Communitygithub.com

Andersonlimahw/lemon-ai-hub

编辑现有视频并在交付前验证任何渲染——重新剪辑、修剪、调整到其他宽高比、烧录或附加字幕、替换或混音音频、循环和导出;以及QC关卡(探测、联系表、按节拍截图、响度、循环接缝、可读性、事实、PII)。用于剪辑素材或任何动态视频的最终检查。

lemon-ai-hub 是什么?

该技能专为AI代理(如Claude Code、Cursor、Codex)设计,提供一套完整的视频编辑和质量控制(QC)工作流。它利用FFmpeg执行无损修整、帧精确裁剪、不同宽高比(如16:9转9:16)的重新构图、字幕烧录或软字幕附加、音频替换、语音下音乐闪避以及LUFS标准化编码等操作。所有编辑均以非破坏性方式进行——将输出写入新文件(如`*_v2.mp4`或`renders/`),保持源文件完整。QC部分通过一个脚本系统运行,包括探测(probe)、联系表(sheet)、按节拍截图(stills)、响度分析(loudness)、循环接缝检测(loop)等检查,并提供一个全面的检查清单(规格、故事连贯性、节奏、可读性、品牌、事实、安全性、音频、可访问性、循环、确定性)。适用于剪辑团队或快速处理最终交付细节的AI代理,支持Mac/Linux环境,并强调质量保证,而非在最终编码中掩盖问题。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Andersonlimahw/lemon-ai-hub/tree/HEAD/plugins/motion-movie-expert/skills/video-edit-qc

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

视频编辑与质量控制

绝不在原地编辑。将输出写入新文件(*_v2.mp4,renders/),保持源文件完整, 并在覆盖或删除任何内容前进行确认。

编辑方案(FFmpeg)

# 不重新编码修剪(在关键帧上切割)/ 重新编码实现帧精确修剪
ffmpeg -ss 00:00:05 -to 00:00:20 -i in.mp4 -c copy out.mp4
ffmpeg -i in.mp4 -ss 5 -to 20 -c:v libx264 -crf 16 -c:a aac out.mp4

# 连接具有相同编解码器的片段
printf "file '%s'\n" a.mp4 b.mp4 > list.txt && ffmpeg -f concat -safe 0 -i list.txt -c copy out.mp4

# 围绕 x=CX(像素)处的主题将 16:9 重新构图成 9:16;优先考虑重新设计布局
ffmpeg -i in.mp4 -vf "crop=ih*9/16:ih:CX-ih*9/32:0,scale=1080:1920" -c:a copy out_9x16.mp4

# 烧录字幕(社交媒体样式)/ 作为软字幕轨道附加
ffmpeg -i in.mp4 -vf "subtitles=captions.srt:force_style='FontName=Inter,FontSize=14,Outline=1,MarginV=60'" out.mp4
ffmpeg -i in.mp4 -i captions.srt -c copy -c:s mov_text out.mp4

# 替换音频 / 音乐语音闪避 / 标准化至 -14 LUFS
ffmpeg -i in.mp4 -i mix.wav -map 0:v -map 1:a -c:v copy -shortest out.mp4
ffmpeg -i music.wav -i vo.wav -filter_complex "[0][1]sidechaincompress=threshold=0.05:ratio=8:attack=150:release=300[m];[m][1]amix=inputs=2:normalize=0" mix.wav
ffmpeg -i mix.wav -af loudnorm=I=-14:TP=-1:LRA=11 -ar 48000 mix_norm.wav   # 最终交付需双通

# 网络/社交媒体交付编码(从母版开始;母版本身是 CRF 16——参见 hyperframes-production)
ffmpeg -i in.mp4 -c:v libx264 -pix_fmt yuv420p -crf 18 -preset slow -movflags +faststart -c:a aac -b:a 192k out.mp4

对于说话人头像的重新剪辑,从转录文本(voice-video-sync 时间戳)的句子边界处切割,仅当剪切不可见时才去除填充词,并在每次剪切时保留 80–150 毫秒的环境音。对于设计的动态内容重新构图,尽可能在源项目中按宽高比重新布局,而非裁剪。

QC 关卡

从项目目录运行(QC=<plugin-root>/scripts/qc.sh):

$QC probe    final.mp4                  # 编解码器、尺寸、帧率、时长、是否存在音频
$QC sheet    final.mp4 qc/sheet.png 4 4 # 用于全面通读的联系表
$QC stills   final.mp4 qc/ 0.5 3 7.5    # 每个故事板节拍一张截图;超出结尾则失败
$QC loudness final.mp4                  # -14 ±1 LUFS(广播使用 -23),真峰值 <= -1 dBTP
$QC loop     final.mp4                  # 仅限循环:接缝必须看起来像正常的帧步进

