Skip to content

nexscope-ai/nexscope-ecommerce-skills / ecommerce-amazon-alexa-search

ecommerce.amazon-alexa-search

Verified

Initiate natural language Q&A through Amazon's storefront Alexa shopping assistant to get shopping guidance answers, recommended product groups, ASIN lists, and follow-up questions. Each call supports only 1 prompt; for follow-ups, the agent must summarize context and concatenate a new question for a new request. A url can be used to supplement Amazon page context. Trigger when the user mentions Amazon Alexa, Alexa shopping assistant, Amazon smart assistant, AI shopping guide, conversational product selection, natural language shopping, Amazon chat Q&A, Amazon Alexa shopping, conversational shopping, AI shopping assistant, follow-up questions, product recommendation conversation, context follow-ups. Even if the user does not explicitly mention "Alexa", if their need is to "ask for product recommendations on Amazon using natural language", this skill should also be triggered.

FileKindSize
SKILL.mdskill md13.9 KB
manifest.jsonconfig287 B
references/api.mdmarkdown7.2 KB
scripts/amazon_alexa_search.pyscript6.5 KB

references/api.md

View on GitHub
# Amazon Alexa Shopping Assistant API Reference

## API Specification

- **Endpoint**: `${NEXSCOPE_PROXY_BASE}/api/v1/tools/research/amazon/alexaSearch`
- **HTTP Method**: POST, Content-Type: application/json
- **Authentication**: Header `Authorization: <api_key>`, api_key is read from environment variable `NEXSCOPE_API_KEY` or `NEXSCOPE_API_KEY` (if not configured, follow the **## Resolving Authentication and Credits Issues** section in SKILL.md)

## Request Parameters

POST Body (JSON):

| Parameter | Type | Required | Description |
|------|------|------|------|
| prompts | string[] | Yes | Conversation prompt array, supports only **1 entry**. Each call accepts only 1 question. For follow-up questions, the agent must summarize key information from the previous response (recommended products, ASINs, key conclusions, etc.), concatenate it with the new question, and send it as a new `prompts[0]`. Each call is an independent new session and does not retain cross-call conversation history |
| format | string | No | Response format: `markdown` (default) returns a readable report; `json` returns a structured data array |
| url | string | No | Linked page URL, used to supplement the page context of Alexa's current response. Only pass this when the user provides a **specific page** (category page / search results page / product detail page, etc.); do **not** pass this parameter for the Amazon homepage (e.g. `https://www.amazon.com/`) |

## Nexscope response envelope

These research endpoints return a platform object with numeric `code`, nullable `msg`, and business `data`. Only outer `code: 0` means success; `200`, string codes, missing codes, and HTTP 200 alone do not. A nonzero code is a platform error: show `msg` and do not interpret the payload as a successful result.

`msg` preserves the upstream message when available; Chinese messages are translated to English by Nexscope. A successful response without a message has `msg: null`. Do not infer success or retry behavior from the message text. On both success and failure, the direct fields `code`, `errcode`, `errorCode`, `msg`, `errmsg`, `message`, and `errorMsg` are removed from public `data`. Read the message only from outer `msg`; deeper business fields are preserved, including nested `code` and `status`.

Business field tables and abbreviated business examples below describe `data`, unless explicitly labeled as a complete platform response. For example, a business `products` field is at HTTP `data.products`, and a business `data` array is at HTTP `data.data`. The research endpoints already had this outer envelope; no additional wrapper is added.

```json
{"code":0,"msg":null,"data":{}}
```

Metadata includes string `ts` (epoch milliseconds), string `cost` (elapsed milliseconds, not credits), `time`, and nullable `traceId`. Handle network/HTTP failures before the platform code; gateway failures may not be platform JSON. Keep the existing billing-header guidance separate from elapsed time.

