douyin-video-analyst
抖音账号视频批量采集与文案分析工作流。当用户提供抖音账号主页链接、要求抓取最新 N 条视频链接、提取视频文案(语音转文字)、或对视频内容进行总结归纳时,激活此 skill。依赖 browser 工具(抓取视频列表)和 mcporter + douyin-mcp(文案提取)。
Best use case
douyin-video-analyst is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
抖音账号视频批量采集与文案分析工作流。当用户提供抖音账号主页链接、要求抓取最新 N 条视频链接、提取视频文案(语音转文字)、或对视频内容进行总结归纳时,激活此 skill。依赖 browser 工具(抓取视频列表)和 mcporter + douyin-mcp(文案提取)。
Teams using douyin-video-analyst 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-video-analyst/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How douyin-video-analyst Compares
| Feature / Agent | douyin-video-analyst | 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?
抖音账号视频批量采集与文案分析工作流。当用户提供抖音账号主页链接、要求抓取最新 N 条视频链接、提取视频文案(语音转文字)、或对视频内容进行总结归纳时,激活此 skill。依赖 browser 工具(抓取视频列表)和 mcporter + douyin-mcp(文案提取)。
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
# Douyin Video Analyst
从抖音账号主页批量采集最新视频链接,通过 douyin-mcp 提取视频语音文案,去除口语化后输出精简原始文案,并进行综合总结。
## 前置依赖
- **browser 工具**:用于渲染抖音 SPA 页面并抓取视频列表(web_fetch 无效,抖音为纯 JS 渲染)
- **mcporter CLI**:`which mcporter` 确认可用
- **douyin-mcp server**:在 `mcporter list` 中应显示 `douyin-mcp (5 tools)`
> mcporter 会自动加载 `~/.cursor/mcp.json` 和 `~/.claude.json` 两个配置文件中的 MCP server。
## 版本与 Key 对照
| 版本 | API 平台 | 环境变量 |
|------|----------|----------|
| ≤ 1.1.0 | 硅基流动 | `DOUYIN_API_KEY` |
| ≥ 1.2.0 | 阿里云百炼 | `DASHSCOPE_API_KEY` |
两个版本均受支持,根据实际配置选择对应环境变量。配置指南见 `references/setup.md`。
## 工作流步骤
### Step 1:检查配置
```bash
# 确认 mcporter 和 douyin-mcp 可用
mcporter list 2>&1 | grep douyin-mcp
```
读取配置文件判断版本和 Key:
```bash
python3 << 'EOF'
import json, os
# mcporter 同时加载这两个配置
for path in ['~/.cursor/mcp.json', '~/.claude.json']:
p = os.path.expanduser(path)
if not os.path.exists(p): continue
d = json.load(open(p))
cfg = d.get('mcpServers', {}).get('douyin-mcp')
if cfg:
print(f"Found in {path}")
print(' args:', cfg.get('args'))
print(' env keys:', list(cfg.get('env', {}).keys()))
break
EOF
```
- env 含 `DOUYIN_API_KEY` → v1.1.0,硅基流动
- env 含 `DASHSCOPE_API_KEY` → v1.2.0+,阿里云百炼
若未配置,参考 `references/setup.md` 完成初始化。
### Step 2:用 browser 抓取视频列表
抖音是纯 JS SPA,**必须用 browser 工具**,不可用 web_fetch。
```
browser(action="open", profile="openclaw", targetUrl="<账号主页URL>")
browser(action="screenshot", ...) # 等页面渲染,确认视频列表出现
browser(action="snapshot", ...) # 提取 listitem 中的 /video/XXXX 链接
```
从 snapshot 的 aria tree 中提取 `link[href=/video/XXXXXXXXXXXXXXXXX]`,取前 N 条,拼接完整链接:`https://www.douyin.com/video/<video_id>`
### Step 3:并发提取视频文案
根据 Step 1 检测到的版本,选择对应的环境变量名,**并发**调用所有视频(不要串行等待):
```bash
# v1.1.0(硅基流动)
DOUYIN_API_KEY="<key>" mcporter call douyin-mcp.extract_douyin_text \
share_link="https://www.douyin.com/video/<video_id>" 2>&1
# v1.2.0+(阿里云百炼)
DASHSCOPE_API_KEY="<key>" mcporter call douyin-mcp.extract_douyin_text \
share_link="https://www.douyin.com/video/<video_id>" 2>&1
```
同时发起所有 exec 调用(放在同一个工具调用块中),设置 `timeout=180`,`yieldMs=120000`。
若出现错误,参考 `references/troubleshooting.md`。
### Step 4:整理与输出
按视频顺序(从新到旧)输出,每条视频包含:
1. **视频标题**(来自 snapshot 的 link 文本)
2. **视频链接**
3. **精简文案**:对原始语音文案去除口语化表达(去掉语气词、重复啰嗦、"大家"/"我们"/"你们"等口语填充词),保留核心信息和论点,以书面化段落呈现,不做摘要压缩,完整保留所有要点
最后附综合总结:跨视频归纳主线逻辑、核心主题、一致的风险提示。
## 输出格式参考
```
## 📊 [账号名] 最近 N 条视频文案整理
---
### 视频1 | <标题>
🔗 <链接>
<精简后的书面化文案,完整保留所有要点,去除口语填充>
---
### 视频2 | <标题>
...