然后对照故事板审查截图和联系表:

关卡通过条件
规格分辨率、帧率、时长和编解码器符合每个宽高比的简报
故事关闭声音也能理解;前 2 秒传达价值或钩子
连续性每个剪辑都有其载体;不相关屏幕之间无交叉淡变;无乒乓接缝
节奏关键动作在节拍上;无死帧;无超过 3 秒的无动机静止
可读性无裁剪或重叠的文本;字幕 ≤2 行,位于安全区内;数字在动态模糊中仍可辨认
品牌采样颜色匹配标记;正确的字体和图标集;无重新设计
事实每个屏幕上的数字或声明都在故事板事实列表中
安全性无 PII,未经许可无真实第三方品牌,具备许可和署名
音频响度和真峰值在范围内;音效在音乐下;配音在音乐上清晰可辨
可访问性≤3 次闪烁每秒;字幕与口语单词匹配
循环当要求时,接缝通过 qc.sh loop 检查
确定性同一时间戳渲染两次结果相同(抽查 3 帧)

将每个关卡报告为通过 / 失败 / 未检查,并附上证据路径(截图、联系表、命令输出)。在源项目中修复失败项并重新渲染;不要在最终编码中掩盖问题。对于长视频,按章节拆开 QC,并并行使用每个章节的 motion-qc 代理。

Individual skills in this repo

This repo contains 9 individual skills — each has its own dedicated page.

Andersonlimahw/lemon-ai-hub

When the user wants to plan a product launch, feature announcement, or release strategy. Also use when the user mentions 'launch,' 'Product Hunt,' 'feature release,' 'announcement,' 'go-to-market,' 'beta launch,' 'early access,' 'waitlist,' 'product update,' 'how do I launch this,' 'launch checklist,' 'GTM plan,' or 'we're about to ship.' Use this whenever someone is preparing to release something publicly. For ongoing marketing after launch, see marketing-ideas. For the offer being launched (bonuses, guarantees, scarcity, naming), see offers.

Andersonlimahw/lemon-ai-hub

Create and edit motion videos end to end — product motion films, motion graphics, narrated explainers, captioned clips, UI animation recreations, and recuts. Orchestrates brief, storyboard, choreography, build (HyperFrames or any deterministic renderer), voice/caption sync, and render QC. Use when the user asks to make, animate, storyboard, narrate, caption, edit, or render a video or motion piece; skip for static images and web UI work with no video deliverable.

Andersonlimahw/lemon-ai-hub

Build and render a deterministic video composition — HyperFrames (HTML + GSAP) by default, or a custom seek(t) + Playwright + FFmpeg pipeline. Covers project setup, composition contract, timeline rules, creative direction for frames, lint/check/snapshot, preview, and local render. Use when implementing an approved storyboard as code.

Andersonlimahw/lemon-ai-hub

Motion law for multi-scene videos — seam continuity (axis, direction, speed, phase), carriers, causal motion, springs and timing, camera, transitions, stillness, and loop design. Use when planning or fixing how scenes connect and move, before and during any animation build.

Andersonlimahw/lemon-ai-hub

Short design-led motion graphics where motion is the message — kinetic typography, stat count-up, chart/data-viz reveal, logo sting, lower third or callout, animated map, tweet/news/headline card, webpage or UI walkthrough, and image-plus-data fusion. Usually under 10 s, up to about 30 s, no narration; renders to MP4 or a transparent overlay. Use when the user wants a short motion graphic, animated stat/chart/logo/map/card, or overlay; when the upstream HyperFrames `motion-graphics` skill is installed, use it for exact CLI flags and registry blocks.

Andersonlimahw/lemon-ai-hub

Turn a video idea, product, or script into an approved master prompt and pre-implementation storyboard — intake, concept, 8–12 state sequence, beat grid, transition map, camera plan, audio cue plan, and render architecture. Use before building any new video, or when a video brief is vague.

Andersonlimahw/lemon-ai-hub

Motion tokens, spring presets, and React/Next.js (motion/react) interaction patterns for product UI that appears in a video — rebuilding real product screens faithfully, animating them as seekable scenes, and keeping the live product's motion consistent with the film. Use when a motion video shows or recreates product UI; for web UI work with no video deliverable use design-expert instead.

Andersonlimahw/lemon-ai-hub

Synchronize narration, captions, music, and SFX with picture — narration writing, script lock, TTS or recorded voiceover, word-level timestamps, caption blocks, shot windows derived from the voice track, dwell budgets, ducking, and loudness targets. Use for narrated explainers, voiceover changes, subtitles, or any video where timing must follow audio.

Andersonlimahw/lemon-ai-hub

Agent skill at plugins/video/SKILL.md

相关技能