Add a new sound effect to @remotion/sfx
npx skills add https://github.com/remotion-dev/remotion --skill add-sfx
Sound effects must first be added to the remotion.media package.
Then it can be deployed using bun run build. The .env may be missing if we are in a worktree, but on the main non-worktree branch it should be present.
The source of truth is generate.ts in that repo. A sound effect must exist there before it can be added to @remotion/sfx.
Sound effects must be:
remotion.media repo (must be done first)In the remotion-dev/remotion.media repo:
soundEffects array in generate.ts: {
fileName: "my-sound.wav",
attribution:
"Description by Author -- https://source-url -- License: Creative Commons 0",
},
bun generate.ts to copy it to files/ and regenerate variants.jsonpackages/sfx/src/index.tsUse camelCase for the variable name. Avoid JavaScript reserved words (e.g. use uiSwitch not switch).
export const mySound = 'https://remotion.media/my-sound.wav';
packages/docs/docs/sfx/<name>.mdxFollow the pattern of existing pages (e.g. whip.mdx). Include:
image, title (camelCase export name), crumb: '@remotion/sfx'<AvailableFrom> tag with the next release version<PlayButton> import and usage@remotion/media's <Audio> componentafinfo on macOS to get duration/format)Open this file on remotion.dev/convertpackages/docs/sidebars.ts — add 'sfx/<name>' to the @remotion/sfx category itemspackages/docs/docs/sfx/table-of-contents.tsx — add a <TOCItem> with a <PlayButton size={32}>After the sound is added to packages/remotion-media and exported from packages/sfx/src/index.ts, regenerate the waveform samples used by the docs:
bun packages/docs/generate-sfx-waveforms.ts
This uses ffmpeg to sample every exported sound effect into around 2000 waveform samples and updates packages/docs/components/sfx-demos/sfx-waveforms.ts.
Add the new URL to the list in packages/skills/skills/remotion-markup/sfx.md.
cd packages/sfx && bun run make
| File name | Export name |
| --------------- | -------------------------- |
| my-sound.wav | mySound |
| switch.wav | uiSwitch (reserved word) |
| page-turn.wav | pageTurn |
Use the current version from packages/core/src/version.ts.
For docs <AvailableFrom>, increment the patch version by 1.
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take remotion-dev/add-sfx from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
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.