Agent skill

Editframe API

by shadcn-labs in shadcn-labs/framecn

JavaScript/TypeScript SDK for Editframe's video rendering API.

MITAuto-check passedMedia & Creative

Install Editframe API

skills CLI
$ npx skills add shadcn-labs/framecn --skill editframe-api -a claude-code

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

GitHub CLI
$ gh skill install shadcn-labs/framecn editframe-api --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/shadcn-labs/framecn.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/editframe-api .claude/skills/editframe-api && 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
editframe-api
GitHub stars
150
Token cost
~1.2k tokens
SKILL.md length
381 words
Files
11 (incl. references)
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

JavaScript/TypeScript SDK for Editframe's video rendering API.

  • Tasks that involve Video production
  • SKILL.md covers Quick Start, Function Index, Unified Files API and Using Files in Compositions, plus 1 more section
  • Reaches assets.editframe.com and editframe.com; needs EDITFRAME_API_KEY

What it does

Editframe API is an agent skill from shadcn-labs/framecn. JavaScript/TypeScript SDK for Editframe's video rendering API. Create renders, upload video and image files, manage assets, and sign URLs for playback.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including reference files (for example `references/authentication.md`, `references/caption-files.md` and `references/files.md`).

It sits in Media & Creative, covering Video production. It works with JavaScript and TypeScript. The repository describes itself as: Beautiful video components, built on Editframe. 100% Free, Zero config, one command setup. The licence is MIT.

When your agent uses it

  • Tasks that involve Video production

Example prompts

  • “/editframe-api”

Requirements

  • Node.js
  • A credential in EDITFRAME_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 7717708. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript and html).

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • assets.editframe.com
    • editframe.com

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • EDITFRAME_API_KEY

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

Context cost

Editframe API loads about 1.2k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 41 tokens; SKILL.md has 381 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~12k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from shadcn-labs/framecn at commit 7717708, republished under its MIT licence (© shadcn-labs). 381 words, ~1,248 tokens.

Download SKILL.mdSave it as .claude/skills/editframe-api/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
editframe-api
description
JavaScript/TypeScript SDK for Editframe's video rendering API. Create renders, upload video and image files, manage assets, and sign URLs for playback.
license
MIT
metadata.author
editframe
metadata.version
2.0

Editframe API

JavaScript/TypeScript client for Editframe's video rendering API. Render videos from HTML compositions, upload and process media files, and manage authenticated access to CDN resources.

Quick Start

typescript
import { Client, createRender, getRenderProgress, downloadRender } from "@editframe/api";

// Initialize client with API key
const client = new Client(process.env.EDITFRAME_API_KEY);

// Create a render from HTML composition
const render = await createRender(client, {
  html: `<ef-timegroup mode="contain" class="w-[1920px] h-[1080px]">
    <ef-video src="https://assets.editframe.com/bars-n-tone.mp4"></ef-video>
  </ef-timegroup>`,
  width: 1920,
  height: 1080,
  fps: 30,
});

// Poll for completion
for await (const event of await getRenderProgress(client, render.id)) {
  console.log(`Progress: ${event.progress}%`);
}

// Download the result
const response = await downloadRender(client, render.id);
const buffer = await response.arrayBuffer();

Function Index

Renders
  • createRender(client, payload) → CreateRenderResult — Create a render job from HTML composition
  • uploadRender(client, renderId, fileStream) → Promise<void> — Upload pre-rendered video file
  • getRenderProgress(client, id) → CompletionIterator — Stream render progress via SSE
  • getRenderInfo(client, id) → LookupRenderByMd5Result — Get render metadata
  • lookupRenderByMd5(client, md5) → LookupRenderByMd5Result | null — Find existing render by hash
  • downloadRender(client, id) → Response — Download completed render
Files (Unified API)
  • createFile(client, payload) → CreateFileResult — Register a file (video, image, or caption)
  • uploadFile(client, uploadDetails, fileStream) → IteratorWithPromise<UploadChunkEvent> — Upload file content with progress
  • getFileDetail(client, id) → FileDetail — Get file metadata and tracks
  • lookupFileByMd5(client, md5) → LookupFileByMd5Result | null — Find existing file by hash
  • deleteFile(client, id) → { success: boolean } — Delete a file
  • getFileProcessingProgress(client, id) → ProgressIterator — Stream processing progress for video files
  • transcribeFile(client, id, options?) → TranscribeFileResult — Start audio transcription
  • getFileTranscription(client, id) → FileTranscriptionResult | null — Get transcription status
Node.js Helpers
  • upload(client, filePath) → { file, uploadIterator } — Upload a file from disk (auto-detects type)
URL Signing
  • createURLToken(client, url) → string — Generate signed JWT for browser access to media endpoints

