What it does
Give Claude the ability to watch any video — scene-change frames + transcript + a structured report, with a 0-10s hook microscope and optional Obsidian auto-save.
- Connects Instruction files the AI reads, with steps that call an outside service
- Account or key Some steps need a key for Groq, OpenAI (per the README)
- Category Otros
Para autores: añade una insignia a tu README
Si lo creaste tú, pega este código en tu README. La insignia enlaza a esta página.
[](https://mcp.popnx.com/en/skills/taoufik123-collab-claude-watch)Skills parecidas
Mismo tipo de trabajo, ordenadas como la lista de Skills
| Este claude-watch | llmfit | claude-video | VideoCaptioner | claude-cookbooks | |
|---|---|---|---|---|---|
| Autor | taoufik123-collab | AlexsJones | bradautomates | WEIFENG2333 | anthropics |
| Skills | 1 | 1 | 1 | 1 | 4 |
| Estrellas de GitHub | 1201 | 39.096 | 21.249 | 16.577 | 54.867 |
| Último cambio de código | 24 jul 2026 | 18 nov 2026 | 25 sept 2026 | 12 sept 2026 | 17 nov 2026 |
| Licencia | MIT | MIT | MIT | GPL-3.0 | MIT |
1 skills (conjuntos de instrucciones) de taoufik123-collab que la IA lee y sigue · no es un MCP server
En qué se diferencia un Skill de MCP
MCP = las manos
Conecta la IA a un servicio o dato externo, como leer Notion o crear una factura. Necesita un programa o servidor en marcha.
Skill = el manual
Un archivo de texto que enseña a la IA cómo hacer una tarea. No se conecta a nada.
A veces se parecen: algunas Skills ejecutan scripts que llaman herramientas y algunos MCP solo envían conocimiento. Empieza por la tarea que quieres hacer.
Funciona con
Claude CodeClaude (เว็บ/แอป)Codex
Según el README del autor y las carpetas del repo
Instalar
Is it safe?
- Who made it
GitHub account taoufik123-collab (person), 1 years old
- Use and upkeep
★ 1201 stars · code last changed 24 jul 2026
- Any scripts?
15 scripts that can run on a computer: hooks/scripts/check-setup.sh, scripts/build-skill.sh, scripts/download.py, scripts/frames.py and 11 more
- Uses the internet?
Scripts that go online: scripts/whisper.py
- Changes machine-wide settings?
Installing the maker’s way adds hooks that run without you asking: run every time a chat starts · Installed as a plugin (/plugin) it will run every time a chat starts in every project
Checked automatically from the repo files at commit 7711231 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
Primero: ¿qué IA usas?
Elige tu app y esta página mostrará solo cómo instalarlo en ella
Option 1Upload to claude.ai (web and app)
Uploading to claude.ai would fail: the description is over 200 characters (402). Use "Let the AI install it" instead
Option 1Deja que Claude Code lo instale
Copia esta frase y pégala en un chat de Claude Code
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Vuelve a abrir Claude Code y escribe /claude-watch, o pide una tarea relacionada y Claude lo usará
Checked against official docs 12 nov 2026 · Source: code.claude.com
For Terminal users
Un Skill son instrucciones que la IA seguirá. Lee los archivos antes de instalar e instala solo de autores de confianza.
La forma que recomienda el autor
/plugin marketplace add taoufik123-collab/claude-watch
/plugin install watch@claude-watchCopiado del README del autor; descarga y ejecuta su código
Abre la Terminal
Mac: pulsa Command+Espacio y escribe Terminal · Windows: el comando no funciona en PowerShell; usa «Que la IA lo instale» arriba
Copia la carpeta del skill a ~/.claude/skills
Descarga el repo a una carpeta temporal y copia solo las carpetas con SKILL.md
git clone --depth 1 https://github.com/taoufik123-collab/claude-watch.git /tmp/popnx-skill-taoufik123-collab-claude-watch-7711231 && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-taoufik123-collab-claude-watch-7711231/.' ~/.claude/skills/claude-watchVuelve a abrir Claude Code y escribe /claude-watch, o pide una tarea relacionada y Claude lo usará
App de escritorio de ChatGPT
La app de escritorio de ChatGPT incluye Codex, y Codex lee las skills de la carpeta ~/.agents/skills
Option 1Deja que ChatGPT lo instale
Abre Codex en la app de escritorio de ChatGPT y pega esta frase en el chat
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Option 2Coloca la carpeta tú mismo
Coloca la carpeta watch en ~/.agents/skills/watch
~ es tu carpeta de inicio ($HOME)
For Terminal users
Un Skill son instrucciones que la IA seguirá. Lee los archivos antes de instalar e instala solo de autores de confianza.
