Agent skill

Videohub Beat Editor

by cacity in cacity/VideoHub

根据一段音频、歌曲或参考视频的节拍,为一个长视频、多个视频或素材目录自动建立镜头候选库,生成卡点剪辑计划,并批量渲染 16:9、3:4、4:3、9:16 等多画幅成片。支持固定镜头数量、强拍切换、歌词字幕、镜头替换、封面、标题、caption、hashtags 和完整 QA。用于“按音乐卡点剪视频”“给音频和素材批量做卡点视频”“检测强拍并自动选镜头”“同一计划输出多个画幅”等任务。

MITAuto-check passedMedia & Creative

Install Videohub Beat Editor

skills CLI
$ npx skills add cacity/VideoHub --skill videohub-beat-editor -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cacity/VideoHub videohub-beat-editor --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cacity/VideoHub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/videohub-beat-editor .claude/skills/videohub-beat-editor && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
videohub-beat-editor
GitHub stars
167
Token cost
~626 tokens
SKILL.md length
86 words
Files
6 (incl. scripts, references)
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

根据一段音频、歌曲或参考视频的节拍,为一个长视频、多个视频或素材目录自动建立镜头候选库,生成卡点剪辑计划,并批量渲染 16:9、3:4、4:3、9:16 等多画幅成片。支持固定镜头数量、强拍切换、歌词字幕、镜头替换、封面、标题、caption、hashtags 和完整 QA。用于“按音乐卡点剪视频”“给音频和素材批量做卡点视频”“检测强拍并自动选镜头”“同一计划输出多个画幅”等任务。

  • Works in 6 steps: 创建独立任务目录 → 分析音频 → 建立视频候选库 → …
  • Tasks that involve Video production
  • SKILL.md covers 核心原则, 1. 创建独立任务目录, 2. 分析音频 and 3. 建立视频候选库, plus 3 more sections
  • Runs Python scripts from its folder; calls python

What it does

Videohub Beat Editor is an agent skill from cacity/VideoHub. 根据一段音频、歌曲或参考视频的节拍,为一个长视频、多个视频或素材目录自动建立镜头候选库,生成卡点剪辑计划,并批量渲染 16:9、3:4、4:3、9:16 等多画幅成片。支持固定镜头数量、强拍切换、歌词字幕、镜头替换、封面、标题、caption、hashtags 和完整 QA。用于“按音乐卡点剪视频”“给音频和素材批量做卡点视频”“检测强拍并自动选镜头”“同一计划输出多个画幅”等任务。

Its SKILL.md is about 630 tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/plan-schema.md` and `scripts/analyze_audio.py`).

It sits in Media & Creative, covering Video production. The repository describes itself as: VideoHub 是一款本地化多平台视频处理与智能剪辑工具,支持 YouTube、抖音/TikTok、Instagram、Bilibili 和 Twitter/X,提供视频下载、Whisper 转写、字幕翻译与润色、多模型 AI 配音、影视解说、故事剪辑、音乐卡点及剧集批量处理,并可通过 Codex、Claude Code… The licence is MIT.

When your agent uses it

  • Tasks that involve Video production

Example prompts

  • “按音乐卡点剪视频”
  • “给音频和素材批量做卡点视频”
  • “检测强拍并自动选镜头”
  • “/videohub-beat-editor”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. 创建独立任务目录
  2. 分析音频
  3. 建立视频候选库
  4. 批量渲染
  5. 歌词、封面和发布包
  6. QA

What it can do on your machine

Read from SKILL.md and the folder at commit d1da59c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 3 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Videohub Beat Editor loads about 626 tokens when it runs, and up to ~968 if it reads all its reference files. Until then it costs about 54 tokens; SKILL.md has 86 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~626
With references · SKILL.md plus every file in references/, read only if the agent opens them
~968

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from cacity/VideoHub at commit d1da59c, republished under its MIT licence (© cacity). 86 words, ~626 tokens.

