Watch — ask questions about any video
Download a video with yt-dlp, extract timestamped frames and a transcript — or let Google's Gemini watch the whole video — then answer questions about it
- What
- Download a video with yt-dlp, extract timestamped frames and a transcript — or let Google's Gemini watch the whole video — then answer questions about it
- Cost
- Free
- Needs
- Python 3.10+; optional free Gemini API key (aistudio.google.com/apikey) for the cloud engine. Local engine needs ffmpeg and yt-dlp; the WhisperX fallback needs a one-time ~1.5 GB model download and 8 GB RAM.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — a video-watching skill by @bradautomates that lets an agent answer questions about any video. With the local engine it downloads the video (URL or local file) with yt-dlp, extracts auto-scaled timestamped frames with ffmpeg and a transcript from captions (or a local WhisperX / Groq / OpenAI fallback), then combines visuals and transcript as evidence. With a Gemini API key, Google's agentic video model watches the full video directly and the report relays its timestamped answer. Includes a guided first-run setup (engine choice, detail levels from transcript-only to token-burner, transcription backend), and security-conscious defaults: keys live in a local `~/.config/watch/.env` (0600 permissions), are never printed, and video content is treated as untrusted evidence, never instructions. Honest caveats: the Gemini engine sends the video to Google (local files are uploaded, then deleted after the answer); the local WhisperX path needs a one-time ~1.5 GB model download and 8 GB RAM; long clips get sparse frame coverage unless you focus a time interval. Credit to its creator. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Watch is a free Muse skill that lets an agent answer questions about any video. With the local engine it downloads the video with yt-dlp, extracts auto-scaled timestamped frames with ffmpeg and a transcript from captions, then combines visuals and transcript as evidence. With a Gemini API key, Google's agentic video model watches the full video directly.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 03ceb42Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: Python 3.10+; optional free Gemini API key (aistudio.google.com/apikey) for the cloud engine. Local engine needs ffmpeg and yt-dlp; the WhisperX fallback needs a one-time ~1.5 GB model download and 8 GB RAM. Install "Watch — ask questions about any video" for me. The agent downloads a video (URL or local file) with yt-dlp, extracts timestamped frames with ffmpeg and a transcript from captions (or WhisperX / cloud transcription), and answers questions about the video from that evidence — or, with a Gemini key, has Google's video model watch the whole video directly. Repository: https://raw.githubusercontent.com/bradautomates/claude-video/03ceb42f7fa2c4439aca01752118044baabffb8f/skills/watch/SKILL.md Pinned version: install the code at commit 03ceb42f7fa2c4439aca01752118044baabffb8f exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files, including the scripts/ folder) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "watch". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. save my Gemini API key in the vault). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
- It works with an API key or a token that you provide.
What the scan found — excerpts from the install prompt
- uses API keys or tokens — Prerequisites: Python 3.10+; optional free Gemini API key (aistudio.google.com/apikey) for the cloud engine. L · Prérequis : Python 3.10+ ; clé API Gemini gratuite optionnelle (aistudio.google.com/apikey) pour le moteur clo
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 03ceb42 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : uses API keys or tokens
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.