Unified Files API

All file types (video, image, caption) use a single set of endpoints:

EndpointMethodPurpose
/api/v1/filesPOSTCreate file record
/api/v1/files/:idGETGet file detail
/api/v1/files/:id/uploadGET/POSTCheck upload status or upload chunk
/api/v1/files/:id/deletePOSTDelete file
/api/v1/files/:id/indexGETGet fragment index (video only)
/api/v1/files/:id/tracks/:trackIdGETGet track data (video only)
/api/v1/files/:id/transcribePOSTStart transcription (video only)
/api/v1/files/:id/transcriptionGETGet transcription status
/api/v1/files/:id/progressGETStream processing progress (SSE)
/api/v1/files/md5/:md5GETLookup file by MD5 hash

The file type field determines processing behavior:

  • "video" — uploaded files are automatically processed to ISOBMFF format
  • "image" — uploaded files are immediately ready
  • "caption" — uploaded files are immediately ready
Show full SKILL.md (101 more words)Show less

Using Files in Compositions

Reference uploaded files using the file-id attribute:

html
<ef-configuration api-host="https://editframe.com">
  <ef-timegroup mode="contain" class="w-[1920px] h-[1080px]">
    <ef-video file-id="uuid-of-processed-video"></ef-video>
    <ef-image file-id="uuid-of-uploaded-image" class="w-24 h-24"></ef-image>
  </ef-timegroup>
</ef-configuration>

The file-id is a stable UUID assigned at file creation time and remains the same throughout upload, processing, and playback.

URL Signing

If your application renders Editframe compositions in a browser, you need URL signing. The browser needs authenticated access to transcode endpoints, but cannot hold your API key.

URL signing creates short-lived, scoped tokens that authorize the browser to access specific media URLs. Set up a server route that calls createURLToken, then configure <ef-configuration signingURL="/your-route"> in your frontend.

See references/url-signing.md for implementation details and integration with elements-composition and react-composition.

© shadcn-labs, 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 10 other files (references) in .agents/skills/editframe-api of shadcn-labs/framecn.

  • SKILL.md
  • references/authentication.md
  • references/caption-files.md
  • references/files.md
  • references/getting-started.md
  • references/image-files.md
  • references/media-pipeline.md
  • references/renders.md
  • references/transcription.md
  • references/unprocessed-files.md
  • references/url-signing.md

Open the folder on GitHubat commit 7717708

Compare with similar skills

Editframe API 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.

Editframe API compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Editframe API this skillshadcn-labs/framecn150—~1.2kAutomated safety check: PassMIT
Anything2explainerVincentwei1021/anything2explainer2.3k—~2.7kAutomated safety check: PassCustom licence
Remotion Motion Graphicshaidrrrry/claude-remotion-skill277—~2kAutomated safety check: PassMIT
Explainroovincentsch/explainroo489—~439Automated safety check: PassMIT
Remotion Render via inference.shHainrixz/editor-pro-max2612 repos~2kAutomated safety check: PassCustom licence
Ffmpeg MixingvargHQ/sdk341—~676Automated safety check: PassMIT

Similar skills

  • Anything2explainer

    Vincentwei1021/anything2explainer

    给一个主题,产出一条黑底 MG 风格(幕底可选星点或点阵波)、有配音字幕章节进度条的科普讲解视频(中文或英文;Remotion 代码动画;时长由用户定,常用 3–5 分钟)。内含可编译模板、图元库、配音/分镜/渲染工具、风格与动效规范、多 agent 分工协议与 QC 判据,以及一条完整样片(《RAG 与知识库》)作为质量标尺。Turn any topic into a narrated…

    2.3k GitHub stars~2.7k tokensUpdated 19 days ago
    Media & CreativeAuto-check passed
  • Remotion Motion Graphics

    haidrrrry/claude-remotion-skill

    Create and edit professional motion graphics videos with Remotion (React-based video).

    277 GitHub stars~2k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Explainroo

    vincentsch/explainroo

    Make an explainer video (MP4) with a voice-over using explainroo.

