Skip to content
SkillScript-led2,731 tokens in use

Podcast Ops

Turns a podcast episode from an RSS feed or transcript into scored, deduplicated clips, threads, articles, newsletter sections and a weekly publishing calendar.

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

Install command as written in the repository's README

Skill label

measured from its files

What installing Podcast Ops costs

27tokens idle
2,731tokens in use
4,457tokens, 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 Script-led

Script-ledMixedModel-led

Most of this skill is scripts, so it behaves much the same whichever model runs it.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: podcast_pipeline.py.

Touches

shelldetectednetworkdetectedwrites filesdetectedcredentialsdetected

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
  • Examples15/15
  • Output15/15
  • Size15/15
  • Resources15/15

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 →
Fair
  • File that was not read−15

    a file the skill ships that was not read, so what it does is unknown

    .env.example
  • Runs shell commands−5

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

    SKILL.md, line 11
  • Reads credentials−15

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

    podcast_pipeline.py, line 37
  • Reaches the network−10

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

    podcast_pipeline.py, line 87
  • Writes files−8

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

    podcast_pipeline.py, line 207

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

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.

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