Podcast Ops takes an RSS feed or a transcript and runs it through a seven-step pipeline: ingest, extract content atoms, generate pieces for each platform, score them for viral potential, remove overlaps, build a weekly calendar and write the results to an output folder.
A bundled Python script does the work. It downloads episode audio, transcribes it with the OpenAI Whisper API and calls the Anthropic API to write the content, so it needs API keys for both.
What You Get
- A timestamped transcript and a JSON file of extracted content atoms: narrative arcs, quotes, contrarian takes, data points, stories, frameworks and predictions
- Draft content for each platform with hooks, captions and call to action
- A viral score per piece from novelty, controversy and utility, with thresholds for what to publish
- A deduplicated set checked against the current batch and recent history
- A weekly publishing calendar in JSON with times by platform
Common Use Cases
- Repurposing the latest episode of a podcast into a week of posts
- Processing the last several episodes in one batch and removing repeated angles
- Producing a calendar from existing outputs without regenerating content
What Makes It Unique
The pipeline pairs generation with a scoring formula, score cutoffs that drop weak pieces, and a similarity check against recent output with a configurable window. Pieces that overlap a recent post are flagged with a suggested new angle. Scheduling rules per platform are built in, and the CLI offers flags for the minimum score and the dedup window.
Under The Hood
The skill ships one Python script and a requirements file. Given an RSS address, the script fetches the feed, downloads the episode audio to a temporary folder, sends the audio to the OpenAI Whisper API and sends the transcript to the Anthropic API for content generation, using keys from environment variables. It writes transcripts, JSON files, a content history file and a pipeline log to an output folder. At the start the instructions also run the repository’s version check and telemetry helper through the shell, with remote telemetry opt-in.