keyword-research

I've been exploring how different tools approach keyword research, and I noticed your skill takes a pretty pragmatic angle on it—curious what drove some of your design choices, especially around the balance between comprehensiveness and keeping things lightweight for developers.

Links:

• GitHub
• Your agentic skill in the SkillzWave marketplace

The TL;DR

You're at 77/100, which puts you solidly in C territory—the skill works and has real value, but there are some gaps keeping you from the 80+ range. The framework is tight and the writing is clean (9/10 on style), but you're missing some structural pieces that would level up the utility and discoverability.

What's Working Well

• Writing is sharp. No marketing fluff, every sentence earns its place. The tone is consistently instructional and the voice stays authoritative throughout the 5-step framework.
• Clear workflow structure. Those five steps (Kicking off, Validating, Refreshing, and the rest) give developers a concrete path forward rather than abstract concepts.
• Efficient use of space. You're not bloated—the skill respects token budgets while still covering the essentials of keyword research strategy.
• Consistent terminology. Terms like "cluster," "intent," "SERP," and "pillar page" are used consistently, which makes it easier to follow the mental model.

The Big One: Missing Reference Files

This is what's costing you the most points—you mention templates (cluster worksheet, SERP teardown table, opportunity calculator) but don't actually provide them as separate files. This hurts you in two ways:

1. Progressive Disclosure Architecture (20/30): You're maxing out a single-file skill when layered references would be way more efficient. Developers have to interpret template structures from y...