Community Sample Skills

Guides Box Skills Community Sample Skills
Edit this page

Community Sample Skills

The community sample skills lists publicly available Skills samples that have been generated by the Box developer community. They are split up into four main categories, and are designed for the processing of files within their associated categories: Document Skills, Image Skills, Video Skills, and Audio Skills.

Community sample skills are created and maintained by the community, and are not owned or maintained by Box.

Want to submit your project? Please review the Contribution Guidelines.

See a full directory of Skills samples on GitHub

Document Skills

Box Skills samples for processing document files on Box.

NameDescription
Leverton Rental Lease Extraction (Node)Uses the Leverton API to automatically extract fields address, landlord, tenant, rent, etc, from rental leases and attach them to the respective files as Skills Metadata Cards
Rossum Invoice Intelligence (Node)Uses the Rossum API to automatically extract fields like amount, tax details, invoice ID, sender name and receiver name from invoices and attach them to the respective files as Skills Metadata Cards.

Image Skills

Box Skills samples for processing image files on Box.

NameDescription
Acuant AssureID Government ID Data Extraction (Node)Uses Acuant AssureID to classify and automatically extract metadata from a government-issued ID, such as name, numbers, address, etc, and add them as Skills Metadata Cards to the respective image files on Box.
Amazon Rekognition Labels Detection (Node)Uses the Amazon Rekognition API to automatically extract labels, which are objects, events, or concepts that are present in the image provided and add them to the respective image files as Skills Metadata Cards.
EXIF/XMP MetaInfo Extraction (Node)Uses the Javascript rewrite of the decade long open-source developed Exiftool to read dozens of MetaInfo from files. Works for all Image, Audio, Video files.
Google Product Search recognition (Node)Uses the Google Cloud Vision Product Search to compare images in Box with the images in a pre-trained product catalog.
Google Image Text and Topics (Node)Uses the Google Cloud Vision API to extract image texts and topics, using generic Google Image Search ML model for identification.
Hive Predict face recognition (Node)Uses the Hive Predict API to automatically recognize faces in images and assign these faces as Skills Metadata Cards to the respective images in Box.
Microsoft Image Text and Topics (Node)Uses the Microsoft Vision API to extract image texts and topics, using generic Bing Image Search ML model for identification.

Video Skills

Box Skills samples for processing video files on Box.

NameDescription
Microsoft Azure Video Faces, Transcript and Topics Extraction (Node)Uses the Microsoft Azure Media Services to extract Faces, Topics, and Transcripts from video files and write it back to Box as metadata on the file, as well show as close caption on the video itself.

Audio Skills

Box Skills samples for processing audio files on Box.

NameDescription
IBM Speech to Text Audio Transcription (Node)Uses the IBM Watson Speech to Text to extract transcripts from from audio files and write it back to Box as metadata on the file.
Microsoft Azure Transcript Topics Detection (Node)Uses the Microsoft Azure Media Services to extract Topics, and Transcripts from from audio files and write it back to Box as metadata on the file.
VoiceBase Dual-Channel Audio Analysis (Node)Uses the VoiceBase API to automatically extract data insights like transcript, topics, call metrics and sensitive information from audio files and attach them to the respective files as Skills Metadata Cards in Box Preview. This Skill is especially geared towards call center audio file analysis.