Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Transcribe and analyze a video v1.0.0

Use this resource to transcribe and summarize a video or recording

New

  • 430 downloads
  • 146 likes
  • 108 saves
  • Gemini key optional

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install video-transcript-analysis

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent fetches the video (YouTube, Loom, Vimeo, Zoom or a local file), then transcribes it with the platform's captions or local Whisper. Depending on the depth you choose, it extracts frames, analyzes key moments and writes a summary with decisions, action items and quotes. It warns you before spending on a long video.

Mostly picked by

Updated November 2, 2026

Structured video summary with timestamped key moments, action items and quotes.

Details

Works in
Install guides
Generates with
Your agent's model
Uses
  • Gemini
  • yt-dlp
  • ffmpeg
  • Whisper (mlx-whisper or faster-whisper)
Licence
MIT

Similar resources

View all
  • Free

    Skills

    Knowledge wiki setup

    • 418418 downloads
    • 129129 likes
    • 161161 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
  • Free

    Skills

    Wiki health check

    • 552552 downloads
    • 202202 likes
    • 127127 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
  • Free

    Skills

    Job search agent

    • 597597 downloads
    • 224224 likes
    • 126126 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
  • Free

    Skills

    Ask your wiki

    • 374374 downloads
    • 131131 likes
    • 214214 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
  • Free

    Skills

    Wiki source ingestion

    • 315315 downloads
    • 230230 likes
    • 246246 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
  • Free

    Skills

    Wiki auditor agent

    • 556556 downloads
    • 205205 likes
    • 192192 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
  • Free

    Skills

    UX research assistant

    • 598598 downloads
    • 142142 likes
    • 236236 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more
  • Free

    Skills

    Wiki ingestion agent

    • 437437 downloads
    • 162162 likes
    • 191191 saves
    Works with
    • Claude Code
    • Codex
    • Cursor
    • and 3 more

What you get

  • SKILL.md: the ten steps, from parsing the input to the report
  • The three depth modes, engine selection and frame cadences
  • A summary template and an error-handling table

Good fit for

  • Summarizing a YouTube video or webinar for research
  • Finding the key moments of a client call recording
  • Pulling quotes from a podcast or conference talk

Not for

  • Editing or publishing a video
  • Reading a private or protected video
  • A machine with no command-line tools installed

Tags

  • video
  • transcription
  • summary
  • whisper
  • youtube

About

You say

"Watch this YouTube video in visual mode and give me a summary with key moments and quotes."

Structured video summary with timestamped key moments, action items and quotes.

Skill published by coreyhaines31 under the MIT license.

Show more

Prerequisites

You bring
The video link or file and The depth level you want
Dependencies
yt-dlp, ffmpeg, and Whisper (mlx-whisper or faster-whisper)
External costs
Optional Gemini API key for multimodal mode (billed by video length) Billed by the provider, on your account.

How to use it

  1. Place the skill folder in your agent's skills folder.
  2. Give the link or file and pick the depth: transcript, visual or multimodal.
  3. Review the summary and the files saved in the working folder.

Content preview

Files

  • LICENSE1 KB
  • NOTICE-PALATEKIT.md0.4 KB
  • SKILL.md15.1 KB

Origin and licence

Modified by PalateKit

Author
coreyhaines31
Source
github.com/coreyhaines31/makerskills/tree/ea7dd78515839ff11fc24e79ba0c53db2d5fff6c/skills/watch-video
Licence
MIT

Notice

Version modifiée de « watch-video » (coreyhaines31, MIT) : traduction française et fiche par PalateKit.

User reviews

–

No ratings yet

Loading reviews…

Delete your review?

Your rating and comment will be removed from the page.

Frequently asked questions

Which tools do I need to install?

yt-dlp and ffmpeg, plus Whisper (mlx-whisper or faster-whisper) to transcribe locally. A Gemini key is only useful for multimodal mode.

The skill mentions other skills (social-fetch, second-brain, decide). Are they required?

No, they are optional pointers. Saving to a second brain is offered, never imposed.