youtube-seo-optimizer
Generate complete YouTube & podcast SEO packages with live-researched keywords — titles, descriptions, tags, hashtags, chapters, and audit fixes. Use for new or underperforming content.
Profile →npx skills add sickn33/agentic-awesome-skills --skill youtube-seo-optimizer --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Generates a complete SEO package for YouTube videos or podcasts, including title, description, tags, hashtags, and chapters, plus an audit/ fixes workflow. It supports both new uploads and underperforming existing content.
How it works
- Requires web_search and web_fetch to research the target keyword and related phrases.
- Classifies the content type (video, podcast, or short) and whether the content is new or existing, selecting the appropriate mode (A-F) accordingly.
- Performs keyword research: identifies a target keyword, 3-6 related phrases, and verifies any superlatives. Uses real-time data from web sources.
- Builds the requested output (title, description, tags, hashtags, chapters, etc.) following the style and structure rules outlined in the templates.
- Runs a quality checklist before finalizing the output.
When to use it
- When a user requests a full SEO package for a new upload or an underperforming piece.
- When a user asks specifically for titles, descriptions, tags, hashtags, chapters, show notes, or audit fixes.
- When the user provides a URL or indicates live content to audit.
What it can touch
- Outputs include: SEO TITLE, DESCRIPTION, PRIMARY KEYWORDS, TAGS, HASHTAGS, CHAPTERS, THUMBNAIL TEXT, CARDS & END SCREEN, PLAYLIST SEO NOTE, PINNED COMMENT, END SCREEN SCRIPT.
- Uses web_search and web_fetch to gather live data for keyword research and resources.
Caveats
- Requires explicit input for scope (one video/podcast/short at a time).
- Will not invent data; all keyword data and recommendations must be based on live research.
- Outputs must be checked to ensure alignment with user intent and platform policies.
# YouTube & Podcast SEO Optimizer ## When to Use - User wants a title/description/tags/hashtags package for a new upload - User needs an audit of a live video or podcast episode that isn't getting views - User asks for show notes, timestamps, or podcast episode metadata - User says "SEO my video", "audit my YouTube video", "write a podcast description", "why isn't my video ranking", "generate tags", "fix my podcast SEO" - Use this for any video or podcast SEO request — new, already published, or short-form ## Overview You need web search + URL fetch for this to work. Whatever your host calls them — `web_search`/`web_fetch`, `WebSearch`/`WebFetch`, an MCP tool — use those. This skill covers 6 scenarios: 3 content types (video, podcast, short-form) × 2 states (new or underperforming). Each has its own mode below. Two rules: 1. **Every keyword is researched, not guessed.** Never generate tags or "trending" from memory. Ask the creator what they want to rank for, then search it. 2. **Match the ask.** If the user asked for just a title, deliver just a title. If they asked for the full package, ship every numbered section. Don't overwhelm them. ## How to execute this skill The sections b
- When to Use
- Overview
- How to execute this skill
- Step 0 — Check scope then classify
- Step 1 — Find the target keyword
- Step 2 — Gather what you still need (scrape first, ask last)
- Title Rules
- Formula
- Power word bank
- Rules
- Title patterns by content type
- Tags Strategy
- Hashtag Rules
- Description Structure
What does the youtube-seo-optimizer skill do?
Generate complete YouTube & podcast SEO packages with live-researched keywords — titles, descriptions, tags, hashtags, chapters, and audit fixes. Use for new or underperforming content.
How do I install it?
Run `npx skills add sickn33/agentic-awesome-skills --skill youtube-seo-optimizer --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From sickn33/agentic-awesome-skills, a repository with 44,414 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.