Skip to content
SkillMixed1,954 tokens in use

Leveling Up Content Engine

Reviews one recording, scores its moments, picks the justified set of long, mid and short cuts, and checks edit boundaries and delivery files before release.

3,862 stars on the repository MIT Licenseericosiu/ai-marketing-skills · leveling-up-content-engine
npx skills add ericosiu/ai-marketing-skills -s leveling-up-content-engine
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Leveling Up Content Engine costs

30tokens idle
1,954tokens in use
4,535tokens, 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/audit_edit_boundaries.py, scripts/validate_delivery.py.

Touches

shelldetectedwrites filesdetected

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 →
Excellent
  • Frontmatter8/15
  • Structure25/25
  • Examples12/15
  • Output15/15
  • 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
  • Runs shell commands−5

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

    SKILL.md, line 15
  • Writes files−8

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

    scripts/audit_edit_boundaries.py, line 51

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

Leveling Up Content Engine takes one grounded source, such as a video, audio file, transcript or link, and works out which assets it can support with evidence. It builds a claim ledger, a rights ledger and an inventory of content moments, scores them, and picks the lightest editing mode that fixes the problem.

When production is requested it plans long-form, mid-form, short-form, carousel and written pieces with titles, covers and captions. Two small Python validators check clip boundaries against the transcript and the delivery folder against its manifest.

What You Get

  • A source brief with scores for hook, clarity, proof, pacing and payoff, plus the recommended editorial mode
  • A claim ledger, rights ledger and timestamped inventory of content moments
  • A portfolio spine and a job, promise and destination for each selected asset
  • Packaging for each asset: titles, thumbnail briefs, covers, hooks, captions and calls to action
  • A delivery folder with a manifest that a script checks, and a 24-hour, 72-hour and seven-day measurement plan

Common Use Cases

  • Reviewing a podcast or webinar recording to decide which clips are worth making
  • Checking that retained clips start and end on complete thoughts before rendering
  • Planning a release order across platforms with notes on overlap between assets

What Makes It Unique

The skill does not invent output counts: opportunities are scored and rejected on the record, and unsupported claims, repeated promises and incomplete excerpts are dropped. It treats a technical pass as separate from a coherent edit, keeps editing approval, source approval and publication approval as separate states, and never publishes, schedules or spends quota without explicit approval and a read-back from the destination.

Under The Hood

The skill is mostly instructions with five reference files and two Python scripts that use only the standard library. At the start it tells the agent to run the repository’s version check and telemetry initializer through the shell when they exist, ignoring failures; remote telemetry is opt-in. One script reads a transcript and a clips file and writes an audit report; the other reads a delivery folder, hashes the files it names and prints a pass or fail result. The agent is also told to resolve source links, transcribe media, render video and write a delivery folder, so it reads and writes local files and may fetch the source over the network.

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