Download SKILL.mdSave it as .claude/skills/videohub-beat-editor/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
videohub-beat-editor
description
根据一段音频、歌曲或参考视频的节拍,为一个长视频、多个视频或素材目录自动建立镜头候选库,生成卡点剪辑计划,并批量渲染 16:9、3:4、4:3、9:16 等多画幅成片。支持固定镜头数量、强拍切换、歌词字幕、镜头替换、封面、标题、caption、hashtags 和完整 QA。用于“按音乐卡点剪视频”“给音频和素材批量做卡点视频”“检测强拍并自动选镜头”“同一计划输出多个画幅”等任务。

VideoHub Beat Editor

把音频节拍、素材筛选和确定性渲染分开处理:

text
音频或参考视频
  -> 节拍、强拍和乐句边界
  -> 固定帧数的切点计划
视频或素材目录
  -> 全片抽帧、质量评分和相似画面去重
  -> 人工复核候选联系表
  -> 镜头编排
  -> 多画幅批量渲染
  -> 歌词字幕、封面和发布文字
  -> 完整解码与逐切点 QA

核心原则

  • 音频决定成片长度和每段帧数,视频素材只填充镜头。
  • 正式计划中的总帧数必须等于 round(audio_duration * fps)。
  • 替换镜头时只改来源和中心时间,不改变该段 frames。
  • 自动评分只生成草案;正式渲染前必须查看候选和入选联系表。
  • 避免连续使用高度相似的航拍、同一主体或同一运动方向。
  • 只有用户提供歌词、可靠字幕或明确要求转写时才烧录歌词;不要凭听感编造。
  • 不混入素材视频原声,除非用户明确要求。
  • 只处理用户有权使用的音频和视频素材。

1. 创建独立任务目录

按仓库 SOP 创建 workspace/projectNNN_project_name/,至少包含:

text
data/  docs/  outputs/  work/  logs/

输入较大时优先建立硬链接;不要复制数 GB 素材。所有计划和输出必须留在任务目录。

2. 分析音频

音频、带音轨视频均可作为输入:

powershell
python .agents/skills/videohub-beat-editor/scripts/analyze_audio.py `
  --audio "<audio_or_reference_video>" `
  --output-dir "<job_dir>" `
  --clip-count 23 `
  --fps 30

不指定 --clip-count 时可使用 --beats-per-cut 1 或 2。先试听 outputs/beat_click_preview.wav,确认点击声落在期望强拍上,再继续。

3. 建立视频候选库

支持单视频、重复 --video 或素材目录:

powershell
python .agents/skills/videohub-beat-editor/scripts/build_video_catalog.py `
  --cut-plan "<job_dir>/outputs/beat_plan.json" `
  --video "<long_video.mp4>" `
  --video-dir "<optional_material_dir>" `
  --output-dir "<job_dir>" `
  --sample-interval 20

检查:

  • outputs/all_candidates_*.jpg
  • outputs/selected_candidates.jpg
  • outputs/video_catalog.csv
  • docs/edit_plan.draft.json

把草案复制为 docs/edit_plan.json 后才能正式渲染。按构图和顺序调整 source_center_sec、focus_x、focus_y;详细字段见 plan-schema.md。

4. 批量渲染

powershell
python .agents/skills/videohub-beat-editor/scripts/render_beat_batch.py `
  --plan "<job_dir>/docs/edit_plan.json" `
  --output-dir "<job_dir>/outputs/final" `
  --ratio 16:9 `
  --ratio 3:4 `
  --ratio 4:3 `
  --subtitle "<optional_lyrics.ass>" `
  --name "beat_edit"

每个画幅独立进行中心裁切。人物或地标不在中央时,在计划中设置 focus_x、 focus_y,不要直接强裁主体。

5. 歌词、封面和发布包

  • 歌词字幕优先使用 ASS;中文和外语分两行,放在平台安全区。
  • 3:4、4:3 封面优先使用真实入选镜头,不生成与成片无关的场景。
  • 标题提供 3 个候选;caption 保持 50-100 个中文可见字符;hashtags 单独保存。
  • 发布文字必须能从成片镜头得到支持,不夸大地点、季节或拍摄方式。

6. QA

渲染脚本必须为每个输出生成 QA JSON 和 Markdown,至少确认:

  • 时长与音频相差不超过一帧。
  • 帧数、分辨率、比例、H.264/AAC 正确。
  • 完整解码无错误。
  • 所有计划切点前后存在明显画面差异。
  • 歌词三段分别抽帧检查字形、位置和遮挡。
  • 多画幅预览没有裁掉人物、地标或字幕。

QA 未通过时不得把文件标记为成品。

© cacity, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts, references) in .agents/skills/videohub-beat-editor of cacity/VideoHub.

