agentmods.dev

video-understanding

video-understanding is a skill for Claude Code from zenstory-ai/video-recap-skills. It costs 126 tokens per session (1,140 once invoked), scanned A, original, MIT.

A video analysis tool that turns a video into a structured index of scenes, spoken words, visual observations, quiet sections, and a writing brief. ASR means automatic speech recognition, which converts speech in the video into timestamped text.

In plain words
What is it for?
Use it to detect scenes, transcribe dialogue, inspect representative frames, find silent sections, combine these findings into a timeline, and prepare a narration brief.
Why use it?
It gives later editing and writing steps a time-based understanding of what happens, what is said, and where meaningful visual or audio changes occur.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the video-recap-skills plugin — 6 skills shipped together

not rated 505repo +7 today A scan SkillSpector: pass 126 tokens original MIT

Good fit Use it to detect scenes, transcribe dialogue, inspect representative frames, find silent sections, combine these findings into a timeline, and prepare a narration brief.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zenstory-ai/video-recap-skills/video-understanding
View source ↗ zenstory-ai/video-recap-skills zenstory.ai
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add zenstory-ai/video-recap-skills --skill video-understanding
Clone the repo
git clone --depth 1 https://github.com/zenstory-ai/video-recap-skills

Made for: Claude Code.

Or install video-recap-skills, the plugin that ships this one along with the rest of its 6 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for video-understanding

README.md
[![agentmods](https://agentmods.dev/badge/skills/zenstory-ai/video-recap-skills/video-understanding/github.svg)](https://agentmods.dev/skills/zenstory-ai/video-recap-skills/video-understanding)
Your own site
<a href="https://agentmods.dev/skills/zenstory-ai/video-recap-skills/video-understanding"><img src="https://agentmods.dev/badge/skills/zenstory-ai/video-recap-skills/video-understanding/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for video-understanding

Your own site · 80×15
<a href="https://agentmods.dev/skills/zenstory-ai/video-recap-skills/video-understanding"><img src="https://agentmods.dev/badge/skills/zenstory-ai/video-recap-skills/video-understanding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,140 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00126 $0.01140
Opus 5 $0.00063 $0.00570
Sonnet 5 $0.00025 $0.00228
Haiku 4.5 $0.00013 $0.00114

Measured 12d ago against content hash 86c395f032d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

video-understanding scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 22 executable files (scripts/agent_brief.py, scripts/agent_text.py, scripts/asr.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/video-understanding/SKILL.md · 76 lines

What it actually says

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。它的创作角色是素材观察员 / 场记，不是导演：

  • 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 写时间戳对白 asr_result.json。
  4. 静音检测：写 silence_periods.json，标注安静窗口与 has_speech。
  5. VLM 观察：写 vlm_analysis.json，包含场景描述、深层分析和 frame_facts。
  6. 时间线融合与创作 brief：写 timeline_fusion.json、asr_writing_chunks.json 和 agent_narration_brief.md。

各阶段只有在输出产物与 provenance sidecar 同时匹配当前视频及影响结果的设置时才会复用；--force 强制重算。

3. 环境要求

# ffmpeg: brew install ffmpeg | apt install ffmpeg | choco install ffmpeg
export MIMO_API_KEY=***

ASR 使用 mimo-v2.5-asr；VLM 使用 mimo-v2.5。--skip-asr 可跳过对白转写，但完整理解仍需要 MIMO_API_KEY 运行 VLM。--mimo-video-overview 可开启按场景块的视频概览。

若 work_dir/background_research.json 存在，本技能会把剧情梗概和角色名折入 VLM 上下文；--context 可补充一条简短提示。

下面的 scripts/... 均相对于本技能目录。若执行器从仓库根目录启动，请给脚本路径加上本技能的绝对目录。脚本不从其他技能目录读取文件；外部输入仅限命令显式传入的视频、参数与 work_dir 产物。

4. 运行命令

python3 scripts/understand.py <video> --work-dir <work_dir> \
  [--context "节目名/角色名"] [--scene-threshold 0.1] [--skip-asr] [--mimo-video-overview] [--force]

5. 输出契约

文件 内容
scenes.json 场景切点、起止时间与时长
asr_result.json [{start, end, text}] 时间戳对白
vlm_analysis.json 逐场景描述、深层分析与 frame_facts
silence_periods.json [{start, end, duration, has_speech}] 安静窗口
timeline_fusion.json VLM、ASR 与静音信息的统一时间线
asr_writing_chunks.json 按句界和场景切分的 ASR 写作块
agent_narration_brief.md Agent 首先阅读的创作简报

后续写作阶段根据创作简报与索引制定方案并写 narration.json。

6. 参考资料

  • 背景调研：references/research-guide.md，产出 background_research.json。
  • JSON 结构：references/data-schema.md。

7. 能力边界

  • 不写解说词，也不做解说评分；只负责生成理解索引与创作简报。
  • 不剪辑、不配音、不合成视频。
  • 不编造信号无法支持的剧情；当 ASR / VLM 过薄时输出素材警告。
  • 不发布、不调度，只向 work_dir 写产物并停止。
Files

What ships with it

25 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 76 lines · 126 tokens per session scan A 86c395f032d9

Subscribe to this mod's changes

video-understanding is a skill published in the GitHub repository zenstory-ai/video-recap-skills (505 stars, last pushed today), licensed MIT. It adds 126 tokens to every session and 1,140 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude CodeCreative and mediaResearchai-agentasrttsvideo-narrationvideo-recap
Related

Other skills, from other repositories

narrator-ai-cli

A command-line client for creating AI-narrated movie and short-drama videos. It can guide a workflow from selecting source material, templates, music, and voices to writing narration and combining the video.

NarratorAI-Studio/narrator-ai-cli-skill · 132 tokens

narrator-ai-cli

Create AI-narrated film/drama commentary videos via CLI. Two workflow paths (Original & Adapted narration), 93 movies, 146 BGM tracks, 63 dubbing voices in 11 languages, 90+ narration templates. Use when creating narration videos, film commentary, short drama dubbing, or video production.

NarratorAI-Studio/narrator-ai-cli · 73 tokens

director-agent

Skill "director-agent" from 6174/recut, covering director agent, core rule, usability and anti-laziness contract, output must be usable and modes.

6174/recut · 0 tokens

recut-editor

A timeline-editing skill for creating new videos or changing parts of an existing timeline in a CapCut-style editor. It can work with media assets and export the result while keeping edits undoable.

6174/recut · 78 tokens

recut-directing-qc

A quality-control workflow for diagnosing problems in a finished video. It connects each visible symptom to a likely cause and a repair, then checks whether the fix passes review.

6174/recut · 47 tokens

recut-directing-short-drama

A directing guide for planning the production of story-based AI short dramas, animated dramas, and narrative short videos. It covers decisions from story intent through a controlled production process and contract management.

6174/recut · 56 tokens