Query Amazon is latest policy, regulation, and compliance feed. Supports paginated browsing by marketplace and time range (with AI-generated Chinese summaries), and fetching full article body by record ID. Trigger when users mention Amazon policies & regulations, seller compliance announcements, platform rule changes, policy alerts, FBA/fee policy updates, multi-marketplace policy tracking, policy original text, news details, or similar terms. Even if the user does not explicitly mention "policy feed," trigger this skill whenever the request involves Amazon is officially published policies, regulations, and news for sellers, including their full text.
npx skills add https://github.com/nexscope-ai/nexscope-ecommerce-skills --skill ecommerce.amazon-policy-feed
This skill retrieves Amazon is latest policy & regulation feed for cross-border sellers. It is a two-step (list then detail) flow: first list feed items by site / time window, then fetch the full article body by its id.
summaryZh field -- an AI-generated 1-3 sentence Chinese summary for quick scanning.amazon/policyFeed -- paginated list; returns structured records with title, AI summary, original URL, and publish time.amazon/policyFeedDetail -- full article body (Markdown) for a single record id obtained from the list.publishedAtGte / publishedAtLte.amazon/policyFeed)| Parameter | Type | Required | Description | Default |
|-----------|------|----------|-------------|---------|
| site | string | No | Marketplace code (uppercase); site filtering only applies to some feed item types, others are always returned regardless of site | US |
| publishedAtGte | string | No | Publish/change time lower bound (incl.), yyyy-MM-dd HH:mm:ss | last 7 days |
| publishedAtLte | string | No | Publish/change time upper bound (incl.), yyyy-MM-dd HH:mm:ss | now |
| page | integer | No | Page number, starting at 1 | 1 |
| pageSize | integer | No | Items per page, 1-100 | 20 |
amazon/policyFeedDetail)| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| id | string | Yes | Record ID (32-char string) from the list response data[].id |
site)US, JP, UK, AU, BE, BR, CA, EG, FR, DE, IN, IT, MX, NL, PL, SA, SG, ES, SE, TR, AE, ZA, IE. Default is US when not specified. Note: site filtering only applies to some feed item types; others are always returned regardless of site.
POST /amazon/policyFeed (amazon_policy_feed.py, full parameters/responses/error codes see references/api.md)POST /amazon/policyFeedDetail (amazon_policy_feed_detail.py, full parameters/responses/error codes see references/api.md)python scripts/<script_name>.py '<JSON params>' [--inline]Output Strategy (default script behavior):
<cwd>/nexscope/<YYYY-MM-DD>/<session>/data/nexscope-amazon-policy-feed-<timestamp>.json (<cwd> is the working directory at script execution time, which in Claude Code is the current project directory; <session> is taken from the SESSION_ID environment variable, auto-grouped by user task; do NOT write to /tmp -- error out if the current directory is not writable)total/costToken, length of the largest list field + first 3 samples)--inline to force full output to stdout (while still writing to disk)Data Reading Tips: First check the summary to see if it is sufficient; when specific fields are needed, prefer using jq or ConvertFrom-Json to extract from the saved JSON file on demand, avoiding loading the entire JSON into context.
Set the NEXSCOPE_API_KEY environment variable. If authentication fails (401/402) or you see insufficient balance errors, visit https://www.nexscope.ai/help/skills-external-access?co-from=skillNS to get an API Key or top up credits.
publishedAtGte / publishedAtLte. Leave empty for the default last 7 days.site code (default US). Note this only filters some feed item types.page to scan deeper; max 100 items per page.id from the list and call the detail script to read the full body.1. Recent feed (last 7 days, US)
{"site": "US", "pageSize": 20}
2. Custom date range
{"site": "US", "publishedAtGte": "2026-05-01 00:00:00", "publishedAtLte": "2026-05-31 23:59:59"}
3. Japan site feed, page 2
{"site": "JP", "page": 2, "pageSize": 50}
4. Full body of one record
{"id": "a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4"}
summaryZh), publish time, and original URL link.stdout Markdown as-is; the response also includes title and summaryZh for context.id -> re-fetch from the list) instead of guessing.pageSize range is 1-100.id: amazon/policyFeedDetail only accepts an id returned by amazon/policyFeed; unknown ids return an error.Applicable -- Amazon official policy & regulation feed:
| User Says | Scenario |
|-----------|----------|
| "What are the latest Amazon policy changes?" | Recent policy feed overview |
| "Amazon US site policy news from the past week" | Site-filtered policy news |
| "What are the latest Amazon policy and regulation updates?" | General policy/regulation updates |
| "Amazon FBA latest policies and regulations" | Topic-specific policy lookup |
| "Show me the full text of this policy update" | Fetch full article body by id |
| "Amazon latest policy updates" | English trigger |
Not applicable -- beyond policy & regulation feed:
Boundary judgment: if the user wants Amazon is officially published policy, regulation, or compliance updates for sellers (and its full text), this skill applies. If they want product/keyword/sales data, use the corresponding data skills.
Take nexscope-ai/ecommerce.amazon-policy-feed from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.