Open Edit

veedstudio/open-edit/.claude/skills/open-edit

作者 veedstudio1d3b75b7f46280061bae5ab4cb47b9538276d8fb无许可证收录于 2026年10月9日更新于 2026年10月9日

Video work with VEED's hosted services and a CLI toolkit — word-timed transcription, cutting, background removal, AI presenters, lipsync, any fal model, sound mixing, and a Chrome renderer for HTML compositions that re-renders only what changed. Captions, edits, motion graphics, or pieces with no footage at all; hands a finished piece to VEED's editor as an editable project, and takes projects back from it. Use when the user wants video made, edited, or captioned by an agent.

仅含说明Design & Creative
AI 生成的概览

借助 VEED 托管服务和 CLI 创建与编辑视频:转写、剪辑、字幕、AI 主播、声音与 HTML 渲染。

功能
该技能指导智能体把视频作品编写为 HTML 页面,并用 OpenEdit CLI 渲染,该 CLI 封装了 VEED 的托管服务。它涵盖逐词时间戳转写、剪辑与拼接片段、背景移除、AI 主播、唇形同步、fal 模型调用、混音与音轨合成,以及把成品交给 VEED 编辑器作为可编辑项目。每个作品保存在各自的 runs 文件夹中,渲染器只重新渲染改动的片段。
适用场景
当用户希望由智能体制作、编辑或添加字幕的视频时使用,包括字幕、剪辑、动态图形,或完全没有素材的作品。也适用于用户希望把成品在 VEED 编辑器中打开继续修改的情况。
运行要求
通过 npx @veedstudio/openedit-cli 运行,需要 Node.js 和网络访问;转写、Fabric、背景移除和编辑器交接需要 VEED 登录,fal 调用计入用户自己的 fal 账户。该技能仅为说明文档,不附带脚本,但会引用配套文档 CUT.md、FABRIC.md、TRANSCRIPTION.md 和 VEED.md。

open-edit

You author the piece yourself, as an HTML page, and render it with render. OpenEdit supplies what a bare shell does not: VEED's hosted services on one login, measured tools for cutting and sound, and a renderer that re-renders only the stretch you changed. openedit below is short for npx @veedstudio/openedit-cli; every command explains its flags with --help.

Setup

Once per workspace, before the first command. WORKSPACE is the current project root, or the current directory outside a project.

npx --yes @veedstudio/openedit-cli init --dry --workspace "$WORKSPACE"npx --yes @veedstudio/openedit-cli init --workspace "$WORKSPACE"

Read the final preflight: line, not the exit code: ready — OPEN_EDIT_ROOT=… means go, and runs/ and the recorded preferences live under that root. If init prints APPROVAL REQUIRED, tell the user every exact action and wait for an explicit yes, then run it again with --auto-approve. When the final line says the user runs the install commands, --auto-approve cannot run them: give the user those commands and run init again once they are done. Never install anything machine-global without that yes, and never infer it from the render request. When a command prints update available, tell the user once; run the init --update command it names only after they say yes, and if they decline, carry on without asking again.

One folder per piece

Keep everything a piece is made of under runs/<key>/: the page, its assets, renders, audio. The code is the edit: that folder is how the user comes back later to change one scene or reuse the piece for another video, so nothing it needs lives anywhere else.

