Home / zenstory-ai / video-recap-skills · GitHub

video-reference SKILL.md skillA

video-reference from zenstory-ai/video-recap-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add zenstory-ai/video-recap-skills/video-reference@git:20261015.5785c33

Pins 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-reference/SKILL.md
Versions recorded: 3
Latest version: git:20261015.5785c33, committed Oct 15, 2026
First version recorded: Oct 3, 2026
Size: 9,672 bytes
Repository stars: 582
License: MIT

按需把一部成片拆成可复用的制作参考：测镜头节奏与响度，标注段落与音轨分工，把原片事实与可迁移方法分开，导出不含原片人名台词的 production_reference.json 供下次制作参考。不在默认生产路径上。触发词：拆片、拆解成片、制作参考、参考模板、production reference。.

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

本技能把一部**已完成的成片**拆成下一次制作可参考的方法与数值，按需在本地运行。它只写自己的测量、标注与导出物，不调用 MiMo，也不对生产流程评分或拦截。

Agent 的角色是**拆片编辑**：先如实记录"这部片子怎么做的"（事实），再提炼"换一部素材还能怎么用"（方法）。
两者必须分开：事实只留在本地工作目录，导出物只含方法和测得的数值。

## 2. 输入

- 成片文件（`.mp4 / .mov / .mkv / .webm`）。
- 对**这部成片**跑出的视频理解产物目录 `U`（建议 `ASR_SEGMENT_SECONDS=5`，窗口越短，旁白语速越准）。
  本技能读取其中可选的 `asr_result.json`、`asr_timing_evidence.json`、`background_research.json`、`understanding_index.json`
  （其 `characters` 的名字、别名与 ASR 提及都进入人名泄漏扫描）；
  标注时 Agent 还应看故事板 / contact sheet 与 `vlm_analysis.json`。

没有理解产物也能跑，但旁白语速为空，泄漏扫描只剩 Agent 自己写的 `entities`，check 会给出警告；
看画面可用 `frames --span 0,<时长> --step 2` 生成的抽帧拼图。

下面的 `scripts/...` 均相对于本技能目录。

## 3. 流程

```bash
python3 scripts/reference.py measure <成片> --work-dir U        # 一次 ffmpeg：切点 + 响度，按文件身份缓存
python3 scripts/reference.py frames  <成片> --work-dir U --review          # 逐帧看被压下的疑似切点
python3 scripts/reference.py frames  <成片> --work-dir U --longest 5       # 看最长镜头里有没有漏切
python3 scripts/reference.py check   --work-dir U [--json]      # 校验并打印派生值
python3 scripts/reference.py export  --work-dir U --out <下次运行的 work_dir>/production_reference.json
```

1. **measure** 写 `U/reference_measurements.json`（只由脚本写）：镜头切点、镜长分布、每分钟切点数、10 秒切点曲线、
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add zenstory-ai/video-recap-skills/video-reference@sha256:eba7399c9021d3ad

The 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.

Badge

[![mdr](https://markdownregistry.com/badge/art_akuqqh67dhhjhldi.svg)](https://markdownregistry.com/a/art_akuqqh67dhhjhldi)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Oct 3, 2026 and Oct 15, 2026, about one every 6 days.

version	committed	commit	size	audit
git:20261015.5785c33 latest	2026-10-15	5785c33	9,672 B	A	view · diff
git:20261014.14640fd	2026-10-14	14640fd	9,694 B	A	view · diff
git:20261003.2d2b183	2026-10-03	2d2b183	9,699 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (9672 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

GitHub

zenstory-ai/video-recap-skills · 582 stars · license MIT · pushed 2026-10-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_akuqqh67dhhjhldi
GET https://markdownregistry.com/api/v1/resolve?ref=zenstory-ai/video-recap-skills/video-reference
GET https://markdownregistry.com/api/v1/blob/eba7399c9021d3ad218a4f4f5cfd4e1f02538c0d31c3670a6a5531487aa927e9

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

AGENTS.md AGENTS.md file

zenstory-ai/video-recap-skills · AGENTS.md

git:20261014.14640fd · audit A · 582 stars

CLAUDE.md CLAUDE.md file

zenstory-ai/video-recap-skills · CLAUDE.md

git:20261014.14640fd · audit B · 582 stars

video-assemble SKILL.md skill

zenstory-ai/video-recap-skills · skills/video-assemble/SKILL.md · 合成视频解说最终成片：把旁白音频铺到源视频上，按旁白窗口压低原声，生成 SRT / ASS 字幕并可烧录，最后做响度标准化。作为最终合成阶段使用。输入源视频、tts_meta.json 与旁白位置；输出 recap…