persona-intel

I've been looking at how you're handling persona inference here—the approach of breaking down user context into structured attributes is solid, but I'm curious about the edge cases where persona signals conflict or are ambiguous.

Links:

• GitHub
• Your agentic skill in the SkillzWave marketplace

The TL;DR

You're at 79/100, which is solid C territory—good fundamentals with some gaps that are totally fixable. This is based on Anthropic's skill grading standards across five pillars. Your strongest area is Ease of Use (21/25)—the framework structure is intuitive. Weakest is Spec Compliance (11/15), mainly because your description is missing trigger phrases that help with discoverability.

What's Working Well

• Framework structure is clean. The 5-step approach (Identify → Research → Prioritize → Document → Brief) gives users a clear path without overwhelming them.
• Practical triggers defined. You've nailed the "When to Use" section with specific scenarios like "multi-persona discovery calls" and "exec briefing prep"—that's exactly what users need to know when to reach for this skill.
• Consistent terminology. "Persona," "discovery," "call brief"—terminology stays locked in throughout. No confusion.

The Big One: Missing Template Reference Files

Your templates are listed but not lived in. You mention "Persona one-pager," "Discovery cheat sheet," and "Exec briefing note," but there are no actual reference files showing what these look like filled out. This kills your Progressive Disclosure Architecture score (23/30) because all the content is crammed into one file.

The fix: Create three new reference files:

• references/persona-one-pager-template.md — Show a completed CFO persona card with real pains, proof points, objections
• `reference...