Borrowing it
Nothing to install: this file belongs to cacity/VideoHub. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cacity/VideoHub/main/.agents/skills/videohub-beat-editor/SKILL.mdgit clone --depth 1 https://github.com/cacity/VideoHubWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cacity/videohub/videohub-beat-editor)<a href="https://agentmods.dev/skills/cacity/videohub/videohub-beat-editor"><img src="https://agentmods.dev/badge/skills/cacity/videohub/videohub-beat-editor.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00144 | $0.01247 |
| Opus 5 | $0.00072 | $0.00624 |
| Sonnet 5 | $0.00029 | $0.00249 |
| Haiku 4.5 | $0.00014 | $0.00125 |
Grade A, and why
videohub-beat-editor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VideoHub Beat Editor
把音频节拍、素材筛选和确定性渲染分开处理：
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：
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：
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：
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_*.jpgoutputs/selected_candidates.jpgoutputs/video_catalog.csvdocs/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
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。
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 118 lines · 144 tokens per session scan A 25ee65899fcf
videohub-beat-editor is a skill published in the GitHub repository cacity/VideoHub (143 stars, last pushed yesterday), licensed MIT. It adds 144 tokens to every session and 1,247 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
qiaomu-cut
A workflow for turning a brief video idea into a planned, sourced, edited, rendered, and checked video project.
stage-compose
Authoring knowledge for Orkas/OVS HTML video compositions -- write an index.html, drive animation from a paused timeline, declare canvas + duration, then run the VideoStudio draft gate to render an mp4. Trigger for explainer / animation / motion-graphics / caption / lower-third / title-card work, or to build a compose…
frontend-design
Aesthetic direction for OrkasVideoStudio HTML and motion-graphics compositions. Use before stage-compose writes composition-manifest.json artdirection and index.html to choose a subject-specific visual point of view, type, palette, layout signature, restrained motion, and anti-template checks.
stage-edit
Intelligent editing of real user-supplied footage—understand it with transcript/OCR/scene/silence/quality/vision evidence, then choose deterministic timeline operations or a constrained semantic AI edit. Trigger for repurpose, montage, cleanup, localization, narration, or local content changes.
stage-plan
The "ingest + plan" half of end-to-end video orchestration — ingest the user's material from evidence, then decompose intent into ONE cross-modal EDL (plan.json: edit/generate/compose/provided segments + narration/music/caption tracks + a delivery promise), validate it with ovs plan validate. Trigger when the…
gate-control
Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…