Skip to content
SkillMixed1,064 tokens in use

shortform-idea-grill

Interview a creator one question at a time, then rank proof-led short-form ideas with five-second hooks, scores and three talking bullets.

3,862 stars on the repository MIT Licenseericosiu/ai-marketing-skills · shortform-idea-grill
npx skills add ericosiu/ai-marketing-skills -s shortform-idea-grill
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing shortform-idea-grill costs

31tokens idle
1,064tokens in use
2,046tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Mixed

Script-ledMixedModel-led

Scripts do part of the work and the model's judgement does the rest.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/score_ideas.py.

Touches

shelldetectedwrites filesdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter8/15
  • Structure19/25
  • Examples12/15
  • Output15/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 89
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    scripts/score_ideas.py, line 139

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity88
  • Maintenance44
  • Community56
  • Maturity28
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers