Alexa Resources

Live events

Communities

Alexa Skills Kit Technical Resources

 
Sustainability Resources

Datasets:

 

Additional bonus category resources: 

Circular Economy / Recycling

Energy and Water Efficiency

Sustainable Transportation

Disaster Relief

STEM Education

 

Building Alexa Skills “For Good”

What exactly is a “tech for good” skill? It’s a skill that has a positive impact on the planet or on local communities and that solves a real customer problem. These should be skills that customers keep coming back to because they continue to provide ongoing value. Here are a few ideas of the types of skills we are thinking of in each of our content bonus prize categories:

  • Sustainable transportation: A skill that helps you plan your route using public transit, or that tells you the location of the nearest bike-share bike or electric vehicle charging station, or a skill that introduces you to local carpooling resources would all have a positive impact on the environment while helping customers.
  • Circular economy: A skill that helps customers understand what can/cannot be recycled in their area, or that identifies the nearest drop-off point and operating hours for a nonprofit that accepts donations of household goods, or a skill that teaches you how to maintain and extend the useful life of products or gear that you own would all count.
  • Resource efficiency: A skill that helps you improve your energy efficiency at home or that connects with your utility data to help you track and improve your energy or water consumption would all have a positive impact on the environment and customers.
  • STEM Education: A skill that helps students and parents find local extracurricular STEM learning opportunities (camps, afterschool programs, etc.) or that helps facilitate STEM learning, like an interactive game to broaden knowledge of STEM topics or careers.
  • Disaster relief: A skill that notifies a customer of a weather service watch, alert, or advisories impacting the area where the customer lives, or a skill that helps a customer learn about the ways to help with a disaster – from donating cash or products to volunteering.

Using Open Data to Create Richer Skills


One way to build richer Alexa skills is to make sure you provide relevant and dynamic information to customers every time they use your skill. For example, if you create a simple fact skill, a user may find the experience interesting the first and second time they use the skill but after that, they will keep running into the same information and might no longer see value in using your skill. Using open data can help you pull information that is relevant and different every time your customer comes back to use your skill. Here is a quick example to illustrate how this could work (Btw, this hasn't been built yet for those of you still looking for ideas...)

Imagine a customer who faces allergies when exposed to poor air quality. This is not uncommon for city dwellers around the world. This customer could benefit from using an Alexa Skill that helps identify the air quality at a location on a particular day. By using data from OpenAQ as an example, the skill could help customers learn about the most recent air quality measurement in their area. A customer could ask: “Alexa, ask [NAME OF SKILL] what the air quality is in [CITY NAME]?”. You can check out this recent machine learning blog on predicting the impact of weather on urban air quality using Amazon Sagemaker.

This is a great example to illustrate that customer would come back to use the skill more often because not only does it make information more accessible, it also provides relevant information to them on a day-to-day basis.

How to Build Great Skills for Echo Show and Echo Spot

With the Echo family of devices now including devices with screens like Echo Show and Echo Spot, you have to consider their graphical user interface (GUI) in addition to their voice user interface (VUI) during the voice design process. To help you understand this and do it in the best way possible, we've outlined top tips for designing multimodal, voice-first experiences that prove engaging across all Alexa-enabled devices. Read the full blog, here.

Using Advanced Voice Features

In the past few months, Alexa has released a series of features to help you build richer, more personalized experiences for Alexa customers. One of our bonus prize categories “Best use of Advanced Voice Features” will specifically reward skills that make use of these features and create deeper, richer experience for Alexa customers. Read more about each feature below:

Dialog Management: Real conversations are dynamic, moving between topics and ideas fluidly. To create conversational Alexa skills, design for flexibility and responsiveness. Skills should be able to handle variations of conversation, conditional collection of data, and switching context mid-conversation. Dialog management makes these natural interactions possible. Read more, here.

Entity Resolution enables you to define synonyms for the Alexa Service to resolve rather than having to figure this out in your code. For example, in your Alexa skill, rain may be synonymous with, downpour, shower, storm, and rainstorm. When the customer says downpour, the Alexa Service will let you know that they said “downpour” and it will also let you know that it’s a synonym for “rain”. Read more, here.

Memory (persistence): Implementing memory (persistence) in your skill means that you can store data about a previous user session to use it in future ones. This is incredibly useful to create experiences that have context rather than starting each session from scratch every time. Adding context to your conversation is what can help make it feel more natural to the user. Watch the tutorial, here.

CanFullFillIntent: You can make it easier for customers to find and engage with your skills by adding support for the CanFulfillIntentRequest. Using CanFulfillIntentRequest, your skill provides information about its ability to fulfill a given customer request at runtime. Alexa combines this information with a machine-learning model to choose the right skill to use when a customer makes a request without an invocation name. As a result, customers find the right skill faster, using the search terms they say most naturally. Read more, here.

Top Tips for Certification

The Alexa Skills catalog is home to tens of thousands of Alexa Skills thanks to our amazing developer community. And as most you know, every Alexa skill submitted to Amazon undergoes a certification process prior to being published in our public catalog. To help you navigate this process, we've shared its main purpose and requirements, the top issues we're seeing, and some helpful reference material. Read the full blog, here.

Our top tip this week is for you to submit your skill early and get it certified. Getting your skill published at least in the US Skill store is an eligibility requirement to receive any prizes.