Saleshandy Review Metrics

Saleshandy Review Metrics

Overview

Turns raw sequence stats into a diagnosis and a single recommended next action, using the benchmark table in reference.md.

Workflow

1. Get the sequence(s) — call list_sequences if the user hasn't given an ID, and ask which sequence(s) if more than one is active and it isn't obvious from context.
2. Call get_sequence_stats for a single sequence, or get_consolidated_stats for multiple sequences over a time period.
3. Compute the key ratios: open rate, reply rate, bounce rate, click rate (if links are used).
4. Compare each against the benchmark table in reference.md and identify the WORST outlier — the metric furthest below (or above, for bounce) the healthy range. That's today's diagnosis.
5. Map that outlier to its likely cause and ONE concrete fix from reference.md — don't dump the whole reference table on the user, just the relevant row(s).
6. If bounce rate is the outlier, treat it as urgent: recommend pausing the sequence and re-running saleshandy-verify-emails on the list before anything else, since continuing to send makes account health worse.
7. If the user wants to act on the recommendation (e.g. edit a step, adjust timing), hand off to saleshandy-build-sequence for the actual edit rather than mutating steps directly from this skill.

Example

User: "How's my fintech sequence doing?"

→ get_sequence_stats → open rate 58% (healthy), reply rate 0.8% (below 1-3% healthy range), bounce rate 0.9% (healthy) → Diagnosis: opens are fine, so subject lines/deliverability aren't the problem — replies are low, which points to messaging/offer relevance, not visibility. → Recommendation: "Reply rate is the weak point, not opens. Worth testing a step variant with a more specific/relevant offer or a clearer single ask — want me to draft one via saleshandy-build-sequence?"