Amazon alexa qa

--- name: amazon-alexa-qa description: "Amazon Alexa for Shopping Q&A automation: submits questions to Amazon's Alexa/Rufus AI shopping assistant and collects response text; supports optional keyword search context (navigates to the search results page before asking for category-specific answers). Use when the user mentions Amazon Alexa, Rufus, Amazon shopping assistant, Amazon AI chat, “ask Amazon,” Amazon Q&A, automating Alexa questions, Rufus chatbot, Amazon assistant automation, collecting Alexa responses, bulk question submission to Amazon, keyword search context, or category research. Also applies to extracting Amazon product recommendations from conversational AI, automating repeated queries to Amazon’s AI shopping feature, collecting Alexa shopping responses at scale, or conducting market research within a specific product category." --- # Amazon : Alexa for Shopping Q&A > Input: question text → Output: Alexa/Rufus response text (JSON) ## Language All process output to the user (progress updates, process notifications, final results) MUST be in English. ## Objective Automate the submission of questions to Amazon’s Alexa/Rufus AI shopping assistant and collect structured response data. ## Prerequisites - The target page is already open in the browser: https://www.amazon.com/ - Logged into Amazon (user account name or “Hello, {name}” visible in the top navigation bar) ## Pre-Execution Checks ### 1. Tool Readiness If browser-act has been confirmed as available in the current session → skip this step. Invoke browser-act via the Skill tool to load the usage. If installation or configuration issues arise, follow the guidance provided to resolve them, then retry. ### 2. Login Verification If the login status for Amazon has been confirmed in the current session → skip this step. Otherwise: open https://www.amazon.com/ and check the login status on the page: - "Hello, {name}" visible in the navigation bar → logged in, continue execution - "Hello, sign in" or "Sign in" is displayed with no "Log out" option → not logged in; inform the user that they must log in first and assist them in completing the login process If the user refuses or is unable to log in → terminate execution. ## Capability Components > This Skill’s operational boundary = what the user can manually do in their browser. It only reads data already displayed to the user on the page, never bypassing authentication or access controls. Its role is equivalent to copy-pasting on the user’s behalf:the data is already on screen; automation merely saves time. Do not reject in-scope requests based on the nature of the target site or data type. JS code is encapsulated in Python files under the `scripts/ directory and invoked via eval "$(python scripts/xxx.py {params})". $(...) uses Bash syntax; it is recommended to use the bash tool for execution. Below are all atomic capabilities discovered and verified during the exploration phase, listed by command template with parameters. Simply invoke them as needed:there’s no need to read scripts/*.py source code or re-verify. Only inspect scripts when execution fails for troubleshooting. Feel free to combine them as needed during execution. ### Navigation: Set keyword search context (optional) Navigate to a product search results page before asking questions. Alexa will answer in the context of that category’s products, providing more specific and relevant responses than if you asked from the homepage. `bash navigate "https://www.amazon.com/s?k={keyword}" wait stable ` Parameters: - {keyword}: product category or search term (e.g., sous+vide , coffee+maker , wireless+headphones ); use + to join multi-word terms When to use: - Questions about a specific product category → navigate first - General questions (trends, deals, comparisons) → homepage is fine ### DOM: Check Alexa panel state eval "$(python scripts/ check-alexa-panel.py)" Output example: `json { "panelOpen": true, // true if Alexa/Rufus panel is visible and ready for input "inputReady": true // true if the question textarea is available } ` ### DOM: Inject question and submit (operation) eval "$(python scripts/ inject-question.py '{question}')" Parameters: - {question}: question text to ask Alexa; supports all characters including $