agentleFS
Sign inStart free
uplikauplika/uplika-plugin/skills/yt-viral/SKILL.md

yt-viral

Skill3 starsChanged 36 days agoMITView on GitHub

Find what is working in a YouTube niche, ranked by how far each video beat its channel, and name the formula. For viral videos, competitor research.

5 other projects use a version of this, 5 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

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

    If a call answers workspace_required, the account has more than one workspace: show the names it lists, ask which one, and pass that …

    line 14

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “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

Adapted from Jakeschincariol/youtube-agent-skill (MIT). Not affiliated with the original author.

yt-viral

Raw view counts rank channel size, not ideas. This ranks each video by how far it beat its own channel, which is the only version of the question that is about the video. Use it for "what's working right now", "find viral videos in my niche", "why did this blow up", competitor research, or a swipe file.

With Uplika connected

If a call answers workspace_required, the account has more than one workspace: show the names it lists, ask which one, and pass that workspaceId on every later call in this session.

  1. Call search_youtube_videos with the niche as a viewer would type it (q), order viewCount, a period that fits ("what's working right now" means a recent one), format if the person only makes Shorts or only long videos, and the largest max the tool accepts. The same search again is cached and free; each new combination spends one of the person's daily searches, shown in quota.
  2. Rank by viewSubRatio: views divided by the channel's subscribers, so above 1 means the video pulled more people than the channel has. This is a different axis from this skill's original method, the multiple over the channel's own median: the ratio compares a video with the size of its channel's audience, not with the channel's other videos. Say which axis you used when you present the list.
  3. viewSubRatio is null when a channel hides its subscriber count. List those separately, never as zero and never as winners.
  4. Name the formula for each top title: put the titles one per line in a file and run python3 ../yt-script/scripts/hookscore.py --json titles.txt, then read each formula (the same 21 formulas swipe.py uses, with the Korean patterns for Korean titles). Without a shell, match them by eye against ../yt-script/scripts/hooks.json.
  5. Failures:
    • research_tool_disabled: only a research tool still in beta answers this. Ask the person once to turn it on at the enableUrl in the error, and do not retry until they say it is on.
    • youtube_quota_exhausted (the shared quota for today, back at resetsAt) or research_quota_exceeded (the person's own daily searches): when a shell is available, fall back to the method without Uplika below, collecting with yt-dlp --flat-playlist -J, and say the axis changed to the channel-median multiple. Without a shell, ask for a pasted list or wait for the reset.
    • platform_error: YouTube did not answer; try once more a minute later. Anything else: get_help with the code.

Without Uplika

The original method ranks by multiple over each channel's own median. From this skill's folder:

python3 scripts/swipe.py collected.json --min 2.0

You need at least four videos per channel or a median means nothing, and the tool will skip the channel and tell you it did. Collect them however the person prefers: when a shell is available, yt-dlp --flat-playlist -J against a channel's videos page is the fastest, the public page works, a manual list works.

[{"channel":"...","title":"...","views":412000,"url":"...","duration":613}]

Read, do not scrape. Public listings only, never a logged-in session, never the person's own account credentials.

Reading the output

The multiple (or the ratio) is the signal. The formula line is a judgement about the TITLE, matched against the 21 formulas: it is not a claim about why the video worked, and you should say so when you present it. A Korean title is matched with newly written Korean patterns and marked Korean: heuristic, not calibrated.

What to hand back: the top five with their multiples or ratios, the formula each used, and the ONE structural thing they share. Then the harder line: which of those the person could actually make this week, in their voice, with what they have. For a full plan built from the pattern, the yt-benchmark skill goes further.

The gate

Nothing here publishes. This skill writes and the person publishes. Every output ends in a block they copy, and the last line of every run is the question: ship it, or change it?

Tools

  • search_youtube_videos: the niche's top videos with views, subscribers and their ratio
  • get_help: the answer for any other error code

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.

Check your setup, free