identify media files and label files. See Supported Dataset Types section for format detection. Step 2: Present Findings to User Before creating the dataset, confirm with the user: Step 3: Create Dataset Step 4: Set Context Set context to the newly created dataset before importing: Step 5: Import Samples For media only (no labels): For media with labels: Step 6: Validate Import Verify samples imported correctly by comparing with source: Compare numsamples with the file count from Step 1. Report any discrepancy to the user. Step 7: Launch App Step 8: Apply Model Inference Ask user for model name and label field for predictions. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/fiftyone-dataset-inference