agentleFS
Sign inStart free
ahmedsakriahmedsakri/youtube-agent-pro/skills/yt-idea/SKILL.md

yt-idea

Skill1 starsChanged 37 days agoMITView on GitHub

Turn a niche or a blank page into video ideas that are searchable, specific and bigger than the channel - each one scored before it costs a week of filming. Use for "what should I make", "I have no idea what to post", "give me video ideas", "ideas for my channel", or when a creator is staring at an empty upload schedule.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is 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.

  • 1

    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) - who the one viewer is, what the channel will not claim.

    line 28
  3. Very specific:

    Never invent demand. This skill shapes an idea.

    line 30

≈ “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-idea

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

Ideas are cheap. Ideas shaped so somebody clicks them are not. This gets from a niche to a scored shortlist without you shooting the wrong one.

A tool lives here and it runs. Use it; do not eyeball the idea.

python3 "$YT_SKILL_DIR/ideascore.py" ideas.txt           # rank a batch
python3 "$YT_SKILL_DIR/ideascore.py" --idea "one line"   # score a single one

Before you write

  1. Use the available voice profile or creator context (see the operating guide) - who the one viewer is, what the channel will not claim. An idea for the wrong audience scores well here and dies on upload.
  2. Never invent demand. This skill shapes an idea; it does not know your market. Pair it with /youtube-agent-pro:yt-viral, which reads what is actually working, before you commit a month to a theme.

The move

  1. Widen, then narrow. From the niche, write 15 raw ideas fast - do not filter yet. Pull from: the creator's own comments (the questions people already ask), /youtube-agent-pro:yt-viral outliers in the niche, the beginner mistakes in the topic, and the "X vs Y" the audience argues about.
  2. Score all 15 through ideascore.py. It rates each on SEARCH, SPECIFIC, REACH and DURABLE and flags the weakest axis.
  3. Refine the strongest candidates. Improve each idea's weakest useful dimension without adding unsupported numbers merely to increase its heuristic score. The score is not measured demand or a calibrated prediction of performance.
  4. Label the mix. Mark each as evergreen or timely. A schedule that is all timely has no library; all evergreen and the channel never rides a wave. Aim roughly 3 evergreen to 1 timely.

What to hand back

  • the 5 reshaped ideas with their scored panels
  • for each: the one query a real person types to find it
  • the evergreen / timely label on each
  • one line: which to shoot first, and why that one now

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