Skip to content
SkillScript-led707 tokens in use

shortform-production

Editorial rules for readable shorts in a fixed V5 style, plus a Metricool client that schedules approved Instagram Reels with receipts.

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

Install command as written in the repository's README

Skill label

measured from its files

What installing shortform-production costs

30tokens idle
707tokens in use
7,195tokens, 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 Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

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

Touches

shelldetectednetworkdetectedwrites filesdetectedcredentialsdetected

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
  • Structure17/25
  • Examples9/15
  • Output10/15
  • Size15/15
  • Resources9/15

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 →
Good
  • Runs shell commands−5

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

    SKILL.md, line 15
  • Reaches the network−10

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

    scripts/metricool.py, line 16
  • Writes files−8

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

    scripts/metricool.py, line 47
  • Reads credentials−15

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

    scripts/metricool.py, line 271

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 Production sets the visual and editorial rules for vertical shorts and the steps to deliver them. The V5 style fixes the export size, colors, caption sizes and evidence handling. The skill also covers producing three opening treatments for one clip, reviewing a finished edit with a rubric and recording results.

For delivery it includes a Python client for the Metricool API. It runs a dry run by default, verifies the account, uploads the video, creates a Reel and reads it back, saving receipts that prevent duplicate posts.

What You Get

  • V5 style rules: 1080 by 1920 masters, a four-second opening headline, ivory, near-black and yellow colors, stable caption placement
  • A way to produce three opening previews for one clip before rendering the full edit
  • A review kit with a rubric, a judge prompt, reference requirements and a scorecard schema
  • metricool.py with schedule, inspect and move commands, dry runs and saved receipts
  • Delivery notes on private profiles, manifests, recovery after a timeout and status wording that matches the evidence
  • A next-batch plan for a production cycle

Common Use Cases

  • Editing a recorded talk into a captioned vertical short with evidence screens
  • Testing three hook treatments for the same clip
  • Scheduling approved Reels on a connected Instagram account
  • Moving a pending scheduled post to a new time or to now

What Makes It Unique

It joins editing rules with a delivery client that guards against duplicates: create intent is saved before the request, a timeout blocks another create, and a verified receipt stops reruns. Statuses such as scheduled or published are reported only with matching evidence.

Under The Hood

The skill is mostly prose and reference files, with one Python script, metricool.py. The script reads a private profile and manifest, reads your API token from an environment variable, sends requests to the Metricool API, uploads video files, and writes receipt files to a folder you choose. It makes no network calls in dry-run mode and writes to Metricool only when you pass the apply flag. A preamble runs the repository’s version check and telemetry setup scripts, where remote telemetry is opt-in.

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