## Response Structure

| Field | Type | Description |
|------|------|------|
| stdout | string | Markdown format Q&A report, containing each round's user question, Alexa answer, recommended products, and follow-up questions; only returned when `format=markdown` |
| data | array | Structured conversation result array; only returned when `format=json` |
| resultsNum | integer | Number of conversation rounds Alexa actually answered; 0 means no valid response was produced |
| costTime | integer | API latency in milliseconds |
| costToken | integer | Tokens consumed by this call; charged only if upstream succeeds |
| taskId | string | Task identifier returned by upstream |
| type | string | Render style: `stdoutWorkbenches` (markdown) or `json` |

### `data[*]` Structure (`format=json`)

| Field | Type | Description |
|------|------|------|
| prompt | string | Prompt sent to Alexa for this round |
| content | string | Text content of Alexa's response for this round |
| screenshot | string | Screenshot link for this round's conversation |
| followUpQuestions | string[] | List of follow-up questions recommended by Alexa |
| products | array | Recommended product group list, each group containing `title` and `items` |
| products[].title | string | Recommended group title |
| products[].items[].asin | string | Product ASIN |
| products[].items[].title | string | Product title |
| products[].items[].url | string | Product detail page URL |
| products[].items[].cover | string | Product cover image URL |
| products[].items[].price | string | Current price (with currency) |
| products[].items[].originalPrice | string | Original or strikethrough price |
| products[].items[].score | string | Rating |
| products[].items[].ratingsCount | string | Review count |
| products[].items[].describe | string | Product description |

## Error Codes

HTTP 200 does not prove business success. Read only the numeric outer platform `code`: `0` succeeds and any other value fails. Show outer `msg`; never test removed provider codes or nested business `code` as the platform status. Authentication, permissions, balance, and validation failures may be platform errors even with HTTP 200; also handle non-2xx HTTP and non-JSON responses.

### Recovery guidance

| Condition | Action |
|---|---|
| Authentication failed | HTTP 401 or authorized error: follow the **## Resolving Authentication and Credits Issues** section in SKILL.md. |
| Billing/insufficient credits | HTTP 402: follow the **## Resolving Authentication and Credits Issues** section in SKILL.md. |

## curl Example

**Markdown format (default):**

```bash
curl -X POST ${NEXSCOPE_PROXY_BASE}/api/v1/tools/research/amazon/alexaSearch \
  -H "Authorization: Bearer ${NEXSCOPE_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
        "prompts": ["best wireless earbuds for running"]
      }'
```

**JSON format:**

```bash
curl -X POST ${NEXSCOPE_PROXY_BASE}/api/v1/tools/research/amazon/alexaSearch \
  -H "Authorization: Bearer ${NEXSCOPE_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
        "prompts": ["best electric kettle on Amazon US"],
        "format": "json"
      }'
```

Platform success response excerpt (business content abbreviated):

```json
{
  "code": 0,
  "msg": "ok",
  "data": {
    "stdout": "# Amazon Alexa Shopping Assistant\n\n## Question 1: best wireless earbuds for running\n\n### Alexa Answer\n- ...\n\n### Recommended Products\n- ...\n\n### Follow-up Questions\n- ...\n",
    "resultsNum": 1,
    "costTime": 12000,
    "costToken": 1500,
    "type": "stdoutWorkbenches",
    "taskId": "1779367311421-d728ce53704fc86e"
  }
}
```

---

## API Key request rate and retries

All API Keys of one Nexscope user share the public API execution request-rate allowance, measured in any rolling 1-second window. The allowed RPS depends on that user's entitlements; it is not a universal 1 RPS. One Skill operation may issue multiple public API requests, each of which uses the allowance.

HTTP 429 with Nexscope outer code `13012` means request-rate exhaustion: honor the response's `Retry-After`. Outer code `13013` means concurrent-request exhaustion, not rate exhaustion; honor `Retry-After` when supplied. Check the HTTP status and outer JSON code separately. Do not automatically replay writes or requests with uncertain outcomes; first reconcile the operation's state.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall