← 返回 Skills 市场
linkfox-ai

TikTok Creator

作者 linkfox-ai · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
29
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install linkfox-tiktok-creator
功能描述
TikTok 达人(Creator/affiliate creator)数据与可购物视频技能,经 LinkFox 网关代理调用 TikTok Shop 达人开放接口:达人主页/档案、达人绑定店铺商品、橱窗商品、可购物视频的上传/内容预检/发布/发布状态查询。需要达人 access_token(user_type=...
使用说明 (SKILL.md)

TikTok 达人(Creator)数据

本 skill 通过 LinkFox 网关 → 紫鸟代理 → TikTok Shop 达人(affiliate_creator)开放接口,提供 TikTok 带货达人的数据查询(达人资料、绑定店铺商品、橱窗商品)与可购物视频带货操作(上传、内容预检、发布、状态查询)。全部接口收录在 references/api.md

📌 前置依赖:本 skill 需要 达人 access_token(user_type=1。请先用 linkfox-tiktok-authappType=creator 完成达人授权并取得 accessToken,再作为本 skill 调用的 ttsAccessToken 传入。

Core Concepts

  • 调用链路:业务请求统一经 LinkFox 网关的 /tiktokShop/developerProxy 转发:传入 appType=creator、TikTok Shop API 的相对 path(如 affiliate_creator/202508/profiles)、method 与达人令牌 ttsAccessToken;紫鸟自动注入 app_key / timestamp / sign,并透传 TikTok 原始响应。达人接口的 appType 必须为 creator(脚本已默认)。
  • 达人令牌ttsAccessToken 为达人 access_token(user_type=1),来自 linkfox-tiktok-authappType=creator)。令牌过期时回到该 skill 刷新。
  • 响应透传:网关返回 httpStatus / contentType / body,其中 body 为 TikTok 原始 JSON 字符串;TikTok 业务层的成功/失败以其 code / message 为准。

API Usage

本 skill 经 LinkFox 网关代理调用,详见 references/api.md

Available Scripts

  • scripts/creator_proxy.py — 通用达人接口代理:按 path + method + ttsAccessToken 调用任意已收录的达人接口。

已收录接口

能力 上游 path Method
获取达人主页/档案(Get Creator Profile) affiliate_creator/202508/profiles GET
搜索达人绑定店铺的商品(Get Shop Products) affiliate_creator/202509/shop_products GET
达人橱窗商品列表(Get Showcase Products) affiliate_creator/202405/showcases/products GET
上传可购物视频文件(Upload Shoppable Video File,multipart) affiliate_creator/202505/videos/video_files POST
发布可购物视频(Post Shoppable Video) affiliate_creator/202603/videos POST
查询可购物视频发布状态(Get Shoppable Video Status) affiliate_creator/202509/videos/{video_id}/status GET
可购物视频内容预检(Pre-check Shoppable Video) affiliate_creator/202511/videos/precheck_task POST
查询视频预检结果(Get Shoppable Video Pre-check Result) affiliate_creator/202511/videos/precheck_tasks/{task_id} GET

⚠️ 含 multipart/form-data 二进制上传的接口(Upload Shoppable Video File)不走通用 creator_proxy.py,需 multipart 链路,详见 references/api.md

典型编排流程

A. 选品 / 查达人数据

  1. 达人资料:Get Creator Profile(接口 1)
  2. 商品:Get Shop Products(接口 2,按关键词搜店铺商品)或 Get Showcase Products(接口 3,达人橱窗/直播袋)→ 拿到 product_id

B. 可购物视频带货(发布全链路)

  1. 上传视频:Upload Shoppable Video File(接口 4)→ 拿 file_id(⚠️ multipart,见限制)
  2. 内容预检:Pre-check Shoppable Video(接口 7,传 file_id + product_id)→ 拿 task_id
  3. 查预检结果:Get Shoppable Video Pre-check Result(接口 8,凭 task_id)→ result=SUCCESS 才继续;FAILissues[] 整改
  4. 发布:Post Shoppable Video(接口 5,传 file_id + product_id + 标题/封面)→ 拿 video.id
  5. 查发布状态:Get Shoppable Video Status(接口 6,凭 video_id)→ post_statusSUCCESS/FAIL/PROCESSING

