Yt Channel Optimizer logo

Yt Channel Optimizer

Community
sergebulaev
yt-channel-optimizer

Audit and rewrite a YouTube channel end-to-end for 2026: name and @handle, banner (2560x1440 with the 1235x338 mobile/TV safe area), profile picture, About plus searchable keywords, trailer for non-subscribers vs featured video for subscribers, sections and playlist layout, watermark, links. Triggers on "optimize my YouTube channel", "rewrite my channel about", "fix my banner", "channel audit", "set my trailer". Converts a viewer into a subscriber. Not for writing a video title (use yt-title-optimizer).

Overview

Publishersergebulaev
Repositoryyoutube-skills
Skill nameyt-channel-optimizer
Stars
85
Forks
21
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by sergebulaev on GitHub. Read the source before you install it.

Installation

Install the Yt Channel Optimizer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/sergebulaev/youtube-skills/tree/main/skills/yt-channel-optimizer
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/sergebulaev/youtube-skills.git /tmp/youtube-skills
mkdir -p .claude/skills
cp -r /tmp/youtube-skills/skills/yt-channel-optimizer .claude/skills/yt-channel-optimizer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Yt Channel Optimizer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Yt Channel Optimizer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Yt Channel Optimizer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

YouTube Channel Optimizer

Audit the parts of a YouTube channel page against what actually converts a one-time video-viewer into a subscriber in 2026, then rewrite each part that needs it. A viewer clicks through from one video to the channel page in a moment of interest. That moment decides whether they subscribe or leave. This skill fixes the page so the answer is subscribe.

When to use

  • User pastes their channel URL or @handle and asks for an audit
  • "Rewrite my channel About", "fix my banner", "set my trailer"
  • A channel with real videos but a default or empty channel page
  • Any of: "optimize my YouTube channel", "channel audit", "what trailer should I set"

Not for writing a single video's title (use yt-title-optimizer), the video description (use yt-description-writer), or the thumbnail overlay (use yt-thumbnail-brief).

Input

  • Channel URL / @handle (or a screenshot of the channel home tab, signed out)
  • Goal: more subscribers / more views / authority / sales - the trailer, About CTA, and section order change by goal
  • Optional: their best-performing videos, to pick a trailer and featured video
  • Note whether the channel already has 3+ playlists to lay out

Output

  1. Scorecard (parts, pass / needs-work / fail)
  2. Priority fixes ranked by impact (trailer, banner, and About first)
  3. Before -> After rewrites for each failing part
  4. Trailer + featured-video picks with the reason for each
  5. Section-order recommendation matched to the goal

Steps

  1. Intake. Collect the channel state + goal. View the channel home tab both signed out (non-subscriber sees the trailer) and as a subscriber (sees the featured video). The two audiences see different things; audit both.
  2. Score the parts against the scorecard below.
  3. Fix the channel name + @handle. Name is a real name or brand plus a searchable topic ("Sam Rivera - AI Tools"). The @handle is short, memorable, no numbers if avoidable. The name field is searchable; set it with intent.
  4. Rewrite the About + keywords. First 2 lines carry the value prop (they show in the sidebar preview). Structure: who the channel is for, what they get, how often, one proof. Weave the real search phrases people type into natural sentences; do not keyword-stuff. Add business email and links.
  5. Set the channel trailer (non-subscribers). A 30-to-90-second pitch: who you are, what the channel delivers, why subscribe now. This is the single highest- leverage slot for subscriber conversion. Not a random recent upload.
  6. Set the featured video (subscribers). Returning subscribers see this instead. Use your best recent video or the one you want watched next, matched to the goal (a launch, a flagship, a series opener).
  7. Lay out featured sections + playlists. Group videos into 3+ named playlists by topic or series, then arrange them as sections. Playlists lift session watch time (autoplay into the next video) and tell a new visitor what the channel is about at a glance. Order sections by the goal: lead with the series that converts, not "Uploads" by default.
  8. Order the sections. Trailer/featured first, then the strongest playlist, then popular uploads. Bury generic "Recent uploads" below the curated rows.
  9. Banner check (2560x1440). Design inside the 1235x338 centered safe area so it reads on mobile and TV where the edges crop. One line of value prop + upload cadence ("New AI builds every Tuesday"), high contrast, not a busy collage. It reinforces the About, it does not repeat it.
  10. Profile picture check. Clear face or clean logo, high contrast, recognizable at the small circle size it renders at across watch pages and search.
  11. Watermark + links. Set a branded watermark (a subscribe-prompt or logo) that shows on every video for one-click subscribe. Add the goal-matched links (site / newsletter / offer) to the banner link row; one primary link wins.
  12. Deliver the before/after diff + the one-visit test: a stranger who clicks through from a single video should, from the trailer + banner + About alone, know what they get by subscribing and want to.

