yt-collab
Skill1 starsChanged 37 days agoMITView on GitHub
Find the right channels to collaborate with and write the pitch that gets a reply - matched by audience overlap and size band, not by fandom. Use for "find a collab", "who should I collaborate with", "collab pitch", "reach out to other creators", or growing through other channels.
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-commentSkill
- yt-editSkill
- yt-endscreenSkill
- yt-funnelSkill
- 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
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 12
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 pitch is in the creator's voice, and it has to name what …
- Distinctive: line 41
Write it short and specific:
≈ “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-collab
Read the shared operating guide for profile lookup, helper paths, capability limits, and cross-skill routing before using this workflow.
The fastest borrowed audience on YouTube is a collab with a channel one size band up that shares your viewer but not your exact topic. This finds those channels and writes the pitch that does not get ignored.
It reads public listings, the same as /youtube-agent-pro:yt-viral - it never logs in as anyone and never touches credentials. Pair the two: /youtube-agent-pro:yt-viral finds who is working, this decides who is reachable and why.
Before you reach out
- Use the available voice profile or creator context (see the operating guide) - the pitch is in the creator's voice, and it has to name what they bring, not just what they want.
- Be honest about size. A channel 50x bigger is not a collab, it is a favour you have not earned. The reachable band is roughly 0.3x to 3x your own median views.
Who to target
- Adjacent, not identical. Same viewer, different topic. Two channels making the exact same video split one audience; two that share a viewer across topics trade audiences.
- In the reachable band (0.3x-3x your views). List five, not one.
- Active and responsive - uploading recently, replying to comments. A dormant channel is a dead pitch.
- With a concrete overlap you can name - "your audience asks about X in your comments, that is the whole of what I make".
The pitch
Write it short and specific:
- Reference one specific video you actually inspected. Do not pretend to be a longtime viewer.
- The overlap, named - why your viewer is their viewer.
- The concrete format - not "let's collab" but "I film a 10-minute X, you do the Y half, we both publish our cut". Give them something to say yes to.
- What you bring, honestly. No begging, no fake numbers.
What to hand back
- five target channels, each with its size band and the named overlap
- the pitch, ready to send, in the creator's voice
- two collab formats that fit (guest segment, split video, response video)
- one line: who to pitch first, and the one video of theirs to reference
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.