The Wiki Waltz

we have the pod manager configured to generate the .ODT source file and the commands for the Ubuntu server. Here is the code for the script that can grab the source file, chunk the text, send it off to eleven labs one chunk at a time, pull them together into a full audio file with the introduction and out roll tunes.

The secret to getting Claude to repeat a process is to build a skills document. The best way to build a skills document is to have Claude build if for you. Have an in depth conversation - what are you trying to do. What is the workflow that should be followed. Break the workflow into defined stages.

I am discussing this project with Claude as we go along - he created a project management list - this came out of a discussion on the goals and process of the project, and generated the below planning document - to be honest the document is not that great. It does provide some guidelines but I post it here to demonstrate what he can produce based on a project conversation

I am using Claude AI to assist in the build of the project. 
once the project is ready to go, we will use Claude to actually write the scripts for the shows, and then use an API service to pull in the voice from 11 labs.

I am using a custom module that is already installed in the site - it allows multiple podcasts from a single Drupal site - the module settings allows you to create the podcast ID and channel data - the content type node selects the associated podcast ID.
each node provides the RSS item data including the enclosure. A controller creates the RSS feed for the podcast aggregators.

Created a Drupal content type to hold the project parent, also created a content type to hold log entries - (this entry)
this content type has fields to define the parent project, a field to define the tech associated with the entry (a taxonomy) as will as this note space and a field to insert code examples