Skip to content
SkillModel-led1,472 tokens in use

Monday Reel Ideas

A weekly run that finds a creator's 3x outlier posts and verified outside breakouts, then writes three scripted short-form video ideas in one document.

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

Install command as written in the repository's README

Skill label

measured from its files

What installing Monday Reel Ideas costs

54tokens idle
1,472tokens 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
  • Structure19/25
  • Examples0/15
  • Output10/15
  • 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

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

Monday Reel Ideas is a weekly idea pipeline for a creator who sells to business operators. It scores last week’s picks, pulls the creator’s own outliers from the last 30 days, adds recent saves, tracked creators and a wider scan, and then builds three ideas.

Each idea copies the hook shape and beat outline of a post that already broke out, with the creator’s own angle and verified proof numbers. The set ships as one organized document with source screenshots and links, and nothing is posted.

What You Get

  • A scored recap of earlier picks that have since posted, with views and the multiplier against the format median
  • The creator’s outliers from the last 30 days, split into feed reels, carousels and trial copies
  • Three numbered ideas, each with a format tag, the hook it copies, a beat outline, a full script of 70 to 110 spoken words and on-screen text
  • A source screenshot of the first frame and a reference link inside every idea block
  • A picks log that next week’s run reads

Common Use Cases

  • Planning a week of reels for a creator with a business audience
  • Checking which past ideas worked before choosing new ones
  • Finding breakout formats from outside creators with their engagement verified first

What Makes It Unique

Ideas have to trace to a post that already broke out, and the script is written on that post’s beat outline with the creator’s angle. Numbers in a script come only from a verified proof sheet, and any other figure becomes a bracketed slot. At least one idea must extend the creator’s own top pattern, topics are checked against the shoot list and earlier runs, and the delivery is one document with the chat message holding only the link.

Under The Hood

This skill is one instructions file with no scripts and no reference files. It tells the agent to pull post analytics, saves and tracked-creator data from whatever sources the creator has connected, verify outside creators’ recent posts, capture real screenshots of source posts and build one shared document. It also reads a shoot list, a concept backlog and a picks log from earlier runs and writes the new picks back to that log. It does not post, schedule or send direct messages, and if a data source fails it delivers what verified and names the gap.

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