reply-classificationlisted

# Positive Reply Scoring ## Pipeline contract **Stage 17 of 20.** Runs after the human has sent the campaign. Reads replies from Smartlead (scripts below) OR `17-replies-raw.csv` (`lead_id, email, reply_text, replied_at`) exported from any sender. Writes `17-replies.csv` (adds `label`, `is_positive`, `next_action`) and `17-reply-score.json`. - Save to the run folder, not the `~/cold-email-ai-skills/` path below. - `unsubscribe` and `negative_hostile` rows go to the do-not-contact list in the same session — that list feeds stage 10's hard disqualifiers. - Positive rows hand off to [`/lead-qualification`](../lead-qualification/SKILL.md). Files live in `runs/<run>/`. Column definitions: [`/prospecting-system`](../prospecting-system/SKILL.md). Standalone use: ignore this block. **Reply rate tells you if people are paying attention. Positive reply rate tells you if they want what you're selling.** This skill computes the second. ## Why this exists A campaign can get 5% reply rate and still be a disaster. If 90% of those replies are "unsubscribe" and "not a fit," you're burning your domains for nothing. The metric that matters is: ``` positive_reply_rate = positive_replies / total_sent ``` Compared side-by-side: - Campaign A: 1% reply rate, 70% positive → 0.7% positive reply rate - Campaign B: 5% reply rate, 10% positive → 0.5% positive reply rate - Campaign A wins. ## Classification schema Every reply is classified into exactly one bucket: | Label | Meaning | Count as