Skip to content
SkillModel-led1,574 tokens in use

Trial Reel Distribution

Run trial reels as a distribution lane: repost your best feed videos unchanged to non-followers and graduate the winners.

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

Install command as written in the repository's README

Skill label

measured from its files

What installing Trial Reel Distribution costs

24tokens idle
1,574tokens in use

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

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

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

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
  • Structure25/25
  • Examples6/15
  • Output10/15
  • Size15/15
  • Resources0/15

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

Trial Reel Distribution is a playbook an agent follows to use trial reels, which are shown to non-followers, as reach for content that already worked. It builds a pool from the top posts of the last 90 days, prepares each one with a fresh export and caption, schedules them in daily batches and reads reach at 48 to 72 hours.

Trials that clear a graduation bar return to the main feed, and the bar is raised once one does. The skill is instructions only, with no scripts.

What You Get

  • A ranked pool of about 30 top posts from the last 90 days, each with its original reach recorded
  • A preparation rule for every post: same video, fresh export, new caption
  • A batch schedule of about five trials a day, best posts first
  • A reading routine at 48 to 72 hours that treats an empty analytics row as pending
  • A graduation and winner rule that moves trial winners to the feed and raises the bar

Common Use Cases

  • Replacing rounds of edit-variant trials that keep returning low reach
  • Opening a repeatable non-follower reach lane that needs no new production
  • Deciding which past posts deserve a second run and in what order
  • Setting a reach bar and a daily posting cap so winners queue behind the feed schedule

What Makes It Unique

Most short-video skills help you make new clips or test new hooks. This one holds the video fixed and spends trial slots only on posts that already earned reach, so the trial result reflects the audience and not an edit. Its worked example compares distribution against variant testing on the same account.

Under The Hood

This skill is a single SKILL.md of instructions and ships no scripts. The agent follows the steps using whatever tools you give it, such as a scheduler with a per-post reach export, and may re-export video files and write captions. It does not fetch pages or call an API by itself. It does not name a specific command to run.

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