Skip to content
SkillMixed2,198 tokens in use

Video Content Engine

Diagnose one video, score its content opportunities and plan the long-form, short-form and written assets it can support.

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

Install command as written in the repository's README

Skill label

measured from its files

What installing Video Content Engine costs

26tokens idle
2,198tokens in use
5,688tokens, 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 →
Good
  • Frontmatter8/15
  • Structure19/25
  • 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

Video Content Engine takes one grounded source, such as a URL, a file, a transcript or a recording, and works out the strongest justified portfolio of content from it. Without a production request it returns a brief with a source score, recommended modes, opportunity counts and the approval needed to begin.

When production is requested it covers edit maps, boundary audits, captions, packaging for each asset and a delivery folder checked by a validator script. It never publishes or schedules without explicit approval.

What You Get

  • A diagnose-and-recommend brief with source score, editorial mode and first release wave
  • A claim ledger, a rights ledger and a timestamped content-atom inventory
  • Edit maps and boundary audits for long-form, mid-form and 15 to 90 second vertical assets
  • Packaging for each asset: titles, thumbnails, hooks, covers, captions and calls to action
  • A delivery folder with a manifest and a 24-hour, 72-hour and seven-day measurement plan

Common Use Cases

  • Deciding how many clips and posts a recorded episode can support
  • Planning a recut of a long video that opens weakly
  • Checking claims and third-party media before a video is released
  • Handing an editor a structured plan with timestamps and source mappings

What Makes It Unique

The skill refuses a fixed quota of derivatives. The opportunity inventory decides how many assets a source supports, and every asset needs its own promise and payoff. It separates technical integrity from editorial approval, so a passing validator never counts as a finished edit.

Under The Hood

The agent follows a long SKILL.md and reads reference files on routing, editing, quality gates and delivery as needed. It runs two Python validators from the shell, one for edit boundaries and one for the delivery folder, and may run the repository telemetry helpers described in the preamble, which log locally with opt-in remote reporting. It can fetch a supplied video URL or transcript, transcribe media and write files such as renders and manifests, but the package has no editor or render service of its own. Publishing, uploading and scheduling need your explicit approval.

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