Baidu Netdisk AIVideoNotes

v1.0.2

百度网盘AI视频笔记是一款基于大模型的视频内容理解工具,可以对视频(本地视频,网络视频)语音识别生成文稿笔记、大纲笔记、图文笔记三种笔记格式。当用户需要从视频生成笔记、总结视频内容、或将视频转化为文字记录时使用,经典场景(教育,会议视频总结笔记,短视频文案建议,关键信息提取)

0· 267·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for ide-rea/ai-notes-for-video.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Baidu Netdisk AIVideoNotes" (ide-rea/ai-notes-for-video) from ClawHub.
Skill page: https://clawhub.ai/ide-rea/ai-notes-for-video
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Required env vars: BAIDU_API_KEY
Required binaries: python3
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install ai-notes-for-video

ClawHub CLI

Package manager switcher

npx clawhub@latest install ai-notes-for-video
Security Scan
Capability signals
Requires sensitive credentials
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description describe generating notes from videos. The scripts implement creating a task, polling, and querying results against Baidu endpoints and include an upload helper for local files — all directly related to the stated purpose. Required binary (python3) and primary env BAIDU_API_KEY are appropriate.
Instruction Scope
SKILL.md instructs running the provided Python scripts to create tasks and poll for results. The scripts only read the provided video path (or URL) and optional sandbox proxy env vars, use BAIDU_API_KEY for authorization, and call the documented API endpoints. The only notable behavior is that local video files will be uploaded to Baidu BOS when a local path is provided — which is consistent with the feature but important for user privacy.
Install Mechanism
No install spec — instruction-only plus Python scripts. No downloads from arbitrary URLs or archive extraction. Risk from install mechanism is low; user must simply have python3 and requests available.
Credentials
Only BAIDU_API_KEY is required and used as a Bearer token when calling Baidu endpoints; the scripts also optionally honor DUMATE_SESSION_ID/DUMATE_SCHEDULER_URL for sandbox proxying. The requested env vars match the service being used and are proportionate. Users should ensure the BAIDU_API_KEY has appropriate scope and is trusted.
Persistence & Privilege
Skill is not always-enabled and does not request elevated or persistent system privileges. It does not modify other skills or system-wide settings. Autonomous invocation is allowed (platform default) but not combined with other privilege red flags.
Assessment
This skill appears to do what it says: it will upload local videos (if you pass a local file path) and call Baidu endpoints to create and poll AI-note tasks, using the BAIDU_API_KEY you supply. Before installing or using it: (1) only provide a BAIDU_API_KEY with limited scope you trust to be used for this purpose; (2) do not pass sensitive videos unless you accept they will be uploaded to Baidu BOS; (3) be aware that if DUMATE_SESSION_ID / DUMATE_SCHEDULER_URL are set, requests will be proxied through that scheduler (proxy headers like X-Dumate-Session-Id and Host will be sent); and (4) source/homepage are unknown — consider using official/verified clients or reviewing the key permissions and privacy policy of the target service before use.

Like a lobster shell, security has layers — review code before you run it.

Runtime requirements

📺 Clawdis
Binspython3
EnvBAIDU_API_KEY
Primary envBAIDU_API_KEY
latestvk970kgkndgh0w9dg5dm92ts1mh85q65y
267downloads
0stars
3versions
Updated 6h ago
v1.0.2
MIT-0

百度网盘AI视频笔记

功能特色

  • 支持mp4、mov、flv、mpeg、avi、mkv、wmv等主流视频格式
  • 异步生成机制、进度反馈、多格式输出

应用场景

  • 视频教学内容理解与笔记
  • 短视频平台内容分析与文案建议
  • 会议视频记录与关键信息提取
  • 高峰时段直播视频回顾与笔记

执行流程

  1. 任务创建: 提交视频URL(本地视频或网络视频) → 生成任务ID
  2. 轮询任务状态: 每3-5秒查询一次任务状态,直到任务完成
  3. 获取解析结果: 当 status = 10002 时,输出解析结果

状态码说明

CodeStatusAction
10000进行中继续轮询
10002完成输出解析结果
Other失败提示异常信息

笔记类型

TypeDescription
1文稿笔记
2大纲笔记
3图文笔记

使用示例

创建任务

Endpoint: POST /v2/tools/ai_note/task_create

Parameters:

  • video_url (required): Public video URL

Example:

python3 scripts/ai_notes_task_create.py --video_url='https://example.com/video.mp4'

Response:

{
  "task_id": "uuid-string"
}

查询任务状态

Endpoint: GET /v2/tools/ai_note/query

Parameters:

  • task_id (required): Task ID from create endpoint

Example:

python3 scripts/ai_notes_task_query.py --task_id="task-id-here"

Response (Completed):

[
   {
  "状态": "完成",
  "文稿笔记": ["note1", "note2"]
   },
   {
  "状态": "完成",
  "大纲笔记": ["note1", "note2"]
   },
   {
  "状态": "完成",
  "图文笔记": ["note1", "note2"]
   }
]

循环拉取任务状态

Option 1: Manual Polling

  1. Create task → store task_id
  2. Query every 3-5 seconds:
python3 scripts/ai_notes_task_query.py --task_id="task-id-here"
  1. Show progress updates:
    • Status 10000: Processing...
    • Status 10002: Completed
  2. Stop after 30-60 seconds (video length dependent)

Option 2: Auto Polling (Recommended)

Use the polling script for automatic status updates:

python3 scripts/ai_notes_poll.py --task_id="task-id-here" [--max_attempts=30] [--interval=5]

Examples:

# Default: 20 attempts, 3-second intervals
python3 scripts/ai_notes_poll.py --task_id="task-id-here"

# Custom: 30 attempts, 5-second intervals
python3 scripts/ai_notes_poll.py --task_id="task-id-here" --max_attempts=30 --interval=5

Output:

  • Shows real-time progress: [1/20] Processing... 25%
  • Auto-stops when complete
  • Returns formatted notes with type labels

异常处理

  • 文件下载失败: "File not found or invalid URL"
  • Processing error: "Failed to parse video"
  • Timeout: "Video too long, try again later"

Comments

Loading comments...