Should I or Shouldn’t I? Coding with Claude for Post-Pros Part 2

June 17, 2026

Turn a Premiere Pro XML into CSV shot lists and DaVinci Resolve conform markers with a free Mac tool - and learn when to buy instead.


Series
Quick Summary

Lessons from building XML Parser, a free, Claude-built Mac app for Premiere Pro to DaVinci Resolve turnovers in two clicks, pulling every picture change from the project XML into CSV shot lists and Resolve timeline markers – plus a candid look at when to buy an existing app instead of building your own.

How I built a tool to solve a common turnover problem, and why I’m giving it away for free

While prepping a feature-length documentary for turnover to picture and sound at a London post house, I came up against a delivery request that made me crack open Claude and build a custom solution to save myself many hours of manual labour.

The request? A list of every re-frame, speed ramp, stabilization, rotation, and other minor change that had been made to the picture during the offline edit, so that the online artist could ensure everything was as it should be. With thousands of shots and – given it’s a documentary – a ton of repositioning work on almost every shot, this could take hours, if not days, to compile by hand.

In this article, I’ll walk through the solution I built – XML Parser – the work I put into it, and why I’m now making it freely available to the Mixing Light community. But the more useful question isn’t whether I could build it – vibe-coding makes that almost too easy. It’s whether I should have, and how you can answer that for yourself before you sink your own hours into a half-built idea.

Plus, my closing thought presents a challenge to the community…


“The best solution… is to not have to do this work at all – to simply solve the translation problem between [non-linear editors] as effectively as possible by parsing the Premiere Pro project, clip for clip, attribute for attribute.”

Jonny Elwyn, Editor & Vibe Coder
My estimation skills are similarly ambitious.
My estimation skills are similarly ambitious.

Key Takeaways

By the end of this Insight, you should understand how to:

  • Decide whether a problem is even worth coding – the gut-check to run before you open Claude at all.
  • Identify the real problem beneath the obvious one – so you build the solution that actually saves time, not just the first one you picture.
  • Research both sides of the market before you build – check whether a better tool already exists, not only whether there’s demand for one.
  • Judge whether a vibe-coded tool is worth trusting – the questions to ask before relying on any app built by an unknown solo developer.
  • Get up and running with XML Parser – I built this free, simple, offline option if you find yourself in my situation.


An Object Lesson on the Future of Post-Production Workflows

They say that third-act problems are really first-act problems. When the story doesn’t end well, it’s because it wasn’t set up properly in the beginning. The same goes for vibe-coded apps.

While I researched whether there was demand for XML Parser, I failed to research whether similar apps already existed. They do, and better too. But we’ll come back to that.

Member Content

Sorry... the rest of this content is for members only. You'll need to login or Join Now to continue (your career will thank you!).

Need more information about our memberships? Click to learn more.

Get Answers, Join Now!
Member Login

Members, enter your details here. You will be returned to this page.


Additional Downloads

Sorry... downloads are available for Premium Members only.

Become a Premium Member

Is your career calling out for help?

Answer the call with a Mixing Light Membership. Gain client-tested tips, workflows, and add new skillsets from our pro Contributors!


JOIN NOW! You don't have to do this alone!
Loading...