Youtube Advisor

Build or update a Claude Code advisor skill from any YouTube channel. Use when the user pastes a YouTube channel URL or handle, names a creator, or says "make an advisor on …", "build a skill from …", "обнови … advisor", "refresh that advisor". Triggers on bare URLs like https://youtube.com/@channel, @handles, or creator-name mentions.

10 stars 1 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add AlexanderAbramovPav/youtube-advisor --skill youtube-advisor

Manual install

git clone --depth 1 https://github.com/AlexanderAbramovPav/youtube-advisor.git /tmp/youtube-advisor
mkdir -p ~/.claude/skills
cp -r /tmp/youtube-advisor/. ~/.claude/skills/youtube-advisor

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# youtube-advisor — build a Claude Code advisor from any YouTube channel

## Two-action user contract

The user does exactly two things:

1. **Drops a channel URL/handle and a one-sentence intent in chat.**
2. **Uses the resulting `/<channel-slug>-advisor` skill** to ask questions about that channel.

**You (the AI agent) do everything in between.** Never expose `--since`, `--max`, `--out`, `bash`, or any CLI flag to the user. Never paste a shell command for the user to run. Compose every command silently, run it via Bash, and report results in plain language.

## When this skill triggers

- A YouTube channel URL, `@handle`, or playlist URL appears in the message.
- Creator name appears in a "build me an advisor on …" / "make a skill from …" / "make a YC advisor" framing.
- The user says "обнови yc-advisor", "refresh that advisor", "check for new videos".

## Workflow

### Step 1 — parse intent silently

Extract from the user's message:

- **Channel(s)** — URL, `@handle`, playlist URL, or a named creator.
  - If a creator is named without a URL, search via `yt-dlp ytsearch5:"<name>"` (or `yt-dlp --get-id ytsearch3:"<name> channel"`), then ASK the user "I found @navalr — Naval Ravikant's channel — use that one?" before continuing. Don't guess.
- **Selection hints**:
  - "last year" → `--since 2025-MM-DD` (today minus 1 year).
  - "long videos only" → `--title-exclude "shorts|#shorts"` (already default — no extra flag).

Read the full skill on GitHub

Details

Skill name: youtube-advisor
Repository: AlexanderAbramovPav/youtube-advisor
License: MIT
Repo updated: 25 October 2026

FAQ

What does the Youtube Advisor skill do?

How do I install the Youtube Advisor skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add AlexanderAbramovPav/youtube-advisor --skill youtube-advisor. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Youtube Advisor popular?

It lives in AlexanderAbramovPav/youtube-advisor, which has 10 GitHub stars and 1 forks.

Related skills

Folio

Ramakm/folio-anatomy

Build a museum-style exhibition plate that explains a technical idea - an invented scientific instrument drawn as a live, engraved isometric figure in three views (SVG, WebGL light, and a 3D bench you can turn through 360 degrees) with internal parts that really rotate and interact, with numbered specimen pins, a catalogue key, a working model behind every number, and wall texts that walk through the formula term by term. Use for explanatory figures, interactive explainers, "how does X work" visuals, or technical illustrations for docs, courses, posts and landing pages, even when the request n

Images, Video & Audio

Talking Head Video

Vibetool/talking-head-video

Turn a raw 口播 / talking-head selfie video plus its script into a finished explainer, vertical 9:16 or landscape 横屏 16:9 — synced burned-in subtitles, animated knowledge graphics in three selectable styles (darkcard 深色科技卡 default, watercolor 纸上水彩, inkline 白纸简笔; both style and orientation are confirmed with the user first), and a circular picture-in-picture avatar that shrinks the speaker to the top-left while a graphic or B-roll fills the screen during explanations. THE pipeline whenever someone has a clip of a person talking to camera and wants it "剪成成片", subtitles auto-added from a 逐字稿/脚本, th

Images, Video & Audio

Guizang Ppt Skill

alingowangxr/guizang-ppt-skill

生成横向翻页网页 PPT（单 HTML 文件），含 WebGL 背景、章节幕封、数据大字报、图片网格等模板。提供两种风格：① "电子杂志 × 电子墨水"（衬线 + 流体背景 + 暖色） ② "瑞士国际主义"（无衬线 + 网格点阵 + IKB/柠檬黄/柠檬绿/安全橙高亮）。也支持生成多平台封面（公众号 21:9、Facebook 1.91:1、Instagram 1:1/9:16、LINE 16:9、YouTube 缩图、LinkedIn 横幅等）。当用户需要制作分享 / 演讲 / 发布会风格的网页 PPT，或提到"杂志风 PPT"、"瑞士风 PPT"、"Swiss Style"、"horizontal swipe deck"、"封面"、"cover"、"Facebook 封面"、"LINE 封面"、"Instagram 封面"时使用。

Images, Video & Audio

Smart Video Editor

Fagan1024/smart-video-editor

把多段原始素材剪成一条成片——先用视觉模型看懂每段画面拍了什么、哪几秒可用，再决定取舍、顺序、时长、调色和 BGM，最后用 ffmpeg 渲染。适用于"我给你几段视频，帮我剪一条小红书/朋友圈/vlog"这类需求。当用户提供视频文件并希望剪辑、拼接、配乐、调色、转成竖屏时使用。不做 AI 生成视频。

Images, Video & Audio

Redbook Creator

BoomSky0416/redbook-creator

Use this skill when the user wants to create Xiaohongshu (小红书/RedBook) posts. Trigger phrases: 小红书创作, create redbook, 小红书, 红书, 笔记创作, 帖子创作. The user will provide images, videos, or text content. This skill analyzes the content, searches for trending Xiaohongshu posts as reference, generates post title and copy, auto-edits videos (merge, subtitles, BGM, narration), attempts auto-upload to Xiaohongshu creator platform, and generates a local preview HTML file.

Images, Video & Audio

Openclaw Genpark Video Creator

alphaparkinc/openclaw-genpark-video-creator

OpenClaw GenPark Video Creator - SMPTE timecode drop-frame/non-drop-frame converter, Ken Burns cubic Bezier camera pan/zoom trajectory solver, and multi-track EDL timeline reconciler with zero dependencies.

Images, Video & Audio

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.