Abre la Terminal
Mac: pulsa Command+Espacio y escribe Terminal · Windows: el comando no funciona en PowerShell; usa «Que la IA lo instale» arriba
Copia la carpeta del skill a ~/.agents/skills
Descarga el repo a una carpeta temporal y copia solo las carpetas con SKILL.md
git clone --depth 1 https://github.com/taoufik123-collab/claude-watch.git /tmp/popnx-skill-taoufik123-collab-claude-watch-7711231 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-taoufik123-collab-claude-watch-7711231/.' ~/.agents/skills/claude-watch
Después de instalar
- App de escritorio de ChatGPT: abre Skills en la barra lateral para ver que la skill está
- Para usarla: en ChatGPT escribe @ y elige la skill · en Codex CLI o la extensión del IDE ejecuta /skills o escribe $ y el nombre de la skill
- Codex detecta solo las skills recién instaladas; si una no aparece, reinicia Codex
Checked against official docs 15 nov 2026 · Source: learn.chatgpt.com
ChatGPT en la web y el móvil
Las skills que instalas tú no funcionan aquí; solo las que vienen con un plugin del directorio
Para usar esta skill con ChatGPT, usa la app de escritorio de ChatGPT como se indica arriba
Checked against official docs 15 nov 2026 · Source: learn.chatgpt.com
Option 1Deja que Codex lo instale
Copia esta frase y pégala en un chat de Codex · Sirve en Codex dentro de la app de escritorio de ChatGPT, en Codex CLI y en la extensión del IDE
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex detecta solo las skills recién instaladas; si una no aparece, reinicia Codex · Para usarla: en ChatGPT escribe @ y elige la skill · en Codex CLI o la extensión del IDE ejecuta /skills o escribe $ y el nombre de la skill
Checked against official docs 15 nov 2026 · Source: learn.chatgpt.com
For Terminal users
Un Skill son instrucciones que la IA seguirá. Lee los archivos antes de instalar e instala solo de autores de confianza.
Abre la Terminal
Mac: pulsa Command+Espacio y escribe Terminal · Windows: el comando no funciona en PowerShell; usa «Que la IA lo instale» arriba
Copia la carpeta del skill a ~/.agents/skills
Descarga el repo a una carpeta temporal y copia solo las carpetas con SKILL.md
git clone --depth 1 https://github.com/taoufik123-collab/claude-watch.git /tmp/popnx-skill-taoufik123-collab-claude-watch-7711231 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-taoufik123-collab-claude-watch-7711231/.' ~/.agents/skills/claude-watchVuelve a abrir Codex y pide una tarea relacionada; Codex mostrará el skill
Option 1Deja que Cursor lo instale
Copia esta frase y pégala en un chat de Cursor
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
En el chat Agent de Cursor escribe / y elige claude-watch
Checked against official docs 12 nov 2026 · Source: cursor.com
For Terminal users
Un Skill son instrucciones que la IA seguirá. Lee los archivos antes de instalar e instala solo de autores de confianza.
Abre la Terminal
Mac: pulsa Command+Espacio y escribe Terminal · Windows: el comando no funciona en PowerShell; usa «Que la IA lo instale» arriba
Copia la carpeta del skill a ~/.cursor/skills
Descarga el repo a una carpeta temporal y copia solo las carpetas con SKILL.md
git clone --depth 1 https://github.com/taoufik123-collab/claude-watch.git /tmp/popnx-skill-taoufik123-collab-claude-watch-7711231 && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-taoufik123-collab-claude-watch-7711231/.' ~/.cursor/skills/claude-watchEn el chat Agent de Cursor escribe / y elige claude-watch
Option 1Let the AI install it
Para otras apps que leen skills. La frase incluye las rutas de Claude Code, Codex y Cursor para que la IA elija la de tu app · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 12 nov 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
For Terminal users
Otras apps con Agent Skills (como Gemini CLI o GitHub Copilot) usan otras carpetas. Mira la guía de esa app y copia allí la carpeta con el SKILL.md.
