agentleFS
gladosAagmangladosAagman/youtube-agent-skill/skills/yt-sponsor/SKILL.md

yt-sponsor

Skill1 starsChanged 5 days agoMITView on GitHub

Run YouTube sponsorships without underpricing or overpromising - a rate card from the channel's real median views, the pitch to a brand, the reply to an inbound offer, the contract terms to ask about, and a sponsor read placed where it does not wreck retention. Use for "how much should I charge", "rate card", "a brand reached out", "sponsorship", "pitch a sponsor", "write the ad read", "is this deal fair".

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. ahmedsakri/youtube-agent-pro★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository14 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 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.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read ~/.claude/youtube/voice.md if it exists.

    line 25
  2. Distinctive:

    Never invent a number. Not views, not audience demographics, not past results for other sponsors.

    line 27
  3. Distinctive:

    Ask about each one before agreeing to a number:

    line 43
  4. Very specific:

    Placement: after the hook has paid off, not inside the first 60 seconds.

    line 68
  5. Very specific:

    Run the read through /yt-script's hook scorer for the transition line and /yt-preflight --script for voice.

    line 77

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

yt-sponsor

Most creators underprice the first deal and overpromise on views, and both come from quoting off their best video. This prices off the typical one, and it writes the read so the sponsor slot does not become the retention cliff.

python3 ratecard.py --views 41000 18000 22500 30100 19800 26000 --cpm-low 20 --cpm-high 35
python3 ratecard.py --views-file last10.txt --cpm-low 15 --cpm-high 30

Before you write

  1. Read ~/.claude/youtube/voice.md if it exists. A sponsor read in the wrong voice is the most skipped 60 seconds in the video.
  2. Never invent a number. Not views, not audience demographics, not past results for other sponsors. Ask for them or leave them out.

The rate

  • Views: the last ten long-form videos, from Studio. Not the channel average, which one hit inflates. ratecard.py uses the median and prints the 25th-75th percentile as the range a sponsor should expect.
  • CPM: the user supplies it. From quotes they have received, a creator in their niche who shared rates, or the brand's own offer. The tool has no default on purpose: niche, audience country and placement move it several times over, and a number from a blog post is not theirs.
  • Shorts are priced separately, if at all. Their views do not translate.

The terms that move the price

Ask about each one before agreeing to a number:

termwhy it matters
Usage rightsthe brand running the read as an ad elsewhere is a separate fee
Exclusivityno competitors for N days costs the creator other deals
Whitelisting / ads from the channelthe brand spending from the creator's account
Revisionshow many rounds, and who approves the script
Deliverablesintegration length, placement, pinned comment, description link
Payment termsnet 30 is normal; net 90 is a loan. Ask for part up front on a first deal
Reportingwhat they need back and when, so nobody argues about views later

The pitch (outbound)

Three short paragraphs: why this brand and this audience (specific, from the channel's real comments or analytics), the offer (format, timing, median views, the rate range), one ask. Attach nothing the user cannot back up.

The reply (inbound)

Thank them, ask the questions in the table above that the offer left out, and give the rate range. Never accept the first number in the first reply.

The read

  • Placement: after the hook has paid off, not inside the first 60 seconds. /yt-retention on past sponsored videos shows where the drop was.
  • Length: 45-75 seconds for an integration. Longer is a cliff.
  • Shape: a transition line that belongs to the video, the creator's real use of the product, one specific benefit, the offer, the return line.
  • Disclosure: say it is sponsored, out loud, near the start of the read, and tick "includes paid promotion" in Studio. That is YouTube's rule, and advertising regulators in most countries require disclosure too.

Run the read through /yt-script's hook scorer for the transition line and /yt-preflight --script for voice.

The gate

Nothing here publishes, sends or signs anything. This skill writes and you send. Every output ends in a block the user copies, and the last line of every run is the question: ship it, or change it?

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.