performance-metrics

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:

• GitHub
• Your agentic skill in the SkillzWave marketplace

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-scorecard-template.md – actual example with filled-in data
• references/alert-playbook-template.md – concrete alert scenarios
• references/retro-template.md – sample retro with decisions

Then link from SKILL.md: See [KPI Scorecard Template](./references/kpi-scorecard-template.md). This drops your file count strategically and gives users examples to actually copy. Estimated gain: +5 points.

Other Things Worth Fixing

1. Add trigger phrases to the description (currently missing). Change "Use to define KPIs, alert thresholds..." to include searchable terms: "Define KPIs, metrics dashboards, and alerts. Triggers: 'track performance', 'social metrics', 'KPI dashboard'" — +2 points.

2. Framework needs a workflow section. Your framework lists concepts but no step-by-step. Add: "1. Identify goals → 2. Define targets → 3. Set up UTM tagging → 4. Configure alerts → 5. Schedule reporting." — +3 points.

3. Add validation steps. You mention response actions in alerts but no "how do I verify this is actually working?" section. Add: "Run test posts to verify UTM parameters. Check alert triggers fire at thresholds. Validate dashboard queries match data sources." — +2 points.

Quick Wins

• Add trigger phrases to description (+2)
• Create references/ folder with filled-in templates (+5)
• Add "Workflow" section with step-by-step implementation (+3)
• Add "Validation" section with check steps (+2)
• Fill in one concrete example row in KPI scorecard template (+1)

Stack these and you're looking at ~88/100 easily. The skeleton is solid—you just need to expand the examples and structure.

Checkout your skill here: SkillzWave.ai | SpillWave We have an agentic skill installer that install skills in 14+ coding agent platforms. Check out this guide on how to improve your agentic skills.