视频内容理解
把视频分析为结构化理解索引：场景检测、ASR 转写、逐场景 VLM 观察、静音窗口、融合时间线和写作 brief。 用于理解、索引或总结视频，也作为后续创作前的分析阶段。输入视频文件；输出 scenes.json、 asr_result.json、vlm_analysis.json、silence_periods.json、timeline_fusion.json、agent_narration_brief.md。 触发词：视频理解、视频分析、视频索引、video understanding、analyze video、看懂视频。
as observed 2026-10-04T09:46:17.065Z- Identifier
video-understanding- Source
- ClawHub
- Version observed
- 1.0.6
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-09-10T12:18:05.764Z
- Observations recorded
- 3
- Installs (reported upstream)
- 0
- Weekly downloads (upstream)
- 32
- Declared license
- MIT-0
Observation history
2026-10-04T09:46:17.065Z
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"- Enhanced skill description and documentation in SKILL.md with detailed processing stages, output contracts, options, and best practices.\n- Clearly outlined each analysis phase, | "- Improved documentation and usage instructions for the video-understanding skill, especially around workflow, output files, and command-line options.\n- Clearly described each pr |
latestVersion |
"1.0.1" | "1.0.6" |
2026-10-03T08:46:10.142Z
Fields that differed: license changelog description displayName latestVersion summary topics
| Field | Before | After |
|---|---|---|
license |
null | "MIT-0" |
changelog |
"Restore general HTTP(S) video downloading and download-only mode per intended product scope; no source-domain whitelist, normal query parameters supported. Preserve consent, opt-i | "- Enhanced skill description and documentation in SKILL.md with detailed processing stages, output contracts, options, and best practices.\n- Clearly outlined each analysis phase, |
description |
"Watch and analyze video URLs or files using Gemini native agentic video understanding for summaries, timestamped answers, transcripts, and visual reconstruction." | null |
displayName |
"video-understanding" | "视频内容理解" |
latestVersion |
"2.0.4" | "1.0.1" |
summary |
"Watch and analyze video URLs or files using Gemini native agentic video understanding for summaries, timestamped answers, transcripts, and visual reconstruction." | "把视频分析为结构化理解索引：场景检测、ASR 转写、逐场景 VLM 观察、静音窗口、融合时间线和写作 brief。 用于理解、索引或总结视频，也作为后续创作前的分析阶段。输入视频文件；输出 scenes.json、 asr_result.json、vlm_analysis.json、silence_periods.json、timeline_fusion. |
topics |
["Twitter"] | ["content-creation","ffmpeg","video-editing","video-recap"] |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.