yt-funnel
Skill1 starsChanged 37 days agoMITView on GitHub
Fix the channel page and the subscriber conversion - the trailer, the above-the-fold, the sections, and the one video that converts browsers into subscribers. Use for "my channel page", "people watch but don't subscribe", "channel trailer", "subscriber conversion", or "optimise my homepage".
In this repository25 other files it gives its agents.
- openai/AGENTS.mdAGENTS.md
- llms.txtllms.txt
- yt-analyticsSkill
- yt-auditSkill
- yt-briefSkill
- yt-chaptersSkill
- yt-collabSkill
- yt-commentSkill
- yt-editSkill
- yt-endscreenSkill
- yt-ideaSkill
- yt-packageSkill
- yt-planSkill
- yt-repurposeSkill
- yt-retentionSkill
- yt-scriptSkill
- yt-seoSkill
- yt-seriesSkill
- yt-shortsSkill
- ytSkill
- yt-sponsorSkill
- yt-thumbnailSkill
- yt-trendSkill
- yt-viralSkill
- yt-voiceSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Read the shared operating guide for profile lookup, helper paths, capability limits, and cross-skill routing before using this workflow.
- Distinctive: line 24
Use the available voice profile or creator context (see the operating guide) - the trailer and the channel description are the channel's …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
yt-funnel
Read the shared operating guide for profile lookup, helper paths, capability limits, and cross-skill routing before using this workflow.
Views are not the funnel. A viewer lands on one video, and whether they become a subscriber is decided on the channel page in the next ten seconds. Most creators never touch it. This does.
For the per-video numbers (impressions, CTR, retention), that is /youtube-agent-pro:yt-analytics. This skill is the layer above: what happens to a viewer between videos, and on the channel page itself.
Before you work
- Use the available voice profile or creator context (see the operating guide) - the trailer and the channel description are the channel's first sentence, in the creator's voice.
- Get the conversion reality: Studio -> Analytics -> Audience shows returning vs new viewers, and Content -> a video -> Analytics shows subscribers gained per video. Subscribers-per-view is the number this skill moves.
The four surfaces
- The channel trailer (shown to non-subscribers). Not a highlight reel - a 30-60s answer to "why subscribe": who it is for, what they get, how often. Treat its first 5 seconds like any hook and run it through /youtube-agent-pro:yt-script's hook logic.
- Above the fold. The banner, the handle, the one-line description. A stranger reads these before a single video plays. They must say who the channel is for in one line.
- The sections. Order the channel homepage so the entry-point video (the one strangers find first) is top, a playlist that creates a binge is second, and the rest supports. Pair with /youtube-agent-pro:yt-series for the binge path.
- The conversion video. Find the one video with the best subscribers-per-view and treat it as the front door - link it, pin it, feature it. Make more like it.
The move
- Audit each of the four surfaces against "does a stranger know who this is for in ten seconds".
- Rewrite the trailer script and the above-the-fold line.
- Name the conversion video and the entry-point ordering.
- Give one change per surface, ranked - not a redesign.
What to hand back
- the rewritten trailer script (hook-first) and the above-the-fold line
- the section order, with the entry-point and binge playlist named
- the conversion video to feature, from the data
- one line: the single highest-leverage change of the four
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

