Shortform Format Library helps a creator move from an idea to a usable delivery structure. It keeps source evidence, editorial interpretation and the creator’s own results apart, and builds a content table with an idea source, a suggested format, a specific watch reference, three talking prompts, a claim limit and a call to action.
It also covers content spike research, recurring creator discovery, a visual page where a user picks an idea and two format references, and a renderer-neutral editing brief. A validator script checks an optional library snapshot.
What You Get
- A content table with idea source, suggested format, watch reference, three talking prompts, claim limit and CTA for each idea
- Rules for judging spikes: creator-relative baselines, sample sizes, posts under 48 hours kept provisional
- A page and data contract for a library where a chosen idea and format turn into an editable three-prompt outline
- A renderer-neutral editing brief with timestamped beats, source ranges, captions, proof timing and acceptance criteria
- validate_library.py, which checks IDs, references, prompt counts, dates, URLs and metric values in a snapshot file
Common Use Cases
- Choosing a delivery format for a short-form idea from a set of reference videos
- A weekly pass over reference accounts to find outlier posts and new format examples
- Building a shareable page where creators browse formats and draft a recording outline
- Handing an editor a brief that cites the exact reference to borrow from
What Makes It Unique
It separates the idea source from the video that demonstrates a format, requires a direct link to the specific reference or the words Reference needed, and treats outliers as evidence about a creator and not proof that a format caused results. It reuses the ManyChat lead magnet skill for comment-to-access delivery when installed.
Under The Hood
This is a prose workflow with four reference documents and one Python validator that reads a JSON snapshot and never writes input files. The skill sends the agent to read the user’s library and supplied analytics, to open reference videos and creator pages for research, and to build or change a page when asked. Inside the AI Marketing Skills repository it runs an optional version check and an optional telemetry logger that follows the saved consent setting. Publishing, scheduling and live lead delivery need the user’s separate authorization.