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
- 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.
- Never invent demand. This skill shapes an idea; it does not know your market. Pair it with $yt-viral, which reads what is actually working, before you commit a month to a theme.
The move
- 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), $yt-viral outliers in the niche, the beginner mistakes in the topic, and the "X vs Y" the audience argues about.
- Score all 15 through
ideascore.py. It rates each on SEARCH, SPECIFIC, REACH and DURABLE and flags the weakest axis. - 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.
- 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