Carpetas de skills comprobadas con las guías oficiales de Claude Code, Codex y Cursor el 11 nov 2026
✓ Comandos revisados el 19 nov 2026
Ver el SKILL.md original
El texto siguiente viene del repo del autor, no de PopNx MCP
Se muestran los primeros 8000 caracteres · Abrir el archivo completo en GitHub
---
name: watch
description: Watch a video (URL or local path) like an editor. Extracts scene-change frames, pacing metrics (cuts/min, shot length), and a dense 0-10s hook microscope; pulls transcript from captions or Whisper. Produces an ingest-ready `report.md` and, after answering the user, optionally auto-ingests the analysis into your Obsidian vault (configurable via `$WATCH_VAULT_DIR`) — tied to *why* the user watched it.
argument-hint: "<video-url-or-path> [why you're watching it]"
allowed-tools: Bash, Read, AskUserQuestion
homepage: https://github.com/taoufik123-collab/claude-watch
repository: https://github.com/taoufik123-collab/claude-watch
author: taoufik
license: MIT
user-invocable: true
---
# /watch — Claude watches a video
You don't have a video input; this skill gives you one. A Python script downloads the video, extracts frames as JPEGs (one per detected shot via scene-change), gets a timestamped transcript (native captions first, then Whisper API as fallback), runs editorial pacing metrics, and microscopes the first 10 seconds at higher density. You then `Read` each frame path to see the images, combine them with the transcript to answer the user, fill the structured `report.md`, and offer to ingest the analysis into Taoufik's Second Brain.
## What v2 does differently
- **Scene-change frame sampling** — one frame per detected shot instead of uniform ticks. Cuts the frame budget on long videos while capturing every transition.
- **Editorial pacing metrics** — cuts/min, mean shot length, motion (when available). Lets you reason about pacing the way an editor does.
- **Hook microscope** — first 10s auto-runs at 2 fps + word-level Whisper. The single most leveraged 10 seconds of any video deserves dense treatment.
- **Structured `report.md`** — every watch emits an ingest-shaped report at `<workdir>/report.md` with TL;DR, key moments, hook breakdown, editorial profile, quotable moments, entities, concepts, and transcript. Narrative sections are emitted as `<!-- pending Claude fill: ... -->` markers — you fill them in before offering ingest.
- **Step 4.5 — Ingest gate** — after answering the user, you ask once: "Want to ingest this into your Obsidian vault?" If yes, and a vault is detected, you read `$VAULT_DIR/CLAUDE.md` (if it exists) and run that vault's Ingest op against the report.
None of the above add new dependencies — pure ffmpeg + stdlib + the existing Whisper backend.
## Configuration — finding the user's Obsidian vault
Steps 4.4 and 4.5 stage the report inside an Obsidian vault so the user can read it where they read everything else. Resolve the vault directory in this order — first hit wins, and the result is what `$VAULT_DIR` refers to everywhere below:
1. **`$WATCH_VAULT_DIR` env var** — if set and the path exists, use it. This is the user-controlled override.
2. **`~/Second brain/`** — if it exists as a directory.
3. **`~/Documents/Obsidian/`** — if it exists as a directory.
4. **`~/Obsidian/`** — if it exists as a directory.
5. **None found** — skip Steps 4.4 and 4.5 entirely. Print one line in chat so the user knows what happened: `📄 Report (no vault detected): <workdir>/report.md`. Suggest they set `WATCH_VAULT_DIR` if they want auto-ingest.
A quick way to resolve it in bash inside the skill:
```bash
VAULT_DIR="${WATCH_VAULT_DIR:-}"
if [ -z "$VAULT_DIR" ] || [ ! -d "$VAULT_DIR" ]; then
for candidate in "$HOME/Second brain" "$HOME/Documents/Obsidian" "$HOME/Obsidian"; do
if [ -d "$candidate" ]; then VAULT_DIR="$candidate"; break; fi
done
fi
```
The vault's URL-name (for the `obsidian://` URL scheme in Step 4.4) is the final path component — e.g. `$HOME/Second brain` → `Second brain`. URL-encode spaces as `%20`.
## Step 0 — Setup preflight (runs every `/watch` invocation, silent on success)
**Python interpreter:** every `python3 ...` command in this skill is for macOS/Linux. On **Windows**, substitute `python` — the `python3` command on Windows is the Microsoft Store stub and will not run the script.