    489 GitHub stars~439 tokensUpdated 3 days ago
    Media & CreativeAuto-check passed
  • Remotion Render via inference.sh

    Hainrixz/editor-pro-max

    Renders MP4 videos from React and Remotion TSX code through the inference.sh CLI, with settings for resolution, frame rate, duration and codec.

    261 GitHub starsUsed in 2 repos~2k tokens
    Media & CreativeAuto-check passed
  • Ffmpeg Mixing

    vargHQ/sdk

    Mix, trim, and concatenate video clips with ffmpeg without audio/video desync.

    341 GitHub stars~676 tokensUpdated 6 days ago
    Media & CreativeAuto-check passed
  • Deprecate API

    remotion-dev/remotion

    Official

    Reference for how deprecation of public Remotion APIs is represented in TypeScript source and documentation.

    62k GitHub stars~529 tokensUpdated today
    Media & CreativeAuto-check passed

More from shadcn-labs/framecn

All 8 skills in this repo
  • Launch Shadcn Registry

    shadcn-labs/framecn

    Launch and promote a custom shadcn/ui registry end-to-end: validate registry.json, prepare the official shadcn-ui/ui directory PR, community directory PRs (registry.directory, shadcntemplates…

    150 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Composition

    shadcn-labs/framecn

    Create video compositions with Editframe using HTML web components or React.

    150 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Editor Gui

    shadcn-labs/framecn

    Build video editing interfaces with Editframe's GUI components.

    150 GitHub stars~832 tokensUpdated today
    Auto-check passed
  • Webhooks

    shadcn-labs/framecn

    Webhook notifications for render completion and file processing events.

    150 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Editframe CLI

    shadcn-labs/framecn

    Command-line tools for Editframe video development. An agent skill from shadcn-labs/framecn.

    150 GitHub stars~378 tokensUpdated today
    Auto-check passed
  • Editframe Create

    shadcn-labs/framecn

    Scaffold new Editframe video projects from templates. An agent skill from shadcn-labs/framecn.

    150 GitHub stars~382 tokensUpdated today
    Auto-check passed

Questions about Editframe API

What does Editframe API do?

JavaScript/TypeScript SDK for Editframe's video rendering API. Editframe API is an agent skill from shadcn-labs/framecn. JavaScript/TypeScript SDK for Editframe's video rendering API.

When should I use Editframe API?

Editframe API fits situations like: tasks that involve Video production.

How do I install Editframe API in Claude Code?

Run `npx skills add shadcn-labs/framecn --skill editframe-api -a claude-code`. Or copy the skill folder (.agents/skills/editframe-api in shadcn-labs/framecn) into .claude/skills/editframe-api in your project. Claude Code loads it when a task matches its description.

How do I install Editframe API in Codex?

Run `npx skills add shadcn-labs/framecn --skill editframe-api -a codex`. Or copy the skill folder (.agents/skills/editframe-api in shadcn-labs/framecn) into .agents/skills/editframe-api in your project. Codex loads it when a task matches its description.

Can I use Editframe API 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 shadcn-labs/framecn --skill editframe-api -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/editframe-api, .gemini/skills/editframe-api, .github/skills/editframe-api and .opencode/skills/editframe-api in your project.

What does Editframe API need to run?

Going by SKILL.md and its folder, Editframe API needs credentials named EDITFRAME_API_KEY. Our summary lists: Node.js; A credential in EDITFRAME_API_KEY.

Does Editframe API access the network?

SKILL.md names 2 domains. In commands or code: assets.editframe.com and editframe.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Editframe API 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. Review the folder before installing.

What licence does Editframe API use?

Editframe API is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Editframe API use?

About 1.2k tokens (SKILL.md is roughly 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 11k tokens, read only when the agent opens those files.

What are the alternatives to Editframe API?

Skills that share tags, products or a category with Editframe API: Anything2explainer (Vincentwei1021/anything2explainer, 2.3k stars), Remotion Motion Graphics (haidrrrry/claude-remotion-skill, 277 stars), Explainroo (vincentsch/explainroo, 489 stars) and Remotion Render via inference.sh (Hainrixz/editor-pro-max, 261 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Editframe API?

shadcn-labs (a GitHub organization) maintains it in shadcn-labs/framecn, which has 150 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 7, 2026.

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