agentleFS
nelsonelagunarnelsonelagunar/obs-ai-workflow/skills/video-editor/SKILL.md

video-editor

Skill0 starsChanged 53 days agoMITView on GitHub

Edición multicam automatizada con selección de planos basada en subtítulos

19 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use brainstorm.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • nicolasestremSkill

    brainstorm

    Structured idea generation and solution exploration with systematic analysis.

    Also in 3 projects that use this

The file

Files
SKILL.md

Video Editor Skill

Objetivo

Editar video multicam alternando entre pantalla y webcam según el contenido hablado, generando un video final con subtítulos quemados.

Inputs

  • Proyecto con N clips en clips/
  • Cada clip tiene:
    • screen.webm - Captura de pantalla (sin audio)
    • webcam.webm - Webcam + micrófono
    • clip.srt - Subtítulos generados
    • metadata.json - Duración, resolución, timestamp

Output

  • output/final.mp4 (1920x1080, horizontal)
  • output/final.srt (subtítulos consolidados)
  • output/metadata.json (metadatos del video final)

Instrucciones para el Agente

1. Análisis de Contenido

Lee todos los archivos clip.srt y clasifica cada segmento:

  • Demo UI: Cuando el hablante describe interfaz, hace click, o muestra software
  • Diálogo directo: Cuando el hablante mira a cámara, introduce temas, o concluye
  • Transición: Silencios o cambios de tema

2. Generar EDL (Edit Decision List)

Crea un archivo JSON con la lista de cortes:

{
  "shots": [
    {
      "clip": "clip_01",
      "source": "screen",
      "start": 0.0,
      "duration": 5.2,
      "transition": "fade",
      "transition_duration": 0.2
    },
    {
      "clip": "clip_01",
      "source": "webcam",
      "start": 5.2,
      "duration": 3.1,
      "transition": "fade",
      "transition_duration": 0.2
    }
  ]
}

3. Generar Comando ffmpeg

Usa ffmpeg-python o comandos directos para:

  • Concatenar clips según EDL
  • Alternar entre screen.webm y webcam.webm
  • Insertar transiciones (fade in/out 200ms)
  • Quemar subtítulos con fuente legible
  • Normalizar audio (loudness EBU R128)

4. Ejecutar y Validar

python edit.py --project <path> --output <path>

Valida que:

  • El video output existe y es reproducible
  • Los subtítulos son legibles y están sincronizados
  • Las transiciones son suaves
  • El audio es consistente

Comandos de ejemplo

# Ejecutar edición
python skills/video-editor/edit.py --project ~/videos/mi-tutorial --output output/final.mp4

# Con opciones avanzadas
python skills/video-editor/edit.py --project ~/videos/mi-tutorial --output output/final.mp4 --font "Arial" --font-size 24

Dependencias

ffmpeg-python>=0.2.0

Notas

  • Mantener el audio original de webcam.webm como fuente única
  • Los cortes deben ser en silencios o transiciones naturales
  • Usar fuente sans-serif para subtítulos (Arial, Helvetica, Roboto)
  • Color de subtítulos: blanco con borde negro para máximo contraste

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.