  • SKILL.md
  • agents/openai.yaml
  • references/plan-schema.md
  • scripts/analyze_audio.py
  • scripts/build_video_catalog.py
  • scripts/render_beat_batch.py

Open the folder on GitHubat commit d1da59c

Compare with similar skills

Videohub Beat Editor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Videohub Beat Editor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Videohub Beat Editor this skillcacity/VideoHub167—~626Automated safety check: PassMIT
HyperFrames Animationheygen-com/hyperframes59k3 repos~2.1kAutomated safety check: PassApache-2.0
Stitch to Remotion Walkthrough Videosgoogle-labs-code/stitch-skills8.4k6 repos~3.2kAutomated safety check: NotesApache-2.0
Faceless Explainer Videoheygen-com/hyperframes59k3 repos~7.7kAutomated safety check: NotesApache-2.0
Video Understandcalesthio/OpenMontage65k—~841Automated safety check: PassAGPL-3.0
Video ShotcraftVincentwei1021/video-shotcraft11k—~2.6kAutomated safety check: PassApache-2.0

Similar skills

  • HyperFrames Animation

    heygen-com/hyperframes

    Collects motion rules, scene blueprints, transitions and runtime adapters for HyperFrames video compositions, with GSAP as the default animation runtime.

    59k GitHub starsUsed in 3 repos~2.1k tokens
    Media & CreativeAuto-check passed
  • Stitch to Remotion Walkthrough Videos

    google-labs-code/stitch-skills

    Official

    Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.

    8.4k GitHub starsUsed in 6 repos~3.2k tokens
    Media & CreativeAuto-check: notes
  • Faceless Explainer Video

    heygen-com/hyperframes

    Turns an article, notes or a topic brief into an explainer video whose visuals are invented per scene, built frame by frame in HyperFrames with no footage.

    59k GitHub starsUsed in 3 repos~7.7k tokens
    Media & CreativeAuto-check: notes
  • Video Understand

    calesthio/OpenMontage

    Understand video content locally using ffmpeg frame extraction and Whisper transcription.

    65k GitHub stars~841 tokensUpdated 5 days ago
    Media & CreativeAuto-check passed
  • Video Shotcraft

    Vincentwei1021/video-shotcraft

    Makes cinematic product videos with Remotion from shot recipe cards, a ready template, real page screenshots, camera moves and sound design, or builds a single animated shot.

    11k GitHub stars~2.6k tokensUpdated 3 days ago
    Media & CreativeAuto-check passed
  • Figma to HyperFrames

    heygen-com/hyperframes

    Imports Figma assets, brand tokens, components and motion into a HyperFrames video composition, using the Figma REST API with a connector or native export for shaders.

    59k GitHub starsUsed in 3 repos~4.5k tokens
    Media & CreativeAuto-check: notes

More from cacity/VideoHub

All 12 skills in this repo
  • 为 VideoHub 的影视解说、连续剧、电影、卡点视频和短视频制作可在个人主页小缩略图中辨认的封面。输入剧照、视频帧或已有底图,突出剧名、集数和简短看点,统一生成 9:16、3:4、4:3、16:9 封面与缩略图预览。用于“做封面”“修改封面”“加大集数”“生成横版和竖版封面”“沿用上一集封面模板”“制作抖音或视频号缩略图”等任务。

    167 GitHub stars~453 tokensUpdated 6 days ago
    Auto-check passed
  • 把电影、电视剧或短剧素材制作成第三者旁白主导、关键影视原声点睛的中文解说视频,并生成抖音竖版封面、标题候选、50-100 字文案、话题和完整发布包。复用 videohub-story-editor 的证据提取、剧情理解、剪辑、后置翻译、TTS…

