save-play-library

31 stars 7 forks
28
F

Use to catalog churn/expansion plays tied to specific signals, cohorts, and owners.

Marketplace
Also in: ci cd

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/save-play-library
skilz install gtmagents/gtm-agents/save-play-library --agent opencode
skilz install gtmagents/gtm-agents/save-play-library --agent codex
skilz install gtmagents/gtm-agents/save-play-library --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/customer-analytics/skills/save-play-library ~/.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
javascript
Market Score
28

Agent Skill Grade

F
Score: 58/100 Click to see breakdown

Score Breakdown

Spec Compliance
11/15
PDA Architecture
15/30
Ease of Use
15/25
Writing Style
6/10
Utility
10/20
Modifiers: +1

Areas to Improve

  • Description needs trigger phrases
  • Missing Template Files
  • Weak Trigger Terms

Recommendations

  • Focus on improving Pda (currently 15/30)
  • Focus on improving Utility (currently 10/20)
  • Address 2 high-severity issues first

Graded: 2026-01-24

Developer Feedback

I took a quick look at your save-play-library skill and noticed you're tackling a pretty common pattern—managing persistent state for interactive applications—but there's quite a bit of room to tighten up how you're presenting the solution to developers.

Links:

The TL;DR

You're at 58/100, which lands in F territory. This is based on Anthropic's Progressive Disclosure Architecture standards. Your strongest area is Spec Compliance (11/15)—the frontmatter and naming conventions are solid. But Utility is dragging you down hard at 10/20, and PDA is sitting at 15/30 because you're missing actual reference files and templates.

What's Working Well

  • Valid YAML frontmatter - Your metadata structure is clean and follows conventions correctly
  • Consistent terminology - Using "play" throughout keeps things coherent
  • Reasonable conceptual framework - The 5-step structure (Signal Definition → Play Blueprint → Feedback Loop) makes logical sense for the workflow
  • Appropriate scope - You're not overengineering; the skill focuses on a specific use case

The Big One: Missing Templates and Examples

This is your biggest blocker. You list three templates—"Play card", "Experiment tracker", "Post-play retrospective form"—but only as bullet points. Developers have no actual templates to reference, no fill-in-the-blank examples, no input/output pairs showing what a real save play looks like.

The fix: Create a references/ directory with three actual markdown files:

  • references/play-card-template.md - A fillable template with fields like Trigger, Action Steps, Owner, KPI, Timeline
  • references/experiment-tracker.md - Column headers and a sample row showing control vs. test cohor...

Report Security Issue

Found a security vulnerability in this agent skill?