Index your archive and turn essays into new drafts

A writer used Claude Code to search a large archive, then reused essays as newsletter and thread drafts with a review step.

Done with Claude Code· Intermediate

What they did
Casey Newton of Platformer had Claude Code build a searchable index of 818 newsletter editions. Darren Rowse also used it to review about 1,000 markdown notes in an Obsidian vault, and another workflow turned a finished essay into separate newsletter, thread, and summary files that followed voice rules in CLAUDE.md. In that setup, the writer checked each change as a diff before accepting it.
How it went
Newton’s archive index was finished in under 30 minutes. Rowse said the vault became part of how they work, and one writer case study said output rose from 4–5 articles a month to 8. A broad cleanup request caused invented tags and a mess.
Tips
Start with a limited inventory and ask for a suggested folder plan before moving anything. For larger cleanups, approve changes one folder at a time and keep original files untouched until you review the draft outputs.

Try it yourself with Claude Code

I have a writing archive in [folder path]. First, scan it and give me an inventory of what’s there, plus a proposed folder structure for keeping it searchable. Pause and ask before moving, renaming, or deleting anything. After I approve, create a searchable index of the archive and a short audit of repeated themes and obvious gaps. Then take [essay filename] and produce three new files in [output folder]: a newsletter draft, a thread draft, and a short summary, all matching the voice rules in [voice guide file]. Show me every edit as a diff and stop after saving the drafts. Do not change or remove any original files without my approval.

Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.

Read the original on ccforeveryone.com ↗

Get 3 agent uses like this every morning

With the day's top AI news. Free, and one click to unsubscribe.