Individual skill
video-understanding
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。
packages/knowledge/video-recap/skills/video-understanding/SKILL.md
Source commit ed56e4a3946fe7e6713b07164787a23128f6a848
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 10, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 725
- Repository last updated
- Nov 8, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai-agents Repository topic
- creative-writing Repository topic
- deepseek-harness Repository topic
- dsh-plugin Repository topic
- fiction-writing Repository topic
- novel-writing Repository topic
- oh-story Repository topic
- screenwriting Repository topic
- short-drama Repository topic
- drama-skills Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 8,117 bytesSKILL.mdcore · 8,117 bytesSKILL.mdcore · 8,117 bytesreferences/data-schema.mddoc · 6,218 bytesreferences/prompt-templates.mddoc · 1,708 bytesreferences/research-guide.mddoc · 2,880 bytesscripts/agent_text.pyruns · 7,379 bytesscripts/asr.pyruns · 11,581 bytesscripts/asr_timing_evidence.pyruns · 9,958 bytesscripts/briefing/__init__.pyruns · 101 bytesscripts/briefing/builder.pyruns · 28,763 bytesscripts/briefing/context.pyruns · 13,844 bytesscripts/briefing/inputs.pyruns · 9,105 bytesscripts/briefing/timeline.pyruns · 18,812 bytesscripts/consolidate.pyruns · 27,417 bytesscripts/detect.pyruns · 25,952 bytesscripts/extract.pyruns · 2,559 bytesscripts/index_normalize.pyruns · 14,305 bytesscripts/lib.pyruns · 23,644 bytesscripts/storyboard.pyruns · 24,654 bytesscripts/timeline_fusion.pyruns · 3,102 bytesscripts/understand.pyruns · 192 bytesscripts/understanding_brief.pyruns · 8,770 bytesscripts/understanding_cache.pyruns · 12,607 bytesscripts/understanding_runner.pyruns · 14,528 bytesscripts/understanding_storyboard.pyruns · 13,614 bytesscripts/vlm.pyruns · 29,109 bytes
Read excerpt
## 1. 定位
本技能把源视频转成 Agent 与下游阶段可读取的理解索引，以**素材观察员 / 场记**的角色记录证据：
- 先观察，再解释；事实与推断分开。
- 除了“发生了什么”，还要让下游看见知识、权力、目标、关系或情绪在哪一刻变化。
- 标出由谁的 POV 承载变化、哪个反应或表演不可替代，以及哪里存在完整台词/动作的自然剪辑边界。
- 证据不足时保留不确定性，不制造戏剧结论。
## 2. 处理阶段
1. **场景检测**：写 `scenes.json`，包含切点、时长和废片段过滤结果。
2. **抽帧**：为视觉分析提取代表帧。
3. **ASR**：通过 `mimo-v2.5-asr` 写粗分段对白 `asr_result.json`，并写