performance-metrics

31 stars 7 forks
28
C

Use to define KPIs, alert thresholds, and reporting cadences for social calendars.

Marketplace
Also in: ci cd networking data analysis

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/performance-metrics
skilz install gtmagents/gtm-agents/performance-metrics --agent opencode
skilz install gtmagents/gtm-agents/performance-metrics --agent codex
skilz install gtmagents/gtm-agents/performance-metrics --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/social-scheduler-orchestration/skills/performance-metrics ~/.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
Technical
Meta-Domain
media
Primary Domain
monitoring
Market Score
28

Agent Skill Grade

C
Score: 75/100 Click to see breakdown

Score Breakdown

Spec Compliance
11/15
PDA Architecture
20/30
Ease of Use
19/25
Writing Style
8/10
Utility
16/20
Modifiers: +1

Areas to Improve

  • Description needs trigger phrases
  • Missing Trigger Keywords in Description
  • No Layered Reference Structure

Recommendations

  • Address 1 high-severity issues first
  • Add trigger phrases to description for discoverability
  • Add table of contents for files over 100 lines

Graded: 2026-01-24

Developer Feedback

I took a look at your performance-metrics skill and noticed you're tackling a real pain point—most developers either skip metrics entirely or build something overly complex. Your approach lands at 75/100, which puts you in solid C territory with real potential.

Links:

The TL;DR

You're at 75/100, Grade C. This is based on Anthropic's five-pillar rubric for agentic skills. Your Writing Style scored strongest at 8/10—the technical voice is clean and objective. The weakness? Progressive Disclosure Architecture at 20/30 because everything's crammed into a single 32-line file with no layering. That's actually fixable and worth about 5-6 points if you restructure it.

What's Working Well

  • Writing is punchy and objective. You're not overselling anything. Phrases like "enforce UTM parameters" and "define test KPIs" are imperative and action-oriented—exactly what users need.
  • Real framework underneath. The five-part stack (Metric Stack → Attribution & Tagging → Alerting → Retro → Cadence) shows you've thought through the full lifecycle, not just the surface.
  • Practical scope. You're solving a genuine problem for social media campaigns, and the templates section shows you understand what users actually need to implement (scorecards, alert playbooks, retros).

The Big One: No Layered Structure (–5 points)

Your whole skill is 32 lines in one file. That works for tiny skills, but you've got templates and playbooks that deserve their own reference files. Right now, templates just list structure:

KPI scorecard (metric → target → actual → variance → owner → notes)

Here's the fix: Create a references/ folder with three files:

  • `references/kpi-score...

Report Security Issue

Found a security vulnerability in this agent skill?