---
## 🗂️ 综合总结
| 主线 | 核心逻辑 | 重点方向 |
|------|----------|----------|
| ... | ... | ... |
```
## 注意事项
- 抖音登录弹窗出现时:直接读取 snapshot,视频列表通常仍可在 aria tree 中获取
- 第一条视频可能需要登录才能访问,从第二条起往往正常
- extract_douyin_text 耗时较长(30~90s/条),务必并发执行
- 若文案提取失败,可先用 `parse_douyin_video_info` 获取下载链接,再手动处理Related Skills
videocut:自进化
字幕生成与烧录。火山引擎转录→词典纠错→审核→烧录。触发词:加字幕、生成字幕、字幕
video-transcriber
视频转写工作流,支持B站和YouTube视频。自动判断有字幕/无字幕,有字幕则获取字幕,无字幕则下载音频+whisper转写。触发场景:(1) 用户要求总结视频内容 (2) 用户要求获取视频字幕 (3) 用户要求转写视频 (4) 处理B站/YouTube视频
video-subtitles
Generate SRT subtitles from video/audio with translation support. Transcribes Hebrew (ivrit.ai) and English (whisper), translates between languages, burns subtitles into video. Use for creating captions, transcripts, or hardcoded subtitles for WhatsApp/social media.
video-script
Create video scripts and publishing materials for YouTubers/UP主. Use when user wants to prepare a video, write a script (口播稿), generate video title, description, tags, or chapter timestamps. Triggers on "写视频脚本", "视频口播稿", "video script", "prepare video", "视频发布素材", or mentions creating content for YouTube/Bilibili.
video-merge-send
合并多个分段视频为一个完整视频,并发送到飞书。使用ffmpeg拼接视频片段,支持淡入淡出转场。触发场景:用户需要合并视频片段、拼接分镜视频、视频合并后发飞书、把多个短视频合成一个、分段视频合并发送。配合 jimeng-storyboard skill 使用,完成数字人视频全流程。
video-marketing
When the user wants to plan video marketing, create video scripts, or optimize for short-form or long-form video. Also use when the user mentions "video marketing," "video script," "short-form video," "long-form video," "TikTok script," "Reels script," "YouTube script," "video hook," or "video content strategy."
video-lyrics-subtitle
Video lyrics subtitle generator — create synchronized subtitle files for music videos
video-generation
Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference image for guided generation.
video-content-analyzer
下载视频并用AI分析内容 - 支持B站/抖音/YouTube等平台,提取语音内容并分析视频结构
video-caption-burner
Burn existing subtitles or captions directly into video exports so they remain visible across platforms and players. Use when a team already has captions and needs a platform-ready, subtitle-baked video for social, ads, storefronts, or review links.
startup-business-analyst-financial-projections
Create detailed 3-5 year financial models with revenue, costs, cash flow, and scenario analysis for startup planning and fundraising.
startup-business-analyst-business-case
Generate a comprehensive, investor-ready business case document covering market opportunity, solution, competitive landscape, financial projections, t Generate comprehensive investor-ready business case document with market, solution, financials, and strategy