sk-render — Claude Code skill for video rendering
The sk-render Claude Code skill renders short videos to MP4, normalizes audio, and prepares the file for upload. It activates for render and export requests, loudness fixes, or reports of broken output.
MIT ★ 204 updated 2026-11-09
npx skills add howznguyen/shorts-kit --skill sk-render -a claude-codeWhat sk-render does
The skill uses Remotion to render a video, adjusts its loudness, then encodes the MP4 for upload with yuv420p, limited range, BT.709 tags, and 48 kHz audio. It checks duration and stream details with ffprobe, and extracts frames from the rendered file for visual inspection.
Before rendering, bun run lint <id> and bun run check must pass, the stills must be reviewed, and voice.json must be newer than narration.json. The workflow uses bun, ffmpeg, and ffprobe; if the voice file is older, run bun run tts <id> first. Outputs stay under out/<id>/. Loudness is measured again after encoding because that step changes the audio.
What it helps with
- render a short video to MP4
- normalize voice and music loudness
- encode a video to the upload specification
- check duration, colour tags, and audio streams
Example prompts for the agent
- Render the short video with ID
demoand inspect the final MP4. - Fix the audio level for video
demo, then prepare its upload file. - Check why the final
demofile is truncated or will not play.
How to install sk-render
1Skills CLI (Vercel)
npx skills add howznguyen/shorts-kit --skill sk-render -a claude-code2Manually: put the files in place
~/.claude/skills/sk-render/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/sk-render/
1Skills CLI (Vercel)
npx skills add howznguyen/shorts-kit --skill sk-render -a codex2Manually: put the files in place
.agents/skills/sk-render/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add howznguyen/shorts-kit --skill sk-render -a cursor2Manually: put the files in place
.cursor/skills/sk-render/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install howznguyen/shorts-kit .claude/skills/sk-render2Manually: put the files in place
.github/skills/sk-render/SKILL.md1Skills CLI (Vercel)
npx skills add howznguyen/shorts-kit --skill sk-render -a gemini-cli2Platform CLI
gemini skills install https://github.com/howznguyen/shorts-kit --path .claude/skills/sk-renderManually: put the files in place
.devin/skills/sk-render/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about sk-render
How do I install sk-render in Claude Code?
Run npx skills add howznguyen/shorts-kit --skill sk-render -a claude-code. The skill file is at ~/.claude/skills/sk-render/SKILL.md.
What does sk-render do?
It renders video with Remotion, normalizes loudness, and encodes an upload-ready MP4. It also checks duration, frames, video settings, and audio.
What does sk-render need to run?
It uses bun, ffmpeg, and ffprobe, along with current voice.json and narration.json files. bun run lint <id> and bun run check must pass before rendering.
Source text
SKILL.md · MIT
---
name: sk-render
description: Renders a short to mp4 with Remotion, normalises loudness, and re-encodes it to the platform upload spec (yuv420p limited range, BT.709 tags, 48 kHz audio, faststart), then verifies each file with ffprobe and by looking at frames. Use when the user says "render the video", "export it", "make the final mp4", "fix the loudness", "it's too quiet", "colours look washed out after upload", "the file won't play", or reports a truncated or broken output. Steps 10, 12 and 13 of sk-pipeline.
---
# sk-render: render, normalize, encode
**Announce:** "Using sk-render for <id>."
Rules: §8 audio (`docs/soul/06-audio.md`), §11 encode spec
(`docs/soul/08-cover-and-handoff.md`), §13 files. The § wins over this file.
## Before rendering
- `bun run lint <id>` 0 errors, `bun run check` clean, stills reviewed (`sk-scene`).
- `voice.json` is newer than `narration.json`; otherwise run `bun run tts <id>` first.
## Steps
1. **Render:**
```bash
bun run render <id> # → out/<id>/<id>.mp4
```
Remotion bundles the source when the render starts. Editing files during a
render changes nothing in that render; if a fix is missing from the output,
compare the file's modification time with the render start before debugging code.
2. **Check the render is whole.** Exit 0 is not proof. Duration should match
`voice.json` duration plus `outroHold`:
```bash
ffprobe -v error -show_entries format=duration -of default=nw=1 out/<id>/<id>.mp4
```
3. **Look at frames from the mp4 itself**, not from the studio: the first frame,
a frame per scene, the last frame.
```bash
ffmpeg -v error -ss <seconds> -i out/<id>/<id>.mp4 -frames:v 1 out/<id>/check-<seconds>.png
```
Open them. Delete the `check-*.png` files when done.
4. **Normalize loudness:**
```bash
bun run normalize <id> # → out/<id>/<id>-loud.mp4, target loudnessLUFS (default -13)
```
Then listen: music must stay below the voice by at least `musicUnderVoiceDb`
(§8), fade to zero, and the last 3 to 4 seconds hold the final frame.
5. **Encode for upload:**
```bash
bun run encode <id> # → out/<id>/<id>-upload.mp4
```
Why this step exists: Remotion's default output can be full-range `yuvj420p`
with an unusual sample rate and no faststart. Platforms re-encode assuming
limited range, so colour comes out crushed or washed out, and nothing errors.
6. **Verify the upload file:**
```bash
ffprobe -v error -select_streams v:0 \
-show_entries stream=pix_fmt,color_range,color_primaries,color_transfer,color_space \
-of default=nw=1 out/<id>/<id>-upload.mp4
ffprobe -v error -select_streams a:0 -show_entries stream=sample_rate \
-of default=nw=1 out/<id>/<id>-upload.mp4
```
Expect `yuv420p`, `tv`, `bt709` on all three colour axes, `48000`.
7. **Re-measure loudness on the final file**, because encoding touches audio:
```bash
ffmpeg -i out/<id>/<id>-upload.mp4 -af ebur128 -f null - 2>&1 | grep -A3 Summary
```
## Traps
- **Never pipe a long ffmpeg command into `head`.** ffmpeg gets SIGPIPE and leaves
an mp4 without a `moov` atom, still exiting 0.
- `ffmpeg -ss` *before* `-i` seeks to a keyframe; for sample-accurate audio checks
use `-af "atrim=start=A:end=B,volumedetect"`. `volumedetect` logs at info level,
so do not pass `-v error` or the numbers vanish.
- Keep every output inside `out/<id>/` (§13). No loose files at the root of `out/`.
- Render order and file names stay stable: the hand-off reads exact paths.
## Verify
- [ ] `out/<id>/<id>.mp4` duration matches the voice + outro hold
- [ ] frames pulled from the mp4 and opened
- [ ] `<id>-loud.mp4` at target loudness, no clipping, music under the voice floor
- [ ] `<id>-upload.mp4` passes the ffprobe checks above
Next: `sk-handoff` (cover can be done before or after encode).
© howznguyen · MIT · howznguyen/shorts-kit