video-compose
Skill1 starsChanged 33 days agoMITView on GitHub
成片合成原子能力:镜头 mp4 列表 + 配音 wav 时间轴(delay_ms)+ SRT 字幕,一条 manifest JSON 合成一条竖屏成片(归一化拼接、adelay/amix 混音、烧字幕、+faststart,字幕失败自动降级重试)。当需要把分镜镜头和配音合成最终视频、批量出片流水线的合成步骤、或替换 build_epxx 类手工脚本时使用。Use when composing final videos from shot clips, voiceover wavs and subtitles via a manifest.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- CatCatUncle/openworkbuddytheir own version, first seen Nov 5, 2026
- puntorigen/avatar-skillstheir own version, first seen Jul 9, 2026
- Utopai-Research/pai-codetheir own version, first seen Jun 12, 2026
- Utopai-Research/pai-protheir own version, first seen Jun 12, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- CatCatUncle/openworkbuddy★ 398same name
- Utopai-Research/pai-code★ 353same name
- Utopai-Research/pai-pro★ 352same name
- puntorigen/avatar-skills★ 3same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ark-agent-plan-imageSkill
- ark-seedance-videoSkill
- ark-seedream-imageSkill
- bilibili-uploadSkill
- chinese-ttsSkill
- douyin-publishSkill
- dreamina-canvas-cliSkill
- feishu-bitableSkill
- image-to-videoSkill
- media-verifySkill
- multi-platform-publish-orchestratorSkill
- quad-platform-publishSkill
- tangshi-data-reviewSkill
- tangshi-pipelineSkill
- tencent-uploadSkill
- video-coverSkill
- video-pipelineSkill
- xiaohongshu-skillsSkill
The file
Files
video-compose — 分镜+配音+SRT → 成片(原子)
✅ 状态:本机实测通过(2026-09-30,EP11A 全量 manifest 复现,输出 14,129,752 B 与官方成片逐字节同大小)
原子边界:manifest 进、一条成片出。manifest 由编排层生成(时间轴规划是编排的事);镜头从哪来(image-to-video / ark-seedance-video)不归本 skill 管。
用法
python scripts/video-compose.py <manifest.json> [--keep-build]manifest 格式
{
"out": "EPxxA-成片.mp4",
"total": 32,
"fps": 24,
"shots": [{"file": "v1.mp4"}, {"file": "v2.mp4"}],
"audio": [{"file": "vo0.wav", "delay_ms": 0},
{"file": "vo1.wav", "delay_ms": 5500}],
"subtitles": "subs.srt",
"style": "FontName=Microsoft YaHei,FontSize=10,..."
}- 路径(相对/绝对)以 manifest 所在目录 为基准解析
audio可[](纯画面);subtitles/style可省略(style 用内置竖屏样式FontSize=10, Outline=1.5, MarginV=90——2026-10-01 用户指定上移:文字块底边落在 ~69% 高度、底部留 1/3 避开平台 UI 遮挡,参考抖音截图位置;旧 MarginV=14 贴底会被 @账号/描述区盖住;横版 18/20 会溢出裁切,已踩坑。全诗字卡行数多时注意:90+行数×15 ≤ 288(超出改 MarginV=60 或 FontSize=9)total是-t硬截断,务必 ≥ 最后一条配音结束时刻
行为(与唐诗 build_epxx 逐参数一致)
- 每个镜头归一化:
scale=720:1280:flags=lanczos,fps=<fps>,format=yuv420p+ libx264 crf18 无音轨 - concat demuxer 顺序拼接
- 配音拷入构建目录(规避中文/空格路径),逐路
adelay=...:all=1→amix normalize=0 duration=longest apad subtitles=subs.srt:force_style=...烧字幕;失败自动降级为无字幕重试-c:a aac 128k -movflags +faststart→ 拷到out,清理<out>.build(--keep-build保留)
验收建议
合成后跑 skill media-verify:astats 核对配音窗/静默窗、brightness 防白屏。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

