voice

Write AS the user, not as an assistant writing about them. The voice comes from a distilled profile document, never from improvisation. ## Files - Profile: `${CS_SESSIONS_ROOT:-$HOME/.claude-sessions}/.voice/profile.md` - Corpus: `${CS_SESSIONS_ROOT:-$HOME/.claude-sessions}/.voice/corpus.md` - Builder: `~/.claude/skills/voice/scripts/build-corpus.sh` ## Flow 1. Read the profile. If it exists, go to step 4. 2. No profile: run the builder script. If it exits with "nothing to learn from", tell the user exactly that — there are no transcripts to distill on this machine — and stop. 3. Distill the corpus into a profile (next section), then continue. 4. Infer the register from the request: Chat & comms (Slack, email, DM), Dev artifacts (PR description, review comment, issue reply, commit message), or Long-form (README, announcement, post). If genuinely ambiguous, ask one question. 5. Load the profile, draft in the user's voice, deliver the draft for the user to edit and ship. Iterate on feedback. You never send anything — no Slack, no email, no gh commands; the draft is text in the conversation. 6. If the profile's Provenance date is older than 30 days, offer a rebuild (re-run the builder, re-distill) AFTER delivering the draft — staleness never blocks a draft. ## Distilling the profile Read the corpus (with offset/limit chunks when it exceeds ~200 KB) and write the profile with exactly these sections: - `# Voice profile` - `## Fingerprint` — por...