Home / zenstory-ai / oh-story-dsh · GitHub

video-assemble SKILL.md skillA

This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.

video-assemble from zenstory-ai/oh-story-dsh 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/oh-story-dsh/video-assemble@git:20261015.215a6fa

Pins git:20261015.215a6fa in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: zenstory-ai/oh-story-dsh
Path: packages/knowledge/video-recap/skills/video-assemble/SKILL.md
Versions recorded: 4
Latest version: git:20261015.215a6fa, committed Oct 15, 2026
First version recorded: Sep 1, 2026
Size: 12,364 bytes
Repository stars: 557
License: MIT

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 成片和字幕。触发词：视频合成、混音、字幕、压字幕、assemble video、mux、ducking、subtitles、成片。.

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

本技能负责最终合成：

1. 把各段旁白音频放到视频时间线上。
2. 在旁白窗口内用固定包络压低原声（盖住原声对白时与落在安静段时各用一档音量），间隙恢复原声。
3. 根据旁白位置生成 `subtitles.srt`；默认同时生成并烧录 `subtitles.ass`，`--no-burn-subtitles` 可关闭。不烧录时（关闭或降级），`subtitles.srt` 复制到成片旁，名为 `recap_<stem>.srt`；烧录时删掉旧的同名外挂字幕。
4. 可选把最终响度标准化到目标 LUFS：两遍 loudnorm，只用一个恒定增益，不做动态压缩；混音的真峰值放不下这么大的增益时，先过 4 倍过采样的真峰值限幅器（最多削 `LOUDNESS_LIMITER_MAX_DB`，默认 6 dB），超出部分才下调目标响度。真峰值目标针对交付的 AAC 文件：AAC 编码会让真峰值比 PCM 混音高 0.3–1.4 dB，所以首次渲染瞄准 TP 下 0.5 dB，渲染后解码成片实测；仍超过 -1 dBTP 时按超出量再降 0.1 dB 只重编码音频（画面流复制），最多两次，仍超出则以 `delivered_true_peak_over_target` 阻断。ffmpeg 实际用的模式、限幅量与成片实测值记在 `assembly_qc.json` 的 `loudness_mode` 与 `loudnorm_final_pass`（`delivered`）。
5. 成片不带原片的容器元数据（`title`、`comment` 等标签与章节）。

## 2. 声音收尾契约

合成阶段只实现创作决定，不凭空制造决定。Agent 在写旁白位置前，已在 `visual_audio_board.json` 为每个 beat 指定 `audio_owner`：

- `original_dialogue`
- `action_sound`
- `ambience` / `music`
- `silence`
- `narration`

旁白间隙按已选声音分工保留。只在确有任务时加入 BGM，并保住必须听见的台词与有意义的沉默。

当前渲染器不解析 `visual_audio_board.json`；Agent 通过旁白时间、`overlaps_speech`、原声留白与现有混音参数落实这些决定。

## 3. 输入契约

- `<video>`：源视频；cut 模式下为 `edited_source.mp4`。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add zenstory-ai/oh-story-dsh/video-assemble@sha256:88ab7ae6de32321e

The line at the top of this page pins the label git:20261015.215a6fa, 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_jlgamrezh23mvhin.svg)](https://markdownregistry.com/a/art_jlgamrezh23mvhin)

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

Versions

The registry has recorded 4 versions of this file, between Sep 1, 2026 and Oct 15, 2026, about one every 15 days.

version	committed	commit	size	audit
git:20261015.215a6fa latest	2026-10-15	215a6fa	12,364 B	A	view · diff
git:20261003.02bb238	2026-10-03	02bb238	12,210 B	A	view · diff
git:20260928.58dbe10	2026-09-28	58dbe10	8,875 B	A	view · diff
git:20260901.38b5be5	2026-09-01	38b5be5	6,926 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 (12364 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/oh-story-dsh · 557 stars · license MIT · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_jlgamrezh23mvhin
GET https://markdownregistry.com/api/v1/resolve?ref=zenstory-ai/oh-story-dsh/video-assemble
GET https://markdownregistry.com/api/v1/blob/88ab7ae6de32321e1bdb1858a132e7968b3f5f20a8b549378f727dfe0d3db2ce

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/oh-story-dsh

AGENTS.md AGENTS.md file

zenstory-ai/oh-story-dsh · AGENTS.md

git:20261014.69c6f05 · audit A · 557 stars

CLAUDE.md CLAUDE.md file

zenstory-ai/oh-story-dsh · CLAUDE.md

git:20261014.69c6f05 · audit B · 557 stars

short-drama-assets SKILL.md skill

zenstory-ai/oh-story-dsh · packages/knowledge/drama/skills/short-drama-assets/SKILL.md · 从短剧剧本拆出人物/造型、地点/视图、道具/状态和跨场连续性，写成创作者可读的视觉设定。用户说“拆角色/场景/道具”“做资产设定”“判断复用还是新变体”“更新造型/道具状态”，或拿现成剧本直接做视觉资产准备时使用；不写图片提示词，不生成媒体…