    167 GitHub stars~1.6k tokensUpdated 6 days ago
    Auto-check passed
  • Videohub Story Editor

    cacity/VideoHub

    把长视频或已有字幕转成有完整叙事的几分钟短片。先基于原文字幕和画面证据理解、选段与重排,再对最终时间轴重新翻译和可选润色;既可输出保留原声的双语字幕版,也可把原声降到 30% 并用 MiniMax 或豆包 TTS 生成影视解说、短剧混剪、播客串讲或知识解读版。已有项目可进入本地五轨时间线继续调整切点、旁白、原声窗口、字幕、音量和转场,并按修订版本渲染。用于“把长视频讲成短故事”“按字幕自动剪辑”…

    167 GitHub stars~2.3k tokensUpdated 6 days ago
    Auto-check: notes
  • Browser Use

    cacity/VideoHub

    Automates browser interactions for web testing, form filling, screenshots, and data extraction.

    167 GitHub starsUsed in 3 repos~2.2k tokens
    Auto-check: warnings
  • Videohub Youtube

    cacity/VideoHub

    处理 YouTube、Twitter(X)、Bilibili 和本地音视频/文本的转写、字幕、翻译与总结。优先复用 src/youtubetranscriber.py 现有 CLI。

    167 GitHub stars~550 tokensUpdated 6 days ago
    Auto-check passed
  • Videohub Douyin

    cacity/VideoHub

    下载抖音单视频或用户主页作品,复用 src/douyincli.py。适合处理抖音分享链接、短链接、标准视频链接和用户主页链接。

    167 GitHub stars~213 tokensUpdated 6 days ago
    Auto-check passed

Questions about Videohub Beat Editor

What does Videohub Beat Editor do?

根据一段音频、歌曲或参考视频的节拍,为一个长视频、多个视频或素材目录自动建立镜头候选库,生成卡点剪辑计划,并批量渲染 16:9、3:4、4:3、9:16 等多画幅成片。支持固定镜头数量、强拍切换、歌词字幕、镜头替换、封面、标题、caption、hashtags 和完整 QA。用于“按音乐卡点剪视频”“给音频和素材批量做卡点视频”“检测强拍并自动选镜头”“同一计划输出多个画幅”等任务。. Videohub Beat Editor is an agent skill from cacity/VideoHub.

When should I use Videohub Beat Editor?

Videohub Beat Editor fits situations like: tasks that involve Video production.

How do I install Videohub Beat Editor in Claude Code?

Run `npx skills add cacity/VideoHub --skill videohub-beat-editor -a claude-code`. Or copy the skill folder (.agents/skills/videohub-beat-editor in cacity/VideoHub) into .claude/skills/videohub-beat-editor in your project. Claude Code loads it when a task matches its description.

How do I install Videohub Beat Editor in Codex?

Run `npx skills add cacity/VideoHub --skill videohub-beat-editor -a codex`. Or copy the skill folder (.agents/skills/videohub-beat-editor in cacity/VideoHub) into .agents/skills/videohub-beat-editor in your project. Codex loads it when a task matches its description.

Can I use Videohub Beat Editor in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cacity/VideoHub --skill videohub-beat-editor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/videohub-beat-editor, .gemini/skills/videohub-beat-editor, .github/skills/videohub-beat-editor and .opencode/skills/videohub-beat-editor in your project.

What does Videohub Beat Editor need to run?

Going by SKILL.md and its folder, Videohub Beat Editor needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Videohub Beat Editor access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Videohub Beat Editor safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Videohub Beat Editor use?

Videohub Beat Editor is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Videohub Beat Editor use?

About 626 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 342 tokens, read only when the agent opens those files.

What are the alternatives to Videohub Beat Editor?

Skills that share tags, products or a category with Videohub Beat Editor: HyperFrames Animation (heygen-com/hyperframes, 59k stars), Stitch to Remotion Walkthrough Videos (google-labs-code/stitch-skills, 8.4k stars), Faceless Explainer Video (heygen-com/hyperframes, 59k stars) and Video Understand (calesthio/OpenMontage, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Videohub Beat Editor?

cacity (a GitHub user) maintains it in cacity/VideoHub, which has 167 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 2, 2026.

Source: cacity/VideoHub on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.