From business-intelligence-skills
Analyzes video content using Volcengine Ark Video Understanding API (doubao-seed models). Uploads videos via Files API (up to 512MB) for scene recognition, object detection, action understanding, and video Q&A.
How this skill is triggered — by the user, by Claude, or both
Slash command
/business-intelligence-skills:canghe-volcengine-video-understandingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
使用字节跳动火山方舟视频理解 API(doubao-seed-2-0-pro-260215 等模型)对视频进行深度理解和分析。
使用字节跳动火山方舟视频理解 API(doubao-seed-2-0-pro-260215 等模型)对视频进行深度理解和分析。
推荐方式:Files API 上传 + Responses API 分析
需要设置 ARK_API_KEY 环境变量。
cp .canghe-skills/.env.example .canghe-skills/.env
.canghe-skills/.env 文件,填写你的 API Key:ARK_API_KEY=your-actual-api-key-here
export ARK_API_KEY="your-api-key"
process.env).canghe-skills/.env~/.canghe-skills/.envcd ~/.openclaw/workspace/skills/volcengine-video-understanding
python3 scripts/video_understand.py /path/to/video.mp4 "描述这个视频的内容"
python3 scripts/video_understand.py /path/to/video.mp4 "视频中出现了哪些人物?"
python3 scripts/video_understand.py /path/to/video.mp4 "分析视频中人物的情感变化"
python3 scripts/video_understand.py /path/to/video.mp4 "总结视频要点" \
--model doubao-seed-2-0-pro-260215 \
--fps 2
python3 scripts/video_understand.py /path/to/video.mp4 "描述视频" --output result.json
| 参数 | 默认值 | 说明 |
|---|---|---|
video_path | 必填 | 视频文件路径 |
instruction | 必填 | 分析指令/问题 |
--model | doubao-seed-2-0-pro-260215 | 模型 ID |
--fps | 1 | 视频采样帧率(预处理) |
--output | - | 结果输出文件路径 |
doubao-seed-2-0-pro-260215 (默认)doubao-seed-2-0-lite-250728doubao-seed-1-6-251015python3 scripts/video_understand.py ~/Desktop/video.mp4 "详细描述这个视频的内容,包括场景、人物和动作"
python3 scripts/video_understand.py ~/Desktop/video.mp4 "用3句话总结这个视频的要点"
python3 scripts/video_understand.py ~/Desktop/video.mp4 "视频中的人物在做什么动作?按时间顺序描述"
python3 scripts/video_understand.py ~/Desktop/video.mp4 "分析视频中的场景变化和环境特征"
Files API 上传:
curl https://ark.cn-beijing.volces.com/api/v3/files \
-H "Authorization: Bearer $ARK_API_KEY" \
-F 'purpose=user_data' \
-F '[email protected]' \
-F 'preprocess_configs[video][fps]=1'
Responses API 分析:
{
"model": "doubao-seed-2-0-pro-260215",
"input": [
{
"role": "user",
"content": [
{
"type": "input_video",
"file_id": "file-xxxx"
},
{
"type": "input_text",
"text": "用户指令"
}
]
}
]
}
| FPS | 适用场景 |
|---|---|
| 0.3-0.5 | 慢节奏视频、静态场景、节省token |
| 1 | 一般视频分析(默认) |
| 2-3 | 快速动作、细节分析 |
from scripts.video_understand import analyze_video
result = analyze_video(
file_path="/path/to/video.mp4",
instruction="描述视频内容",
model="doubao-seed-2-0-pro-260215",
fps=1
)
# 提取回答
text = ""
for item in result.get("output", []):
if item.get("type") == "message":
for content in item.get("content", []):
if content.get("type") == "output_text":
text = content.get("text", "")
break
print(text)
常见错误及解决方案:
| 错误 | 原因 | 解决方案 |
|---|---|---|
| API Key 错误 | 未设置或错误 | 检查 ARK_API_KEY 环境变量 |
| 文件不存在 | 路径错误 | 检查文件路径 |
| 上传失败 | 文件过大或格式不支持 | 检查文件大小(<512MB)和格式 |
| 处理超时 | 视频过长或复杂 | 缩短视频或降低 FPS |
npx claudepluginhub freestylefly/canghe-skills --plugin content-skillsAnalyzes video files or YouTube URLs: extracts frames/audio, detects scenes/motion/silence/transitions via ffmpeg tools with structured workflow.
Analyzes a video into a structured index: scene detection, ASR transcript, per-scene VLM analysis, silence windows, fused timeline, and narration brief. Use to understand, index, or summarize video content.
Analyzes a video synchronously using TwelveLabs AI to return a summary or answer questions about its content. Accepts video URLs, file paths, asset IDs, or indexed video IDs.