Review reversible podcast edits made by a show-specific Claude skill
At a glance
Julia Thompson connected Claude to Descript and gave each podcast its own editing rules, keeping the first cleanup pass reversible. This workflow is listed under podcast-production, audio-editing, human-review.
Her skill targets the host's spoken track, applies Studio Sound only there and marks cuts with strikethrough instead of deleting audio. Separate show rules control filler removal, pauses and protected reactions. The workflow also drafts show notes and ranks social-clip candidates.
How it went
She reports that one skill handles about 80% of her overall production workflow, after several episodes spent refining prompts and instructions.
Worth knowing
Claude has told her an edit was made when it was not. She listens to the complete episode, checks the cuts and adjusts the clip selections herself.
Save ideas in this browser. Upvotes count across the board.
An indie hacker packaged an agency's eight repeated workflows (briefs, client approval with revision counters, quotes with margin checks, content calendars, post-mortems) as free MIT Claude skills.
Anthropic’s Building Effective Agents appendix highlights two proven patterns—support agents that pull data and take actions like refunds, and coding agents that iterate against tests—with clear success metrics and human review.
Indie Hackers founder Sean Prentice used Claude Code to build an orchestrator + marketing director + specialist agents (content/ads/research) for his SaaS; outputs land in Slack and nothing posts or spends without his explicit say (~$10/mo self-use).
A lawyer used Claude’s Word add-in on a 30-page document—it rewrote sections and replied to comments as real tracked changes, judged better than Microsoft’s offering.
