SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillslinkfox-amazon-help-doc-changes

linkfox-amazon-help-doc-changes

General & other

View repository

Updated 10-16 00:00

About this skill

Amazon Help Doc Change Monitor

This skill monitors changes to Amazon Seller Central Help documentation. An AI layer pre-screens edits and surfaces only the changes that actually matter to sellers. It is a two-step (list → detail) flow: first list AI-curated valuable changes by time window / title keyword, then fetch the change detail + latest full document by its id.

Core Concepts

  • AI-curated, not raw diffs: results contain only changes the AI judges "valuable to sellers". Pure formatting / non-substantive edits are filtered out, so the returned count is usually far smaller than the document's actual edit count — this is by design, not missing data.
  • Two coupled tools:
    1. amazon/helpDocChanges — paginated list of valuable changes (structured), each with an AI-generated Chinese summary, ordered by change time (newest first).
    2. amazon/helpDocDetail — full change detail for one change id: AI summary + what specifically changed + the latest document body (Markdown).
  • Coverage & timing: monitors English (en-US) help docs by default. changedAt is the detection time (when the system detected the diff), not Amazon's official publish time. Change monitoring data starts from 2026-05-29. The Amazon backend original is authoritative.

Parameters

List (amazon/helpDocChanges)

Parameter Type Required Description Default
keyword string No Document-title fuzzy match (case-insensitive) -
changedAtGte string No Change-time lower bound (incl.), yyyy-MM-dd HH:mm:ss last 3 months
changedAtLte string No 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

No parameter is required — call with no params to get the last 3 months of valuable changes.

Detail (amazon/helpDocDetail)

Parameter Type Required Description
id integer Yes Change-record ID (≥1) from the list response data[].id

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_help_doc_changes.py '{"keyword": "FBA", "pageSize": 20}'
python scripts/amazon_help_doc_detail.py '{"id": <id from the list response>}'

How to Build Queries

  1. Set the time window: convert "last month / since 2026-03" into changedAtGte / changedAtLte. Leave empty for the default last 3 months.
  2. Filter by keyword: pass topical terms (e.g. FBA, fee, inventory) into keyword for title matching.
  3. Paginate: increase page to scan more changes.
  4. Drill into a change: take a record's id (integer) from the list and call the detail script to read the AI summary, the specific edits, and the latest document.

Usage Examples

1. Valuable changes in the last 3 months (default)

{}

2. FBA-related doc changes in a date range

{"keyword": "FBA", "changedAtGte": "2026-03-01 00:00:00", "changedAtLte": "2026-05-28 23:59:59"}

3. Page 2, 50 per page

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

4. Full change detail of one record

{"id": 35}

Display Rules

  1. List view: present results as a table with title, breadcrumb (directory path), change time, and the AI summary; include the original url.
  2. Detail view: render the stdout Markdown as-is; keep the leading change-summary / change-time / breadcrumb / source-link block.
  3. Set expectations on count: when results look sparse, remind the user that only AI-judged valuable changes are returned (formatting-only edits are filtered) — a low count is expected, not a data gap.
  4. Only present data: report what changed; do not add subjective business advice.
  5. Detection-time caveat: note that changedAt is the detection time, not Amazon's official publish time; the backend original is authoritative.
  6. Error handling: on a failed call, explain the reason from the error response (e.g. invalid id → re-fetch from the list).

Important Limitations

  • AI-filtered results: only "valuable to sellers" changes appear; returned count is far smaller than the raw edit count (by design).
  • English docs by default: monitors en-US help documentation.
  • Monitoring start: change data begins from 2026-05-29; earlier history is unavailable.
  • Detail needs a valid list id: amazon/helpDocDetail only accepts an integer id returned by amazon/helpDocChanges.
  • Not for aggregation: detail returns long-form text and the list is change metadata — this skill's output is not suited for second-pass statistical/aggregation analysis.

User Expression & Scenario Quick Reference

Applicable — Amazon help-center documentation change monitoring:

User Says Scenario
"What noteworthy changes have there been in Amazon help documentation in the last month?" Recent valuable changes by time
"What changed in Amazon's help documentation about FBA?" Keyword-filtered doc-change lookup
"Help me look at the details and latest full text of this document change" Fetch change detail + latest doc by id
"Have the Help Center rules been updated?" Help-center rule-change monitoring
"Fee-related document adjustments" Fee/policy documentation change tracking

Not applicable — beyond help-doc change monitoring:

  • Amazon Seller News policy announcements → use the Amazon policy-news 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 to know what changed in Amazon's help documentation (and the change detail / latest text), this skill applies. If they want Amazon's published Seller News policy announcements, use the policy-news 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.

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_help_doc_changes.py --out-dir <DIR> '<params>'
python scripts/response_io.py read <file> --fields "<paths>"   # or --path "<JMESPath>"

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_help_doc_changes.py, amazon_help_doc_detail.py. Pass --script scripts/<name>.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.

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