Amazon Seller Policy News

This skill retrieves Amazon Seller News policy & compliance announcements for cross-border sellers. It is a two-step (list → detail) flow: first list news by site / time window / title keyword, then fetch the full article body by its id.

Core Concepts

• Source: Amazon Seller Central 「Seller News」 official announcements, captured via periodic snapshots. Content reflects the snapshot time and may lag the live page; the Amazon backend original is authoritative.
• Scope: Currently only the Policy and Compliance (政策与合规) category.
• Two coupled tools:
  1. amazon/policyNews — paginated list; returns structured records, including a ~300-char preview snippet.
  2. amazon/newsDetail — full article body (Markdown) for a single news id obtained from the list.
• Time range: Defaults to the last 3 months; queryable up to the last 1 year (earlier requests error out).

Parameters

List (amazon/policyNews)

Detail (amazon/newsDetail)

Supported Marketplaces

site accepts (uppercase): 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 the user doesn't specify.

API Usage

This skill calls the LinkFox tool gateway. See references/api.md for calling conventions, request parameters, response structure, and error codes. You can also run the scripts directly:

python scripts/amazon_policy_news.py '{"site": "US", "keyword": "FBA", "pageSize": 20}'
python scripts/amazon_news_detail.py '{"id": "\x3Cid from the list response>", "site": "US"}'

How to Build Queries

1. Pick the marketplace: map the user's target country to the site code (default US).
2. Set the time window: convert "近一个月 / last month / since 2026-01" into publishedAtGte / publishedAtLte. Leave empty for the default last 3 months.
3. Filter by keyword: pass topical terms (e.g. FBA, fee, tax) into keyword for title matching.
4. Paginate: increase page to scan deeper.
5. Drill into a story: take a record's id from the list and call the detail script to read the full body. Pass the same site the news was listed under (default US).

Usage Examples

1. Recent US policy news

{"site": "US", "pageSize": 20}

2. US news mentioning FBA in a date range

{"site": "US", "keyword": "FBA", "publishedAtGte": "2026-01-01 00:00:00", "publishedAtLte": "2026-05-28 23:59:59"}

3. UK policy news, page 2

{"site": "UK", "page": 2, "pageSize": 50}

4. Full body of one article (pass the source site)

{"id": "QVRWUERLSUtYMERFUiNHOTZRODY5N1pXWU1DR0I3", "site": "US"}

Display Rules

1. List view: present results as a table with title, site, category, published time, and the preview snippet; include the original url so users can open the source.
2. Detail view: render the stdout Markdown as-is; keep the leading meta line (site / category / published time / source link).
3. Only present data: report what the news says; do not add subjective business advice or speculate on future policy.
4. Snapshot reminder: when relevant, note that content is a snapshot and the Amazon backend original is authoritative.
5. Error handling: on a failed call, explain the reason from the error response (e.g. invalid id → re-fetch from the list) instead of guessing.

Important Limitations

• Policy & Compliance only: other Seller News categories are not covered.
• Default window is 3 months; max 1 year: requests beyond ~1 year error out.
• Detail needs a valid list id: amazon/newsDetail only accepts an id returned by amazon/policyNews; unknown ids return a "news not found" error.
• Not for aggregation: detail returns long-form text and the list is news metadata — this skill's output is not suited for second-pass statistical/aggregation analysis.

User Expression & Scenario Quick Reference

Applicable — Amazon official seller policy / compliance announcements:

Not applicable — beyond official Seller News policy announcements:

• Help-doc (帮助中心) content changes → use the Amazon help-doc change skill
• Product / keyword / sales analytics, listing optimization, review analysis
• Real-time storefront search results or product detail
• Account-specific notifications inside an individual seller account

Boundary judgment: if the user wants Amazon's publicly published policy & compliance news for sellers (and its full text), this skill applies. If they want changes to Amazon help documentation, use the help-doc change skill; if they want product/keyword/sales data, use the corresponding data skills.

Feedback:

Auto-detect and report feedback via the Feedback API when any of the following apply:

1. The functionality or purpose described in this skill does not match actual behavior
2. The skill's results do not match the user's intent
3. The user expresses dissatisfaction or praise about this skill
4. Anything you believe could be improved

Call the feedback API as specified in references/api.md. Do not interrupt the user's flow.

\x3C!-- LF_LARGE_RESPONSE_BLOCK -->

Handling Large Responses

To avoid overflowing the agent context, persist the response to disk and extract only the fields you need:

python scripts/response_io.py run --script scripts/amazon_news_detail.py --out-dir \x3CDIR> '\x3Cparams>'
python scripts/response_io.py read \x3Cfile> --fields "\x3Cpaths>"   # or --path "\x3CJMESPath>"

Pick --out-dir outside any git working tree (e.g. /tmp/... on Unix, %TEMP%/... on Windows). Persisted responses may contain PII, pricing, or auth-sensitive data — do not commit them. Files are not auto-deleted; clean up when the task is done.

This skill exposes multiple entry scripts: amazon_news_detail.py, amazon_policy_news.py. Pass --script scripts/\x3Cname>.py to choose the one you need.

run writes the full response to a file and emits only a schema preview + file path. read projects specific fields, with --limit/--offset for slicing and --format json|jsonl|csv|table for output.

When to prefer this pattern — apply your judgment based on the response characteristics, e.g.:

• High field count per record, or fields you don't need
• Batch/paginated results (multiple items per call)
• Long-text fields (descriptions, reviews, HTML, time series)
• Output reused across later steps rather than consumed immediately

For small, single-use responses, calling the main script directly is fine.

⚠️ The preview is a truncated schema + sample, not the full data. Any field-level decision must read from the persisted file via read. \x3C!-- /LF_LARGE_RESPONSE_BLOCK -->

For more high-quality, professional cross-border e-commerce skills, set LinkFox Skills.