mph-voice-refresh
Installation
SKILL.md
MPH Voice Refresh
Keeps the VOICE.md corpus alive. Without this, the writer keeps reusing the same "Michael impersonations" until they sound canned.
When to invoke
- User asks to refresh / update / mine the voice corpus
- User says drafts are "sounding the same" or "you keep using that phrase"
- It's been more than ~3 weeks since last refresh (check the date at the bottom of VOICE.md)
Two sources, two miners
| Source | Script | What it captures |
|---|---|---|
Chat transcripts (~/.claude/projects/*/*.jsonl) |
scripts/mine_voice.py |
Unfiltered, conversational — tics like .., lol, or whatever, Ugh., mid-sentence self-corrections. The way Michael actually types. |
Substack RSS feed (mphinance.substack.com/feed) |
scripts/mine_feed.py |
Polished, published — paired openers, contradiction-filter constructions, punchy closers. The way Michael writes for readers. |
Both write to the same VOICE.md, but into separate sections. Don't mix them — chat voice has tics that don't belong in a Substack draft, and published voice has constructions that would sound forced in chat.