douyin-search-keyword
抖音公开内容智能搜索,精准检索视频/图文/用户数据,支持多维度排序与时间筛选,输出结构化JSON/Markdown,助力短视频营销、竞品分析与热点追踪。
Best use case
douyin-search-keyword is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
抖音公开内容智能搜索,精准检索视频/图文/用户数据,支持多维度排序与时间筛选,输出结构化JSON/Markdown,助力短视频营销、竞品分析与热点追踪。
Teams using douyin-search-keyword should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/douyin-search-keyword/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How douyin-search-keyword Compares
| Feature / Agent | douyin-search-keyword | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
抖音公开内容智能搜索,精准检索视频/图文/用户数据,支持多维度排序与时间筛选,输出结构化JSON/Markdown,助力短视频营销、竞品分析与热点追踪。
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# 抖音搜索关键词技能 (Douyin Search Keyword)
## 1. 技能概述
### 1.1 核心定位
抖音公开内容智能搜索,精准检索视频/图文/用户数据,支持多维度排序与时间筛选,输出结构化JSON/Markdown,**助力短视频营销、竞品分析与热点追踪**。
### 1.2 核心能力
- 🔍 **抖音热门搜索**:精准检索视频/图文/用户数据
- 🎯 **多维度排序**:按点赞数、最新发布智能排序
- 📅 **时间筛选**:支持1天/7天/半年内数据精准筛选
- 📊 **互动数据**:提取点赞、评论、收藏、分享等核心指标
- 🛠️ **智能纠错**:自动清洗关键词,提升检索准确率
- 📦 **多格式输出**:JSON(程序处理)/Markdown(人工阅读)双格式
### 1.3 适用场景
| 场景 | 用户痛点 | 技能如何解决 |
| :------------: | :------------------: | :--------------------------------------: |
| **短视频营销** | 缺乏爆款视频创意灵感 | 一键获取“抖音热门”视频数据,分析热门趋势 |
| **竞品分析** | 难以追踪竞品内容策略 | 精准搜索竞品账号视频,分析互动数据 |
| **热点追踪** | 错过热点话题黄金期 | 实时搜索“抖音热门”话题,掌握最新动态 |
- 链接提取:直接获取视频下载地址和图文原始链接
### 1.4 技能特性
- **实时搜索**:获取最新的抖音公开内容
- **参数灵活**:支持排序、时间、数量、格式自定义
- **安全可靠**:仅采集公开数据,符合数据采集合规要求
- **易于集成**:支持 OpenClaw 环境和直接命令行调用
- **多维度数据**:返回视频、图文等多种类型内容
- **详细信息**:包含标题、发布人、互动数据等完整信息
### 1.5 技术原理
该技能通过调用抖音搜索API,实现关键词搜索功能。具体流程如下:
1. 接收用户输入的搜索关键词
2. 清洗关键词,移除特殊符号
3. 验证关键词格式
4. 调用API创建搜索任务
5. 轮询获取搜索结果
6. 格式化输出结果
7. 保存结果到本地文件
## 2. 快速调用指南
### 2.1 前置条件
- 安装Node.js 16+环境
- 配置环境变量 `GUAIKEI_API_TOKEN`(默认TOKEN仅用于体验,私有TOKEN需申请)
### 2.2 基础语法
```bash
# 语法:node scripts/search.js [关键词] [选项]
```
### 2.3 选项说明
| 选项 | 类型 | 可选值 | 默认值 | 说明 |
| --------- | ------ | -------------------- | ------ | ------------------------------------------------------- |
| --keyword | string | 2-50字符(无特殊符号) | 无 | 搜索关键词(必传) |
| --sort | number | 0/1/2 | 0 | 排序方式(0 - 综合 / 1 - 最多点赞 / 2 - 最新) |
| --time | number | 0/1/7/180 | 0 | 发布时间范围(0 - 全部 / 1-1 天 / 7-7 天 / 180 - 半年) |
| --limit | number | 10-60 | 10 | 返回结果数量 |
| --output | string | json/markdown | json | 输出格式 |
| --help/-h | - | - | - | 显示帮助信息 |
### 2.4 典型示例
```bash
# 示例1:基础搜索(JSON格式)
node scripts/search.js AI
# 示例2:带空格的关键词
node scripts/search.js "AI 教程"
# 示例3:自定义排序(最多点赞)
node scripts/search.js AI --sort 1
# 示例4:自定义发布时间(半年)
node scripts/search.js "AI 模型" --time 180
# 示例5:自定义返回结果数量(20条)
node scripts/search.js AI --limit 20
# 示例6:自定义输出格式(Markdown)
node scripts/search.js "AI 教程" --output markdown
# 示例7:复杂搜索(最新+近半年+20条结果+JSON格式)
node scripts/search.js --keyword "AI 教程" --sort 2 --time 180 --limit 20
```
## 3. 输出数据规范
### 3.1 JSON格式(默认)
```json
{
"status": "success",
"keyword": "AI 教程",
"message": "搜索任务完成",
"sort": 0,
"time": 0,
"limit": 20,
"output_format": "json",
"total": 18,
"timestamp": "2026/3/29 09:05:51",
"results": [
{
"aweme_id": "7622261059679800627",
"desc": "#刘慈欣称AI不可能完全代替人类作者 科幻作家谈#AI快速发展对科幻产业影响几何",
"create_time": 1774695958,
"author_uid": "98524606968",
"author_nickname": "央视财经",
"author_avatar": "https://...",
"author_sec_uid": "MS4wLjABAAAAt6AsGhjrHeoxZNkceYg2J0FWvrWKzEaTAvF44-sPYco",
"comment_count": 4,
"digg_count": 356,
"share_count": 6,
"collect_count": 17,
"share_url": "https://www.iesdouyin.com/share/video/...",
"dynamic_cover": ["https://...", "https://..."],
"play_addr": "https://...",
"play_uri": "v0200fg10000d73r95fog65tmhj30190",
"music_id": "7622261065841150756",