Tools

NeedCommand
A transcript with real per-word timestranscribe <video> [...] runs the provider recorded in $OPEN_EDIT_ROOT/.open-edit-prefs.json. None recorded (the command refuses and says so), "No VEED login found", or a failed run: read TRANSCRIPTION.md first
Remove, reorder or join takesread CUT.md (speech-probe, apply-edl, retime-transcript)
Join whole clips whose shapes disagreeconcat-videos (re-encodes to one canvas at 30 fps)
Look at a video, a page or a pile of imagesframes <video> --at <sec,...> --sheet (one sheet of those moments; --images for a folder of references), render --stills
Cut the subject out of its backgroundbackground-removal (the free VEED route; when it cannot run, the command stops with fal's price, and only --fal buys)
A presenter speaking a scriptFabric: read FABRIC.md first
New audio on a facelipsync
Any fal model: images, video, music, voice, effectsfal schema <model>, then fal run <model> --input <json or @file> --run runs/<key> (--batch <jobs.json> for many); local files in the input are uploaded for you
Web fonts as local filesfonts <Family> [...] --out <dir>
Real, licensed picturesstills search, stills show, stills save
One soundtrack from several piecesmix-audio runs/<key> (voice tracks duck the bed; mix-audio --help has the spec)
Sound on a render, at delivery loudnessmux-audio --video <render> --audio <source clip or built track> --out <file>
The piece in VEED's editor for the user to change, or a project they bring from itread VEED.md (veed-project, veed-pull)

Fabric, background removal, lipsync and veed-project reuse the VEED transcription login: same veed.io account, same stored token, no second sign-in. The editor hand-off's bookmarks run in the user's own VEED session in the browser. background-removal --fal needs no VEED login at all.

Render

openedit render runs/<key>/index.html --out runs/<key>/out.mp4 --fps <fps> --duration <seconds>

The canvas is the page's #stage (or [data-stage]) element, captured at its own size, else 1920x1080. --width/--height instead capture that much of the page from its top-left corner and ignore the stage. With footage, the canvas and frame rate are the source's own, and frames prints both. Pass its frameRate (such as 30000/1001) to --fps, never the decimal beside it.

  • The renderer owns time. It drives a virtual clock (performance.now, Date.now, requestAnimationFrame, timers, a seeded Math.random), sets every CSS and Web Animations animation to the frame's time and seeks GSAP's global timeline. Anything else that moves with time goes in window.__seek(t) (it may be async).
  • It waits for fonts, images and videos before the first frame, and shows each <video> at the exact frame. Keep fonts and assets as files beside the page.
  • --from <s> --to <s> re-renders only that stretch and reuses the rest. After a change, re-render what changed, not the piece.
  • --stills 0.5,2,4 --sheet <file> shows moments without a full render. --transparent gives alpha.
  • It fails loudly on a page error, a blank render or a Chrome that did not start; read the reason it prints. A load it lists as failed (a video, an image, a font) is a wrong render: fix it and re-render before delivering.
  • The output is silent: mux-audio lays the sound on (build a many-piece track first with mix-audio).

No footage

If the user attached no video, read the ask before assuming one is needed:

  • A clip is coming: wait for it.
  • A talking head from a script: Fabric, per FABRIC.md.
  • A clip from another model (anything on fal, their key and their bill): say in the same breath that captions are transcribed from the clip's speech, and most generators return silent clips.
  • No video at all: build from stills, graphics, generated imagery and audio. That is a whole run.

If it is unclear which, ask.

Money

  • VEED transcription consumes the VEED transcription credits of one workspace. On an account with several, the CLI will not pick: name the one the user chose with --workspace.
  • Fabric consumes the AI Playground credits of the workspace chosen for it; FABRIC.md has its three stops.
  • Every fal call (fal run, lipsync, background-removal --fal or --fast) bills the user's own fal account. Before the first paid call, say in one line what you will make and what it costs, and let them answer. Background removal's default route is free.
  • Report what was spent, and on which account, when you deliver.

Talking to the user

One line when you start, then the deliverable's path and a sentence or two on the result. No step-by-step progress and no internals: run keys, command names, raw tool output. Pass on in plain terms a warning about the result, such as words transcribed without timings. If you must stop, say in plain terms what is wrong on screen and what the options are.

来源与署名

来源:veedstudio/open-edit位于.claude/skills/open-edit提交1d3b75b

许可证: 无许可证

内容归原作者所有。SourceWeft 从公开仓库中收录这些内容。

举报或申请下架