From bd0a116399af1b35aeeb9704ac2d516c249ede79 Mon Sep 17 00:00:00 2001
From: vitya <vitya.kuznetsov@gmail.com>
Date: Wed, 20 May 2026 09:27:21 +0300
Subject: [PATCH] feat(skills): add using-yt-tools v0.1.0 (promoted from
 .workshop/.brainstorm/yt-tools.md)

---
 skills/using-yt-tools/SKILL.md | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)
 create mode 100644 skills/using-yt-tools/SKILL.md

diff --git a/skills/using-yt-tools/SKILL.md b/skills/using-yt-tools/SKILL.md
new file mode 100644
index 0000000..3664f02
--- /dev/null
+++ b/skills/using-yt-tools/SKILL.md
@@ -0,0 +1,33 @@
+---
+name: using-yt-tools
+version: 0.1.0
+description: Use when the agent needs to "watch" a YouTube video iteratively — fetch a clean-markdown transcript with [mm:ss] anchors, decide which moments matter, then pull only those frames as JPGs for vision-reading via Read. Triggers on "транскрипт видео", "расшифровка YouTube", "что в этом ролике", "о чём ролик", "покажи кадр на N", "посмотри момент N", "что показано в видео на N", "watch this video", "video summary", "youtube transcript", or any youtube.com URL where WebFetch can't reach the actual content. Wraps yt-dlp + youtube-transcript-api + PySceneDetect + ffmpeg via CLI in `~/projects/.common/lib/yt-tools/`. Skip for non-YouTube videos (Vimeo/Twitch/local mp4), audio-only podcasts (no STT here), or pure-download workflows (use yt-dlp directly).
+---
+
+# using-yt-tools
+
+Iterative-watching YouTube для агента: clean-markdown транскрипт с `[mm:ss]`-якорями → агент решает, какие моменты интересны → targeted frame extraction по таймкодам → агент видит кадры через `Read`.
+
+## When to use
+
+<пусто, дописывается во втором проходе>
+
+## Inputs
+
+<пусто>
+
+## Steps
+
+<пусто>
+
+## Failure modes
+
+<пусто>
+
+## Side effects
+
+<пусто>
+
+## What NOT to do
+
+<пусто>