"music_title": "@央视财经创作的原声",
"music_author": "央视财经",
"tags": [
"刘慈欣称AI不可能完全代替人类作者",
"AI快速发展对科幻产业影响几何"
],
"url": "https://www.douyin.com/video/xxx",
"author_url": "https://www.douyin.com/user/xxx",
"create_time_str": "2026/3/28 19:05:58"
}
]
}
```
### 3.2 Markdown格式(人工阅读)
以结构化列表形式展示搜索结果,非常**适合内容创作者快速浏览和整理灵感素材**。
```markdown
## **抖音综合搜索结果**: AI 教程
**1 .** 刘慈欣称AI不可能完全代替人类作者 科幻作家谈#AI快速发展对科幻产业影响几何
**发布人**: 央视财经
**发布时间**: 2026/3/28 19:05:58
**链接**: https://www.douyin.com/video/xxx
**封面**: https://...
**视频**: https://...
**点赞**: 364 **评论**: 4 **收藏**: 18 **分享**: 7
---
**共 20 条结果**
```
## 4. 注意事项
## 4.1 合规要求
- 仅用于抖音公开数据采集,禁止爬取私密 / 违规内容
- 符合 OpenClaw 安全规范与数据采集合规要求
### 4.2 风控提示
- 默认 TOKEN 有调用频率限制,生产环境建议使用私有 TOKEN
- CDN 链接(视频 / 图片)为临时链接,建议及时下载留存
- 关键词包含违规内容时,技能会直接拦截并提示Related Skills
zaker-news-search
基于ZAKER权威资讯库进行关键词新闻检索,支持指定时间范围(30天内)。Use when the user asks about 搜索新闻, 某事件新闻, 某人物新闻, 某关键词相关新闻, 查新闻, 新闻检索, 相关新闻, 某时间段新闻.
github-repo-search
帮助用户搜索和筛选 GitHub 开源项目,输出结构化推荐报告。当用户说"帮我找开源项目"、"搜一下GitHub上有什么"、"找找XX方向的仓库"、"开源项目推荐"、"github搜索"、"/github-search"时触发。
xiaohongshu-search
小红书运营全链路数据工具|关键词监控+爆款挖掘+竞品分析+KOL筛选+趋势洞察,用数据驱动小红书流量增长,告别盲目创作
codebase-search
Search and navigate large codebases efficiently. Use when finding specific code patterns, tracing function calls, understanding code structure, or locating bugs. Handles semantic search, grep patterns, AST analysis.
skywork-search
Search the web for real-time information using the Skywork web search API. Use this skill whenever the user needs up-to-date information from the internet — for example, researching a topic, looking up recent events, finding facts or statistics, gathering material for a document or presentation, or answering questions that require current data. Also trigger when the user says things like "search for", "look up", "find information about", "what's the latest on", or any request that implies needing information beyond your training data.
wiki-researcher
Conducts multi-turn iterative deep research on specific topics within a codebase with zero tolerance for shallow analysis. Use when the user wants an in-depth investigation, needs to understand how something works across multiple files, or asks for comprehensive analysis of a specific system or pattern.
seo-keyword-strategist
Analyzes keyword usage in provided content, calculates density, suggests semantic variations and LSI keywords based on the topic. Prevents over-optimization. Use PROACTIVELY for content optimization.
search-specialist
Expert web researcher using advanced search techniques and synthesis. Masters search operators, result filtering, and multi-source verification. Handles competitive analysis and fact-checking. Use PROACTIVELY for deep research, information gathering, or trend analysis.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
hybrid-search-implementation
Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.
hig-components-search
Apple HIG guidance for navigation-related components including search fields, page controls, and path controls. Use this skill when the user says "how should search work in my app," "I need a breadcrumb," "how do I paginate content," or asks about search field, search bar, page control, path control, breadcrumb, navigation component, search UX, search suggestions, search scopes, paginated content navigation, or file path hierarchy display. Cross-references: hig-components-menus, hig-components-controls, hig-components-dialogs, hig-patterns.
exa-search
Semantic search, similar content discovery, and structured research using Exa API