Skip to content
SkillMixed1,296 tokens in use

shortform-format-library

A workflow for keeping a library of short-form video formats and matching each content idea to a format, a recording outline and an edit brief.

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

Install command as written in the repository's README

Skill label

measured from its files

What installing shortform-format-library costs

28tokens idle
1,296tokens in use
3,476tokens, 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/validate_library.py.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

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
  • Structure23/25
  • Examples6/15
  • Output15/15
  • Size15/15
  • Resources7/15

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

No findings.

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 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.

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