← Back to Skills Marketplace
ahsbnb

Douyin Video Search

by an · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
175
Downloads
1
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install douyin-video-search
Description
(已验证) 通过 TikHub API 搜索抖音视频,支持关键词、分页、多维度排序和筛选。
README (SKILL.md)

SKILL.md for douyin-video-search

Description

一个功能强大的抖音视频搜索技能,它通过调用 TikHub 官方 API 来获取搜索结果。该技能支持通过关键词进行搜索,并提供了丰富的参数选项,包括分页、多种排序方式(综合、最多点赞、最新发布)以及发布时间和视频时长的筛选。

这是一个核心的、原子化的搜索工具,可以被其他上层技能(如 visual-benchmark-finder)调用,以实现更复杂的业务逻辑。

Configuration

本技能需要一个有效的 TikHub API Token 才能工作。请在您的 ~/.openclaw/config.json 文件中添加以下配置项。该 Token 可与 douyin-downloader 等其他 TikHub 系技能共用。

{
  "tikhub_api_token": "YOUR_TIKHUB_API_TOKEN"
}

您可以在 TikHub 官网 注册免费获取 Token。

How to Use

该技能的核心脚本 (scripts/douyin_search.py) 是一个功能完善的命令行工具,可以直接调用,也可以被其他技能通过 exec 工具调用。

Parameters

  • keyword (必填): 搜索的关键词。
  • --cursor: 分页游标,第一页默认为 0
  • --sort: 排序方式。
    • 0: 综合 (默认)
    • 1: 最多点赞
    • 2: 最新发布
  • --publish: 发布时间。
    • 0: 不限 (默认)
    • 1: 最近一天
    • 7: 最近一周
    • 180: 最近半年
  • --duration: 视频时长。
    • 0: 不限 (默认)
    • 0-1: 1分钟内
    • 1-5: 1-5分钟
    • 5-10000: 5分钟以上
  • --raw: 如果提供此参数,将输出原始的 JSON 数据而不是格式化后的文本。

Example Invocation

简单搜索:

& "F:\python 3.10\python.exe" "C:\Users\EDY\.openclaw\skills\douyin-video-search\scripts\douyin_search.py" "美食"

带参数的高级搜索:

& "F:\python 3.10\python.exe" "C:\Users\EDY\.openclaw\skills\douyin-video-search\scripts\douyin_search.py" "旅行" --sort "2" --publish "7"
Usage Guidance
The skill's behavior (call TikHub search API, require a TikHub token) matches its description, but the registry metadata and provenance are weak: the SKILL.md instructs you to store a tikhub_api_token in ~/.openclaw/config.json or set TIKHUB_API_TOKEN, yet the registry lists no required env or config path and the source URL is a placeholder. Before installing: 1) Verify the skill's origin (trusted repo or author) and request a real homepage/source; 2) Prefer setting TIKHUB_API_TOKEN as an environment variable with restricted permissions rather than leaving tokens in a shared config file; 3) Inspect the included script yourself (you have it) and ensure config file permissions are restrictive; 4) Be aware that the script prints debug response text which may end up in logs — avoid running it with sensitive tokens in shared/logged environments. If these provenance and metadata issues can't be resolved, treat the package as untrusted.
Capability Analysis
Type: OpenClaw Skill Name: douyin-video-search Version: 1.0.0 The skill is a legitimate tool for searching Douyin videos via the TikHub API. It follows standard practices by retrieving an API token from a local configuration file (~/.openclaw/config.json) or environment variables, and its code logic in scripts/douyin_search.py is transparent, well-documented, and strictly limited to its stated purpose without any signs of malicious intent or data exfiltration.
Capability Assessment
Purpose & Capability
The code and SKILL.md match the declared purpose (search Douyin via TikHub API). However the registry metadata does not declare the required TikHub API token or the config path (~/.openclaw/config.json) even though the skill requires them; the published source link in SKILL.md is a placeholder. These provenance/metadata omissions are incoherent with how a production skill should declare secrets and origin.
Instruction Scope
Runtime instructions and the script are scoped to performing searches: they read a TikHub token from ~/.openclaw/config.json or TIKHUB_API_TOKEN, call the TikHub API endpoint, and format results. The instructions do not ask the agent to read unrelated system files or transmit data to unexpected endpoints.
Install Mechanism
There is no install spec (instruction-only plus a small Python script). The SKILL.md lists only Python and requests. No downloads or archive extraction are performed.
Credentials
The skill legitimately needs a TikHub API token (stored in ~/.openclaw/config.json or TIKHUB_API_TOKEN), but the skill registry metadata failed to list this requirement or any config path. Requiring a bearer token is proportionate for the described API integration, but the metadata omission reduces transparency and increases risk of accidental token exposure. The code prints debug output which could surface API responses in logs.
Persistence & Privilege
The skill is not always-enabled and does not request elevated persistence. It only reads its own config file and environment variables; it does not modify other skills or system-wide settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install douyin-video-search
  3. After installation, invoke the skill by name or use /douyin-video-search
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of douyin-video-search. - Search Douyin videos using TikHub API with support for keywords. - Multiple filtering and sorting options: by relevance, most liked, newest, publish time, and video duration. - Supports pagination with a cursor parameter. - Requires a TikHub API Token for authentication. - CLI script usage with detailed parameters documented. - Usable as an atomic tool or as a base for more complex skills.
Metadata
Slug douyin-video-search
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Douyin Video Search?

(已验证) 通过 TikHub API 搜索抖音视频,支持关键词、分页、多维度排序和筛选。 It is an AI Agent Skill for Claude Code / OpenClaw, with 175 downloads so far.

How do I install Douyin Video Search?

Run "/install douyin-video-search" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Douyin Video Search free?

Yes, Douyin Video Search is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Douyin Video Search support?

Douyin Video Search is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Douyin Video Search?

It is built and maintained by an (@ahsbnb); the current version is v1.0.0.

💬 Comments