AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Tiktok Category Strategy

skill-aronhy-tiktok-agent-skills-tiktok-category-strategy · by aronhy

Use when a user wants to evaluate, enter, position, or operate a TikTok or TikTok Shop category and needs market, product, shop, content, creator, competition, or category strategy.

No reviews yet
0 installs
19 views
0.0% view→install

Install

$ agentstack add skill-aronhy-tiktok-agent-skills-tiktok-category-strategy

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-aronhy-tiktok-agent-skills-tiktok-category-strategy)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Tiktok Category Strategy? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

TikTok 类目策略

基于可追溯的商品、店铺、视频、达人和官方趋势证据,判断一个 TikTok/TikTok Shop 类目的进入条件,并形成运营策略;不把缺失数据、单个爆款或行业传闻写成市场事实。

先加载参考

在调用工具或下结论前,必须完整读取:

  1. [references/workflow.md](references/workflow.md)
  2. [references/report-template.md](references/report-template.md)

需要选择 KSS MCP 工具、参数、返回字段或关联方式时,再读取共享的 [../tiktok-shop-operator/references/mcp-tools.md](../tiktok-shop-operator/references/mcp-tools.md)。实际连接的 MCP schema 始终优先于该参考。

控制流程

  1. 确认目标类目和目标国家或地区。两者都是初始必需输入。首次发现任一项缺失时,只问一个最高优先级问题并停止:若类目缺失,只问“目标类目是什么?它决定研究对象、商品映射和内容比较范围。”;否则只问“目标国家或地区是什么?它会改变趋势、价格、政策和竞争格局。”同一回复不得附带框架、策略、go/no-go、市场主张或报告,即使用户在该次请求中要求继续。
  2. 只有在完成上述提问后,用户后续明确表示无法或不愿提供该输入、并再次要求继续时,才可按报告参考输出“通用/条件性部分框架”。不得调用依赖缺失维度的实时研究工具或页面,不得给出市场特定事实、go/no-go、价格、政策或竞争主张;必须列出缺失输入及影响、分开标示假设、给出 C 级低可信度,并说明仍被阻断的研究与结论。
  3. 记录可选条件:价格带、账号类型、商业目标、预算、内容语言和计划周期。不要把未给出的条件补成行业基准、固定内容数量、视频时长、达人层级或效果阈值。
  4. 两个必需输入齐全时,按工作流规范化类目和市场,用 product_search 建立候选商品池,再以 shop_searchvideo_searchcreator_search 和代表视频的 caption_extract 补齐相互关联的证据。保留对象 ID、地区、币种、统计窗口、分页范围和停止原因。
  5. 以 TikTok Creative Center 的同地区、同类目公开趋势作为当前官方补充;它不可访问、需登录、受地区限制或字段不足时明确记录,不能用搜索摘要、记忆或其他网页冒充其数据。
  6. 仅在目标类目和目标市场均已提供后,才完成允许的重试、分页、ID 关联和公开浏览器读取,再检查证据完整性。此后的关键取证缺失会改变进入结论、切入方向或合规判断时,只问一个问题;用户要求继续时可提供带影响范围和 A/B/C 可信度的部分报告。
  7. 只有跨来源且口径可比的证据才能支持进入、竞争、需求、内容或达人结论。结果前置:先按报告模板给“是否建议进入”和三个优先动作,后给证据、明细、限制和风险;把观察、推断、假设和待验证项分开写。

输出边界

  • 两个必需输入齐全时使用固定的十二节报告模板;标明目标市场、收集时间、筛选条件、样本/页数、来源、完整性、默认值、缺失字段和可信度。输入缺失的后续拒绝例外只能使用报告参考中的受限部分框架,不能伪装成正式报告。
  • 不混淆播放量、销量、销售额、商品价格、视频发布时间和统计窗口;不跨地区、币种或不兼容周期合并排名。
  • 不编造 KSS 字段、Creative Center 趋势、政策要求、链接、成功调用、配额状态或量化行业基准。没有返回的字段写“未提供”;浏览器无法读取写“读取失败”或“未公开”。
  • 不绕过登录、验证码、反爬、地域限制或访问控制;不保存或回显 API Key、Token、Cookie 或其他凭证;不发布、投放、下单、改店或联系达人。

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.