mcpbeat Sign in

Canvas Capture Extension Skill for Codex

Rebuild, install, and reload the private Remotion Canvas Capture unpacked Chrome extension. Use when the extension needs to be restored after a Codex worktree was deleted, rebuilt after source changes, moved to its durable install directory, or reloaded in Chrome or Chrome Canary.

1k tokens
context cost
the whole folder, loaded on every use
3
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
55471
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/remotion-dev/remotion --skill canvas-capture-extension

What comes with it

2 233 bytes besides the instruction
agents/openai.yaml
scripts/rebuild-extension.sh

The instruction itself

3 sections, as written by the author

Canvas Capture Extension

Build the extension from packages/canvas-capture-extension, but always install

the unpacked copy outside the checkout so deleting a worktree cannot break it.

Rebuild and install

  • Locate a Remotion checkout containing

packages/canvas-capture-extension/package.json. Prefer the current checkout;

otherwise use /Users/jonathanburger/remotion.

  • Run:
   .agents/skills/canvas-capture-extension/scripts/rebuild-extension.sh \
     --repo <remotion-checkout>

The script builds with Bun and installs the four unpacked-extension files in

/Users/jonathanburger/Applications/Remotion Canvas Capture Extension.

  • Confirm that the installed directory contains manifest.json,

background.js, content.js, and receiver.js.

Reload in Chrome

  • Open chrome://extensions manually in Chrome or Chrome Canary.
  • Enable Developer mode on chrome://extensions.
  • If Remotion Canvas Capture already points to the durable directory, click

Reload.

  • If Chrome shows the deleted worktree path, remove that broken entry, choose

Load unpacked, and select:

  /Users/jonathanburger/Applications/Remotion Canvas Capture Extension

This one-time move changes the extension ID because Chrome derives unpacked

extension identity from its absolute path.

  • Keep loading future builds from the durable directory, never from a

worktree-local dist directory.

  • Enable chrome://flags/#canvas-draw-element and restart Chrome when the

experimental HTML-in-canvas API is unavailable.

Do not edit Chrome's Preferences or Secure Preferences files to move or

reload the extension, and do not automate the Chrome UI. Let the user use

Chrome's extensions page so its integrity metadata stays valid.

Other skills for the same job

different authors, same section of the catalogue
Pydicom
by christophacham
×3

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.

13k tokens scripts
Pydicom
by ComeOnOliver
×3

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.

15k tokens scripts
Remotion Best Practices
by ncklrs
×3

Best practices for Remotion - Video creation in React

19k tokens
Podcast Generation
by microsoft
vendor ×2

Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.

4k tokens scripts
Remotion Best Practices
by ComeOnOliver
×2

Best practices for Remotion - Video creation in React

23k tokens
Remotion To Hyperframes
by aiskillstore
×1

Port an existing Remotion (React) composition''s source to HyperFrames HTML. Use ONLY on an explicit ask to port/convert/migrate/translate a Remotion source — one-way, Remotion-only. A passing Remotion mention, reference-only code, or "make something like my Remotion video" is a fresh build (/general-video). Unclear → /hyperframes.

88k tokens scripts
Gemini API Dev
by lingxling
×1

Use this skill when building applications with Gemini API hosted models, including Gemini and Gemma 4, working with multimodal content (text, images, audio, video), implementing function calling, using structured outputs, or needing current model specifications. Covers SDK usage...

2k tokens
Github Issue Creator
by lingxling
×1

Turn error logs, screenshots, voice notes, and rough bug reports into crisp, developer-ready GitHub issues with repro steps, impact, and evidence.

1k tokens

How to use it

Copy the folder

Take remotion-dev/canvas-capture-extension from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.