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.