Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
linkfox-ai avatar

Linkfox Amazon Store Feeds

  • 182 installs
  • 64 repo stars
  • Updated August 3, 2026
  • linkfox-ai/linkfox-skills

Helps with ai & agent building tasks.

About

linkfox-amazon-store-feeds is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted development.

  • linkfox-amazon-store-feeds
  • AI & Agent Building
  • AI-coding skill

Linkfox Amazon Store Feeds by the numbers

  • 182 all-time installs (skills.sh)
  • +35 installs in the week ending Aug 2, 2026 (Skillselion tracking)
  • Ranked #3,035 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
  • Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/linkfox-ai/linkfox-skills --skill linkfox-amazon-store-feeds

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs182
repo stars64
Last updatedAugust 3, 2026
Repositorylinkfox-ai/linkfox-skills

What it does

Helps with ai & agent building tasks.

Files

SKILL.mdMarkdownGitHub ↗

Amazon 店铺 Feeds

本 skill 与 `linkfox-amazon-store-auth` 等同属 Amazon Store 系列:先 `POST /spApi/storeTokens`,再 `POST /spApi/developerProxy` 转发 GET / POST / DELETE

官方参考索引

能力文档
createFeedDocumentcreateFeedDocument
getFeedDocumentgetFeedDocument
createFeedcreateFeed
getFeedgetFeed
getFeedsgetFeeds
cancelFeedcancelFeed

---

Prerequisites

1. 依赖 `linkfox-amazon-store-auth`;运行 python scripts/check_auth_dependency.py,exit 42 时需先安装授权 skill。 2. 应用需具备 Feeds 相关角色;feedType 须与上传文件格式匹配(见 Amazon Feed Type Values 文档)。

---

典型工作流

1. `create_feed_document.py` → 得到 feedDocumentId`url`(上传地址)。 2. `upload_feed_document.py` → 对 url PUT 上传 feed 文件(不经 developerProxy)。 3. `create_feed.py` → 传入 inputFeedDocumentIdfeedTypemarketplaceIds。 4. `get_feed.py` / `get_feeds.py` → 轮询 processingStatus(如 IN_QUEUE、IN_PROGRESS、DONE、FATAL)。 5. 处理完成后用 `get_feed_document.py` 下载 resultFeedDocumentId 对应文档(再按返回 URL 自行下载结果文件)。

---

Current Capabilities

能力pathmethod脚本
createFeedDocumentfeeds/2021-06-30/documentsPOSTcreate_feed_document.py
getFeedDocumentfeeds/2021-06-30/documents/{feedDocumentId}GETget_feed_document.py
createFeedfeeds/2021-06-30/feedsPOSTcreate_feed.py
getFeedfeeds/2021-06-30/feeds/{feedId}GETget_feed.py
getFeedsfeeds/2021-06-30/feedsGETget_feeds.py
cancelFeedfeeds/2021-06-30/feeds/{feedId}DELETEcancel_feed.py
上传文档内容createFeedDocument 返回的 URLPUTupload_feed_document.py

共享模块:`_spapi_feeds_common.py`

---

Scripts 示例

export LINKFOXAGENT_API_KEY="<your-key>"

python scripts/create_feed_document.py '{"sellerId":"A1...","region":"NA","contentType":"text/tab-separated-values; charset=UTF-8"}'

python scripts/upload_feed_document.py '{"uploadUrl":"<from createFeedDocument>","contentType":"text/tab-separated-values; charset=UTF-8","filePath":"./inventory.tsv"}'

python scripts/create_feed.py '{"sellerId":"A1...","region":"NA","feedType":"POST_FLAT_FILE_INVLOADER_DATA","marketplaceIds":["ATVPDKIKX0DER"],"inputFeedDocumentId":"<feedDocumentId>"}'

---

Display Rules

1. 先看 `developerProxy.errcode` / `httpStatus`;createFeedDocument 常为 201,createFeed 常为 202。 2. getFeeds 分页:仅用上一页 `nextToken` 作为下一请求的 `paginationToken` 参数名在 Amazon 侧为 `nextToken`(脚本字段名 nextToken)。 3. upload 失败与 SP-API 网关无关,检查 uploadUrl 是否过期、Content-Type 是否与 createFeedDocument 一致。 4. 网关 path 白名单需包含 `feeds/2021-06-30/` 前缀。

---

Important Limitations

  • 本 skill 代替 Amazon 侧 feed 文件 schema 校验;feedType、TSV/XML 格式以官方为准。
  • 下载 getFeedDocument 返回的 url 内容需另行 HTTP GET(与 upload 类似,不经 developerProxy)。
  • 详见 `references/api.md`

Feedback: skillNamelinkfox-amazon-store-feeds

--- 更多跨境 skill:[LinkFox Skills](https://skill.linkfox.com/)

<!-- 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/cancel_feed.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: cancel_feed.py, check_auth_dependency.py, create_feed.py, create_feed_document.py, get_feed.py, get_feed_document.py, get_feeds.py, upload_feed_document.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. <!-- /LF_LARGE_RESPONSE_BLOCK -->

Related skills

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.