所有调用都需先经 linkfox-tiktok-authappType=creator)拿到达人 accessToken 作为 ttsAccessToken

Display Rules

  1. 只呈现数据:展示达人资料字段即可,不做主观评价。
  2. 令牌安全:不要明文输出完整 ttsAccessToken,仅展示掩码。
  3. 错误说明:失败时依据 TikTok 业务 code / message 与网关 httpStatus 解释原因。
  4. 前置校验:无达人令牌时,先引导用户经 linkfox-tiktok-authappType=creator)授权。

Important Limitations

  • 达人令牌必备:所有接口都需 user_type=1 的达人 access_token;店铺(erp)令牌不适用。
  • 达人权限:达人须具备相应电商(EC)/选品区域权限,否则返回 16015006 / 16015007 / 16504002 等。
  • 限流:短时间内请求过多会触发 36009002,请退避重试。

User Expression & Scenario Quick Reference

Applicable

User Says Scenario
"查一下这个 TikTok 达人的资料" / "Get TikTok creator profile" 获取达人主页/档案
"搜一下达人店铺里的商品" / "Get shop products of the creator" 搜索达人绑定店铺的商品
"看看达人橱窗里有哪些商品" / "Get creator showcase products" 达人橱窗商品列表
"上传一个可购物视频" / "Upload shoppable video" 上传可购物视频文件
"发布可购物视频 / 把视频和商品绑定发出去" / "Post shoppable video" 发布可购物视频
"视频发布成功了吗 / 查下视频发布状态" / "Get shoppable video status" 查询可购物视频发布状态
"发布前先检测下视频有没有违规" / "Pre-check shoppable video" 可购物视频内容预检
"预检结果出来了吗 / 视频违规检测结果" / "Get video pre-check result" 查询视频预检结果
"看看达人的带货信息" 达人数据查询(按已收录接口)

Not applicable

  • TikTok 达人授权本身 → 用 linkfox-tiktok-authappType=creator)。
  • TikTok 选品 / 商品销量(EchoTik 等数据源)→ 由对应 skill 负责。

Feedback

当出现以下任一情况时,自动通过 Feedback API 上报反馈:

  1. 本 skill 描述的功能与实际行为不符
  2. skill 的结果与用户意图不符
  3. 用户表达了对本 skill 的不满或赞赏
  4. 任何你认为可以改进的点

references/api.md 中的规范调用 Feedback API,不要打断用户的主流程。

\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/creator_proxy.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.

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, visit LinkFox Skills.

安全使用建议
Install only if you are comfortable giving this skill a LinkFox API key and TikTok creator access token. Before using it, confirm every publish or precheck request manually, avoid putting secrets in prompts or feedback, keep persisted response files outside repos, and delete those files after use.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The stated purpose fits TikTok creator profile, product, precheck, status, and shoppable-video workflows, but the helper accepts arbitrary path/method values through the LinkFox developer proxy and includes live publishing actions against a creator account.
Instruction Scope
The skill discloses token use and tells agents not to print full ttsAccessToken values, but it does not require explicit per-action confirmation before publishing or precheck actions and instructs automatic feedback reporting to a separate endpoint.
Install Mechanism
The package contains markdown references and Python helper scripts only; metadata/static scan show no install-time hooks, dependency installs, or persistence mechanisms beyond included files.
Credentials
Network access, LINKFOXAGENT_API_KEY, creator access tokens, and local response persistence are coherent with the integration, but they are high-impact for a creator account and not tightly scoped by the scripts.
Persistence & Privilege
response_io.py writes full captured API responses to user-selected disk locations for large-response handling; SKILL.md warns that persisted files may contain PII, pricing, or auth-sensitive data and are not auto-deleted.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install linkfox-tiktok-creator
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /linkfox-tiktok-creator 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release
元数据
Slug linkfox-tiktok-creator
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

TikTok Creator 是什么?

TikTok 达人(Creator/affiliate creator)数据与可购物视频技能,经 LinkFox 网关代理调用 TikTok Shop 达人开放接口:达人主页/档案、达人绑定店铺商品、橱窗商品、可购物视频的上传/内容预检/发布/发布状态查询。需要达人 access_token(user_type=... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 29 次。

如何安装 TikTok Creator?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install linkfox-tiktok-creator」即可一键安装,无需额外配置。

TikTok Creator 是免费的吗?

是的,TikTok Creator 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

TikTok Creator 支持哪些平台?

TikTok Creator 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 TikTok Creator?

由 linkfox-ai(@linkfox-ai)开发并维护,当前版本 v1.0.0。

💬 留言讨论