video-understanding SKILL.md skillA
video-understanding from zenstory-ai/video-recap-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add zenstory-ai/video-recap-skills/video-understanding@git:20261015.5785c33Pins git:20261015.5785c33 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- zenstory-ai/video-recap-skills
- Path
skills/video-understanding/SKILL.md- Versions recorded
- 12
- Latest version
- git:20261015.5785c33, committed Oct 15, 2026
- First version recorded
- Jun 14, 2026
- Size
- 8,117 bytes
- Repository stars
- 600
- License
- MIT
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。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file 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，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 `asr_timing_evidence.json` 说明可用性、有限时间精度与文本修正来源。 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 ```bash # 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。未设置 key 时重跑会复用已缓存的转写、画面分析、概览与故事索引（key 决定的默认 endpoint 不参与比对）；需要请求模型的 consolidation 记为 `skipped_no_key`，不发请求。缓存对不上（例如复制 work_dir 时没保留文件时间）而已有转写时，运行停下并保留转写：用 `cp -p` / `cp -Rp` / `rsync -t` 保留时间重新复制，或设置 key 后重跑（会重新转写）。不要用 `--skip-asr` 绕过，它会把现有转写替换成 `[]`。 …
Read the whole file at its exact version.
How to install
mdr add zenstory-ai/video-recap-skills/video-understanding@sha256:e0a9612667bf2fdfThe line at the top of this page pins the label git:20261015.5785c33, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_b2ahd4q7jhbigizs)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 12 versions of this file, between Jun 14, 2026 and Oct 15, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261015.5785c33 latest | 2026-10-15 | 5785c33 | 8,117 B | A | view · diff |
| git:20261014.14640fd | 2026-10-14 | 14640fd | 7,185 B | A | view · diff |
| git:20261003.76268aa | 2026-10-03 | 76268aa | 7,191 B | A | view · diff |
| git:20261003.8e06f65 | 2026-10-03 | 8e06f65 | 6,757 B | A | view · diff |
| git:20261003.c1e9698 | 2026-10-03 | c1e9698 | 6,201 B | A | view · diff |
| git:20260921.aeb0238 | 2026-09-21 | aeb0238 | 4,128 B | A | view · diff |
| git:20260920.e0218cf | 2026-09-20 | e0218cf | 4,703 B | A | view · diff |
| git:20260714.468182c | 2026-07-14 | 468182c | 3,852 B | A | view · diff |
| git:20260627.00f5ff7 | 2026-06-27 | 00f5ff7 | 4,230 B | A | view · diff |
| git:20260619.c0c48cf | 2026-06-19 | c0c48cf | 3,615 B | A | view · diff |
| git:20260615.02e402f | 2026-06-15 | 02e402f | 3,545 B | A | view · diff |
| git:20260614.79e91bb | 2026-06-14 | 79e91bb | 3,482 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8117 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
zenstory-ai/video-recap-skills · 600 stars · license MIT · pushed 2026-10-30 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_b2ahd4q7jhbigizs GET https://markdownregistry.com/api/v1/resolve?ref=zenstory-ai/video-recap-skills/video-understanding GET https://markdownregistry.com/api/v1/blob/e0a9612667bf2fdff0b50252daa18d3546c1a88cb53bca61544317dea86736b5
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from zenstory-ai/video-recap-skills
Every file in zenstory-ai/video-recap-skills