agentleFS
ahmedsakriahmedsakri/youtube-agent-pro/skills/yt-series/SKILL.md

yt-series

Skill1 starsChanged 38 days agoMITView on GitHub

Design a multi-video series or a playlist as an architecture - an order people binge, each video earning the next click, a shared package so the set reads as one thing. Use for "plan a series", "a playlist", "a course", "multi-part video", "how do I structure a season", or turning one big topic into several videos.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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
  1. Distinctive:

    Read the shared operating guide for profile lookup, helper paths, capability limits, and cross-skill routing before using this workflow.

    line 13
  2. Distinctive:

    Use the available voice profile or creator context (see the operating guide) and, if there is one, the channel's existing format - a series …

    line 22
  3. Distinctive:

    The binge seam: Every video ends on the exact question the next one opens with.

    line 32
  4. Distinctive:

    Write each part's one-line promise and its binge seam to the next.

    line 43

≈ “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.

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

yt-series

Read the shared operating guide for profile lookup, helper paths, capability limits, and cross-skill routing before using this workflow.

A playlist is not a folder. A series that works is an architecture: an order that creates a binge, each video ending on the question the next one answers, and a shared look so the set reads as one thing in the sidebar. This designs that.

Before you plan

  1. Use the available voice profile or creator context (see the operating guide) and, if there is one, the channel's existing format - a series has to fit the cadence the creator can actually keep.
  2. A series is a commitment. Size it to the uploads they will finish, not the ones they imagine. Four videos shipped beats a twelve-part plan abandoned at three.

The architecture

  1. The spine. One question big enough for the whole series, split into parts that each stand alone and lead on. Part 3 must be watchable by someone who found it first, and must make them want part 4.
  2. The binge seam. Every video ends on the exact question the next one opens with. That seam is a reason to continue watching. Measure actual continuation instead of claiming an algorithmic reward.
  3. The shared package. A title pattern (numbered or named), a thumbnail template that varies one element per part, and a playlist title that is itself a search query. Hand the per-video packaging to /youtube-agent-pro:yt-package and /youtube-agent-pro:yt-thumbnail so each one is still linted on its own.
  4. The entry point. Decide which video a stranger lands on first - usually not part 1. Order the playlist so the strongest standalone is the front door and the spine still holds.

The move

  • Map the spine into N parts, N sized to real capacity.
  • Write each part's one-line promise and its binge seam to the next.
  • Define the title pattern and the thumbnail template (what stays, what changes per part).
  • Set the playlist title as a query, and name the entry-point video.

What to hand back

  • the ordered series with each part's promise and its seam to the next
  • the title + thumbnail pattern for the set
  • the playlist title (as a search query) and the entry-point pick
  • one line: the realistic cadence, and the first video to shoot

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.