Drop-off Investigator
Find where and why users drop out of one flow using events, segment cuts, and replays, then rank what to fix first.
Before & after
Same prompt, same agent — the only difference is the skill.
I can help analyze your customer success team's data and trends. You'd definitely need to share your ticket volumes, response times, customer satisfaction scores, and any other performance metrics you're tracking. What time period are you most concerned about analyzing? Is ticket volume increasing in specific categories or for specific customer segments? I could help identify patterns and trends, but I'd need more detailed context about your support system infrastructure and your typical customer base.
CS PRODUCTIVITY ANALYSIS — TICKET SURGE ROOT CAUSE ANALYSIS: METRICS SUMMARY (90-day period): Tickets opened: 1,240 total (+22% increase vs prior quarter). Tickets closed: 980 total (-8% decrease vs prior quarter). Open backlog: 260 tickets (baseline was 80, growth of 225%). Average ticket resolution time: 3.2 days (baseline was 2.1 days, +52% increase). BOTTLENECK IDENTIFICATION & ANALYSIS: 1. Pre-sales misalignment (27% of all tickets): 340 tickets are customer onboarding issues caused by sales team overpromising features not yet built. Customer expectations misaligned with product reality. 2. Knowledge base content decay (17% of all tickets): 210 tickets contain questions already answered in existing documentation, but customers cannot find answers due to outdated search indexing. Last KB update: 2026-06-12 (8 weeks old). No search index built. 3. Team understaffing (critical issue): Team has capacity for 1,200 tickets per quarter. Current inbound rate 1,240 tickets per quarter. Operating at 103% capacity—unsustainable. TEAM PRODUCTIVITY BREAKDOWN: Senior CS representatives handle 45 tickets/week average (efficient). Junior CS representatives handle 28/week average. Junior reps spend 40% of their time researching answers instead of actually resolving tickets. QUICK WINS (2-week impact, low cost): Update knowledge base top 5 FAQ topics. Brief sales team on realistic onboarding timeline. Pair junior reps with seniors 2 hours per week. Projected ticket backlog reduction: 15%. MEDIUM-TERM FIX (6 weeks): Hire 1 additional full-time CS representative. Projects backlog approaching zero by 2026-09-30. WARNING ALERT: Current unsustainable trajectory cannot continue beyond Q3 2026 without organizational intervention and hiring.
About this skill
Answer the question 'why aren't users finishing this?' with evidence instead of opinions. The skill measures the funnel, cuts it until the drop-off is explained, checks the pattern against replays and tickets, and ranks what to fix.
What it does
- Validates tracking first: duplicate events, identity stitching, bots, and tracking changes
- Builds the step funnel with conversion windows and time between steps
- Segments the worst step by platform, source, account attributes, path, and release timing, showing segment sizes
- Checks top segments against 10-20 replays or tickets
- Estimates recoverable users per finding and ranks findings by impact and confidence
What you get
A findings memo that answers the question up front, with the funnel table, ranked findings and evidence, what to change first, what was ruled out, and next questions.
Best for
Product managers and analysts using Amplitude, Mixpanel, PostHog, GA4, or SQL who need to explain a leaky flow.
SKILL.md preview
---
name: drop-off-investigator
description: Investigate one product question - usually "where and why do users drop off in this flow" - using event data, segment cuts, and qualitative evidence, then deliver a findings memo that ranks what to change first and states how confident each finding is. Use when the user asks why a flow underperforms, where users get stuck, why a feature isn't adopted, or wants a specific analytics question answered from Amplitude, Mixpanel, PostHog, GA4, or SQL, including casual asks like "why are people bailing on signup", "where do we lose users in checkout", or "is this funnel number real".
---
# Drop-off Investigator
… (sign up to view the full skill)More business & ops skills
View all Business & Ops skills →Product Practice Diagnostic
Trace a product-team symptom (unused features, roadmap churn, priority fights) to the broken stage of the loop and fix one thing first.
Feature Launch Go-to-Market Plan
Plan one feature launch: tier, plan access, audience messages, readiness gates for support, sales, billing, and docs, and success metrics.
Pricing Tier and Packaging Diagnosis
Finds why your pricing tiers underperform and redesigns value metric, fences, price gaps, and upgrade triggers with a migration plan.
Product Specs, Roadmaps, and Research Decisions
Turn customer evidence into testable PRDs, dependency-aware roadmaps, and stakeholder updates with clear decisions and tradeoffs.