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.