conversion-diagnostic-kit

31 stars 7 forks
28
D

Structured approach for investigating funnel issues across e-commerce experiences.

Marketplace

Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security

Installation for Agentic Skill

View all platforms →
skilz install gtmagents/gtm-agents/conversion-diagnostic-kit
skilz install gtmagents/gtm-agents/conversion-diagnostic-kit --agent opencode
skilz install gtmagents/gtm-agents/conversion-diagnostic-kit --agent codex
skilz install gtmagents/gtm-agents/conversion-diagnostic-kit --agent gemini

First time? Install Skilz: pip install skilz

Works with 22+ AI coding assistants

Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...

View All Agents
Download Agent Skill ZIP

Extract and copy to ~/.claude/skills/ then restart Claude Desktop

1. Clone the repository:
git clone https://github.com/gtmagents/gtm-agents
2. Copy the agent skill directory:
cp -r gtm-agents/plugins/e-commerce/skills/conversion-diagnostic-kit ~/.claude/skills/

Need detailed installation help? Check our platform-specific guides:

Related Agentic Skills

Agentic Skill Details

Repository
gtm-agents
Stars
31
Forks
7
Type
Non-Technical
Meta-Domain
development
Primary Domain
github
Market Score
28

Agent Skill Grade

D
Score: 66/100 Click to see breakdown

Score Breakdown

Spec Compliance
11/15
PDA Architecture
18/30
Ease of Use
18/25
Writing Style
7/10
Utility
11/20
Modifiers: +1

Areas to Improve

  • Description needs trigger phrases
  • Missing Reference Files for Templates
  • Vague Description Missing Triggers

Recommendations

  • Focus on improving Utility (currently 11/20)
  • Address 3 high-severity issues first
  • Add trigger phrases to description for discoverability

Graded: 2026-01-24

Developer Feedback

I've been digging into conversion optimization toolkits, and your diagnostic approach is interesting—though the execution feels like it's caught between being a reference guide and an interactive tool. What's the vision here: is this meant to help developers understand conversion problems or solve them?

Links:

The TL;DR

You're at 66/100, solidly in D territory. This is based on Anthropic's progressive disclosure architecture standards for agentic skills. Your strongest area is spec compliance (11/15)—the frontmatter is clean. Your weakest is utility (11/20)—the framework describes what to do but doesn't actually enable developers to do it.

What's Working Well

  • Valid YAML frontmatter - Name follows conventions perfectly, and the structure is technically sound
  • Consistent terminology - "Signal Stack," "Segmentation Grid," "Conversion Taxonomy"—you're building a coherent mental model
  • Real-world focus - You're tackling an actual gap (conversion diagnostics), not solving problems that don't exist

The Big One: Missing Templates & Reference Files

Here's what's eating 6+ points: you mention three templates (workbook, standup agenda, experiment brief) but don't actually provide them. This kills your utility score because developers are left saying, "okay, how do I structure this stuff?"

Fix: Create a references/ directory with actual files:

  • references/templates/diagnostic-workbook.md - Data inputs, findings capture format
  • references/templates/standup-agenda.md - Cross-functional war room structure
  • references/templates/experiment-brief.md - Hypothesis, KPIs, guardrails template

Even stub templates would add 6 points because they shift this ...

Report Security Issue

Found a security vulnerability in this agent skill?