Skip to main content
Agent skill

Experts

Maintain Remotion's experts directory and its generated assets. Use when adding, removing, or editing experts; changing experts data or portraits; rendering expert cards; or regenerating the homepage experts animation for Chrome and Safari.

Get started

Get the complete skill folder, including its scripts and reference files.

When to use this skill

Use Experts when an AI agent needs a reusable SKILL.md workflow for this job: Maintain Remotion's experts directory and its generated assets. Use when adding, removing, or editing experts; changing experts data or portraits; rendering expert cards; or regenerating the homepage experts animation for Chrome and Safari.

When not to use it

Skip Experts when the task is outside the writing category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.

How to install

Where will you use it?

Install scope
Claude Code folder setup
mkdir -p ~/.claude/skills/experts
# Save SKILL.md to ~/.claude/skills/experts/SKILL.md
  1. Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/experts/SKILL.md. For a shared project, commit the folder at .claude/skills/experts/ instead.
  2. Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
  3. For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.

Full install guide for Claude, Cursor, and Codex →

Try a starter prompt

After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.

Starter prompt
Use the Experts skill for this task: Use Experts when this documented workflow matches the task. Confirm any required inputs or files before making changes.

What supports this recommendation?

70/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.

Documentation
77/100
Practical detail
68/100
Source evidence
63/100
Source signals
70/100
Model compatibility evidence
  • claudeuntested

    No model-specific signal or recorded compatibility test was found.

  • chatgptuntested

    No model-specific signal or recorded compatibility test was found.

  • geminiuntested

    No model-specific signal or recorded compatibility test was found.

  • copilotuntested

    No model-specific signal or recorded compatibility test was found.

  • llamauntested

    No model-specific signal or recorded compatibility test was found.

  • perplexityuntested

    No model-specific signal or recorded compatibility test was found.

  • mistraluntested

    No model-specific signal or recorded compatibility test was found.

  • grokuntested

    No model-specific signal or recorded compatibility test was found.

Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.

What this skill does

# Experts

## How to update the videos

Regenerate the homepage experts animation whenever the experts shown by `packages/promo-pages/src/components/experts/experts-data.tsx` change. The `ExpertsGraphic` composition imports this array directly.

1. Render a fresh transparent ProRes 4444 master from the current branch. Never convert an existing WebM or MOV.

```bash cd packages/brand bunx remotion render ExpertsGraphic /tmp/experts-graphic-master.mov \ --codec=prores \ --prores-profile=4444 \ --pixel-format=yuva444p10le \ --image-format=png \ --timeout=120000 \ --overwrite ```

2. Verify the master reports `prores (4444)`, a `yuva...` pixel format, and `1080x1080`. Extract an alpha frame and confirm it is not fully opaque.

```bash ffmpeg -i /tmp/experts-graphic-master.mov ffmpeg -y -i /tmp/experts-graphic-master.mov \ -vf alphaextract -frames:v 1 /tmp/experts-graphic-alpha.png ```

3. Encode the transparent 540x540 Chrome WebM.

```bash ffmpeg -y -i /tmp/experts-graphic-master.mov \ -vf scale=540:540 \ -c:v libvpx \ -pix_fmt yuva420p \ -auto-alt-ref 0 \ -an /tmp/experts-graphic.webm ```

4. Encode a 540x540 ProRes intermediate and convert it to the Safari HEVC-with-alpha MP4.

```bash ffmpeg -y -i /tmp/experts-graphic-master.mov \ -vf scale=540:540 \ -c:v prores_ks \ -profile:v 4 \ -pix_fmt yuva444p10le \ -an /tmp/experts-graphic-540-prores.mov

avconvert \ --source /tmp/experts-graphic-540-prores.mov \ --preset PresetHEVCHighestQualityWithAlpha \ --output /tmp/experts-graphic.mp4 \ --replace ```

5. Use the `offload-r2` skill to upload both outputs under `homepage/` with new versioned keys. Update the URLs in the homepage consumers, including `packages/promo-pages/src/components/homepage/EvaluateRemotion.tsx`. Keep rendered binaries out of both docs and promo-pages.

6. Inspect both uploaded files. Each must be 540x540 and 60 seconds long. The Safari MP4 must report `major_brand: mp42`, `compatible_brands: isommp41mp42`, `Video: hevc (Main) (hvc1)`, and `handler_name: Core Media Video`. Confirm the public objects have the same SHA-256 hashes as their local outputs.

Do not commit rendered media. Commit the hosted URL changes.

## Expert data

The source of truth is `packages/promo-pages/src/components/experts/experts-data.tsx`. Keep portraits in both `packages/docs/static/img/freelancers` and `packages/promo-pages/public/img/freelancers`, with identical contents.

After adding or changing an expert, render their expert card from `packages/docs`:

```bash bun render-cards ```

Verify the expected `https://remotion.media/docs/generated/experts-<slug>.png` was uploaded and is publicly accessible. The command requires R2 credentials from the environment. To replace an existing card, pass `--overwrite=experts-<slug>`. Generated local PNGs are ignored.

Intended uses

  • Use Experts when this documented workflow matches the task.

Implementation notes

  • Review the source instructions and adapt inputs before running the workflow.

Try it, then tell us how it went

A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.