Before every `/watch` run, verify that dependencies and an API key are in place:
```bash
python3 "${CLAUDE_SKILL_DIR}/scripts/setup.py" --check
```
This is a <100ms lookup. On exit 0, the script emits **nothing** — proceed to Step 1 without comment. **Do NOT announce "setup is complete" to the user** — they don't need a status message on every turn. The only acceptable user-visible output from Step 0 is when remediation is required.
On non-zero exit, follow the table:
| Exit | Meaning | Action |
|------|---------|--------|
| `2` | Missing binaries (`ffmpeg` / `ffprobe` / `yt-dlp`) | Run installer |
| `3` | No Whisper API key | Run installer to scaffold `.env`, then ask user for a key |
| `4` | Both missing | Run installer, then ask for a key |
The installer is idempotent — safe to re-run:
```bash
python3 "${CLAUDE_SKILL_DIR}/scripts/setup.py"
```
On macOS with Homebrew, it auto-installs `ffmpeg` and `yt-dlp`. On Linux/Windows, it prints the exact install commands for the user to run. It scaffolds `~/.config/watch/.env` with commented placeholders at `0600` perms, and writes `SETUP_COMPLETE=true` once deps + a key are in place so the next session knows this user has already been through the wizard.
**If an API key is still missing after install:** use `AskUserQuestion` to ask the user whether they have a Groq API key (preferred — cheaper, faster) or an OpenAI key. Then write it into `~/.config/watch/.env` — set the matching `GROQ_API_KEY=...` or `OPENAI_API_KEY=...` line. If they don't want to set up Whisper, proceed with `--no-whisper` and tell them videos without native captions will come back frames-only.
**Structured mode (optional):** `python3 "${CLAUDE_SKILL_DIR}/scripts/setup.py" --json` emits `{status, first_run, missing_binaries, whisper_backend, has_api_key, config_file, platform}` where `status` is one of `ready | needs_install | needs_key | needs_install_and_key`. Use this when you need to branch on specifics (e.g. "is this the user's very first run?" → `first_run: true`).
Within a single session, you can skip Step 0 on follow-up `/watch` calls — once `--check` returned 0, nothing about the environment changes between turns.
## When to use
- User pastes a video URL (YouTube, Vimeo, X, TikTok, Twitch clip, most yt-dlp-supported sites) and asks about it.
- User points at a local video file (`.mp4`, `.mov`, `.mkv`, `.webm`, etc.) and asks about it.
- User types `/watch <url-or-path> [question]`.
## Recommended limits
- **Best accuracy: videos under 10 minutes.** Frame coverage scales inversely with duration.
- **Hard caps: 100 frames total and 2 fps.** Token cost grows with frame count, so the script targets a frame budget by duration (and never exceeds 2 fps even when the budget would imply more):
- ≤30s → ~1-2 fps (up to 30 frames)
- 30s-1min → ~40 frames
- 1-3min → ~60 frames
- 3-10min → ~80 frames
- \>10min → 100 frames, sparsely spaced (warning printed)
- If the user hands you a long video, consider asking whether they want a specific section before burning tokens on a sparse scan.
## How to invoke
**Step 1 — parse the user input.** Separate the video source from any question the user asked. The question (or the user's prior stated interest) IS the intent — pass it to the script via `--intent`. Example: `/watch https://youtu.be/abc what's the hook pattern?` → source = `https://youtu.be/abc`, intent = `what's the hook pattern?`. If no question is given, use a brief inferred intent ("general summary") so the report's TL;DR has a lens. The intent shapes how the report's TL;DR and entity/concept sections get filled at Step 4 — same video with intent "pricing tactics" vs "editing style" produces different reports.
**Step 2 — run the watch script.** Pass the source verbatim. Do not shell-escape it yourself beyond normal quoting:
```bash
python3 "${CLAUDE_SKILL_DIR}/scripts/watch.py" "<source>" --intent "<intent string>"
```
Pass `--intent` whenever you have any signConversación
Pregunta, comparte un consejo o avisa de que no funciona. Ordenado por lo que la gente marcó como útil.
Aún no hay publicaciones. Sé la primera persona en preguntar o compartir.
Lo publicado aquí lo escriben usuarios, no el equipo de PopNx.
Desde GitHub
- Estrellas en GitHub
- 1201
- Autor
- taoufik123-collab
- Licencia
- MIT
- Último cambio de código
- 24 jul 2026
- Archivos SKILL.md del repo (con traducciones y plantillas)
- 1