Shortform Idea Grill turns current work into short videos that earn attention fast and repay the opening promise. The agent reads supplied chats, briefs, transcripts and analytics first, then interviews the user one question at a time about outcome, viewer, proof, claim limits and CTA.
It returns one fixed table: rank, topic, a five-second hook, virality and three-second hook scores, three talking bullets, the complete payoff with proof, and a CTA. A script validates and scores saved JSON.
What You Get
- A ranked table in a fixed column order with exactly three spoken bullets per idea
- One five-second overlay hook per idea, with the evidence behind any number
- Virality and three-second hook scores from 1.0 to 10.0 with a stated rubric
- An internal priority formula that weights virality, hook and payoff confidence
- score_ideas.py, which validates JSON idea records and writes a scored file
- A final checklist covering net-new status, proof paths, source links and public-output safety
Common Use Cases
- Planning a week of videos from what a founder built and measured
- Ranking a backlog of short-form ideas by recording priority
- Interviewing a subject expert to pull out proof, numbers and claim limits
- Saving machine-readable idea lists for an editor or scheduler
What Makes It Unique
It asks one question at a time and stops when more questions would not change the ranking. Scores rank what to record and are stated not to forecast views. It requires a complete payoff for every hook and marks unsupported numbers as needing verification.
Under The Hood
This is mostly a prose workflow with reference files for intake, output format, scoring and the JSON schema, plus one Python script. score_ideas.py reads an ideas JSON file, checks fields, computes a priority score and writes a scored JSON file to a path you give it. The skill sends the agent to read the user’s supplied chats, briefs, transcripts and analytics before asking questions. It does not call external services on its own.