I notice you're tackling UX research and design as a skill—that's a territory where most tool-builders stay surface-level, so I'm curious how you're structuring the progression from research fundamentals to actual design decisions.
Links:
The TL;DR
You're at 64/100, solidly in D territory. This is based on Anthropic's 5-pillar framework. Your strongest area is Spec Compliance (12/15)—the frontmatter is clean and triggers are well-chosen. The real drag is Progressive Disclosure Architecture (13/30), where you're missing the layered reference structure that makes skills actually teachable.
What's Working Well
- Good trigger coverage: "user research", "persona creation", "journey mapping" will catch the right moments when Claude needs this skill
- Real working code: Your persona generator script actually produces output with confidence scoring, not just theoretical
- Correct YAML structure: No metadata issues, just straightforward and valid
The Big One: Missing Reference Architecture
Here's what's holding you back—SKILL.md is 300 words of overview, but the actual smarts are buried in a 150+ line Python script. Users have no guide for when to use what, or how the pieces fit together.
The fix: Create a references/ directory with layered docs:
references/persona-methodology.md - detailed methodology (what makes a persona valid?)references/journey-mapping-guide.md - step-by-step journey mappingreferences/example-personas.md - 2-3 real output examples showing what "good" looks like
Then in SKILL.md, add a Research Workflow section with numbered steps that tie back to these docs. This alone buys you +6 points by fixing the PDA score.
Other Things Worth Fixing
-
No usage examples in SKILL.md - Show what the persona generator outputs with actual sample data. Right now users can't tell if they're using it right. (+3 points)
-
Incomplete capabilities list - You claim "usability testing frameworks" and "research synthesis" but there's no script or guidance for these. Either remove them or add them properly. (+2 points)
-
Script needs a TOC - Your persona_generator.py is past 100 lines but has no table of contents. Add a docstring that lists main classes and helper functions so people can navigate it. (+2 points)
-
Marketing language creeping in - "Comprehensive toolkit" reads like marketing copy. Just say "Provides research methods and scripts for user-centered experience design." (+1 point)
Quick Wins
- Highest impact: Add
references/ directory with persona methodology + example outputs → +6 pts
- Next: Create numbered workflow in SKILL.md linking to those references → +3 pts
- Easy: Add sample input/output to the script section → +3 pts
- Polish: Remove unimplemented capabilities or back them up with guides → +2 pts
Checkout your skill here: [SkillzWave.ai](https://skillzwave.ai) | [SpillWave](https://spillwave.com) 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.
I notice you're tackling UX research and design as a skill—that's a territory where most tool-builders stay surface-level, so I'm curious how you're structuring the progression from research fundamentals to actual design decisions.
Links:
The TL;DR
You're at 64/100, solidly in D territory. This is based on Anthropic's 5-pillar framework. Your strongest area is Spec Compliance (12/15)—the frontmatter is clean and triggers are well-chosen. The real drag is Progressive Disclosure Architecture (13/30), where you're missing the layered reference structure that makes skills actually teachable.
What's Working Well
The Big One: Missing Reference Architecture
Here's what's holding you back—SKILL.md is 300 words of overview, but the actual smarts are buried in a 150+ line Python script. Users have no guide for when to use what, or how the pieces fit together.
The fix: Create a
references/directory with layered docs:references/persona-methodology.md- detailed methodology (what makes a persona valid?)references/journey-mapping-guide.md- step-by-step journey mappingreferences/example-personas.md- 2-3 real output examples showing what "good" looks likeThen in SKILL.md, add a Research Workflow section with numbered steps that tie back to these docs. This alone buys you +6 points by fixing the PDA score.
Other Things Worth Fixing
No usage examples in SKILL.md - Show what the persona generator outputs with actual sample data. Right now users can't tell if they're using it right. (+3 points)
Incomplete capabilities list - You claim "usability testing frameworks" and "research synthesis" but there's no script or guidance for these. Either remove them or add them properly. (+2 points)
Script needs a TOC - Your persona_generator.py is past 100 lines but has no table of contents. Add a docstring that lists main classes and helper functions so people can navigate it. (+2 points)
Marketing language creeping in - "Comprehensive toolkit" reads like marketing copy. Just say "Provides research methods and scripts for user-centered experience design." (+1 point)
Quick Wins
references/directory with persona methodology + example outputs → +6 ptsCheckout your skill here: [SkillzWave.ai](https://skillzwave.ai) | [SpillWave](https://spillwave.com) 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.