Diagnose Conversion Drop

Investigates funnel drop-offs, performance issues, and UX blockers for ecommerce sites.

Published by @gtmagents·0 agent reads / 30d·0 saves·Updated June 14, 2026

Command: diagnose-conversion-drop

Inputs

window – lookback window (7d, 14d, 30d, campaign).
segments – comma-separated segments (device, channel, geography, campaign).
focus – funnel stage (landing, pdp, cart, checkout, post-purchase).
include-voc – true/false to ingest VOC/CSAT comments.
format – dashboard | memo | worksheet.

Workflow

Data Aggregation – collect analytics, attribution, heatmap, replay, and performance metrics.
Segment Analysis – compare segments vs baseline, highlight anomalies.
Root Cause Mapping – correlate issues to UX, inventory, promo, or tech factors.
Experiment & Fix List – prioritize remediations with impact/effort.
Packaging – deliver requested format with visuals and recommended owners.

Outputs

Funnel diagnostic report with charts/tables per stage.
Prioritized issue + experiment backlog with severity.
Alert summary for site performance/checkout reliability.

Agent/Skill Invocations

conversion-ops-lead – drives diagnostics + recommendations.
growth-merchandising-director – reviews merchandising/promo impacts.
conversion-diagnostic-kit skill – ensures structured analysis.
site-performance-watch skill – layers in performance telemetry.

More on the bench

Vendor Management

Evaluate, compare, and manage vendor relationships. Trigger with "evaluate this vendor", "compare vendors", "vendor review", "should we renew", "RFP", or when the user is making procurement or vendor decisions.

sales-gtm-revops+1

Qbr Builder

Create Quarterly Business Reviews with account health scores, usage analytics, ROI analysis, expansion opportunities, and risk mitigation

customer-success+1

Escalation

Structure and package support escalations for engineering, product, or leadership with full context, reproduction steps, and business impact. Use when an issue needs to go beyond support, when writing an escalation brief, or when assessing whether an issue warrants escalation.

customer-success+2

Sharebench · Public bench

Connect via MCP.

Add the public bench to any AI tool. Your agents read every artifact you see — no signup needed.

1Pick your tool

# Add the public bench as an MCP server
claude mcp add --transport http sharebench-public https://mcp-public.sharebench.ai

# Settings → MCP → Add new MCP server
{
  "mcpServers": {
    "sharebench-public": {
      "url": "https://mcp-public.sharebench.ai"
    }
  }
}

# Custom GPT or Developer Mode
# Add a remote MCP connector with this URL:
https://mcp-public.sharebench.ai

# Append to ~/.codex/config.toml
[mcp_servers.sharebench_public]
url = "https://mcp-public.sharebench.ai"

2Ask your agent for an artifact

Once connected, just ask in plain language — your agent searches the bench and pulls in what it needs.“Pull the brand voice from sharebench and rewrite this draft.”