Channel scorecard

#PartPass criteria (2026)
1Channel name + @handleReal name or brand + a searchable topic; @handle short and memorable, no stray numbers
2Banner (2560x1440)Value prop + cadence inside the 1235x338 mobile/TV safe area, high contrast, readable small
3Profile pictureClear face or clean logo, high contrast, recognizable at small circle size
4About + keywordsFirst 2 lines carry the value prop; who/what/cadence/proof; real search phrases in natural sentences, no stuffing
5Channel trailerPresent, 30 to 90s, a made-for-non-subscribers pitch matched to the goal, not a random upload
6Featured videoPresent, the best or most goal-relevant video for returning subscribers
7Sections + playlists3+ named playlists laid out as sections, curated rows above generic uploads
8Section orderTrailer/featured first, converting playlist next, "Recent uploads" buried below
9WatermarkBranded subscribe-prompt watermark set on every video
10LinksOne goal-matched primary link in the banner row; extras only if they earn the slot

Hard rules

Global voice rules: see root SKILL.md Voice rules. Additional skill-specific rules:

  • Audit the channel page as both a non-subscriber (trailer) and a subscriber (featured video). They are two different first impressions.
  • The banner must be designed inside the 1235x338 safe area centered in the 2560x1440 canvas. Anything outside it is cropped on mobile and TV. Never put the value prop near the edges.
  • The trailer is the highest-leverage slot for subscriber conversion. A channel with no trailer leaves that slot empty; always recommend setting one.
  • First 2 lines of the About carry the whole value prop (they show in the preview before "more"). Lead with the viewer's benefit, not a mission statement.
  • Real search phrases in natural sentences. Never a comma-separated keyword dump.
  • One primary link. A wall of links dilutes the click.
  • At most one em dash in the About text (about one per 100 words). No "leverage", "fundamentally", "unlock".

Related skills

  • yt-title-optimizer - title the videos the optimized channel will host
  • yt-thumbnail-brief - design the thumbnails the channel grid shows
  • yt-description-writer - the per-video SEO description and chapters
  • yt-content-planner - plan the upload cadence the banner promises

Frequently asked questions

What does the Yt Channel Optimizer AI skill do?

Audit and rewrite a YouTube channel end-to-end for 2026: name and @handle, banner (2560x1440 with the 1235x338 mobile/TV safe area), profile picture, About plus searchable keywords, trailer for non-subscribers vs featured video for subscribers, sections and playlist layout, watermark, links. Triggers on "optimize my YouTube channel", "rewrite my channel about", "fix my banner", "channel audit", "set my trailer". Converts a viewer into a subscriber. Not for writing a video title (use yt-title-optimizer).

Why use Yt Channel Optimizer on TypingMind?

Because you install it once and use it with any model. Yt Channel Optimizer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Yt Channel Optimizer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sergebulaev/youtube-skills/tree/main/skills/yt-channel-optimizer. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Yt Channel Optimizer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Yt Channel Optimizer?

As many as you like. As long as a model supports skills, you can use Yt Channel Optimizer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Yt Channel Optimizer AI skill free?

Yes. It is published on GitHub by sergebulaev under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