Feedback on your pattern-finder skill

[RichardHightower]

I took a look at your pattern-finder skill and wanted to share some thoughts.

Links:

• GitHub
• Your agentic skill in the SkillzWave marketplace

The TL;DR

You're at 71/100, which puts you solidly in C territory — adequate with some gaps. Based on Anthropic's best practices, your strongest area is Spec Compliance (13/15 — your YAML frontmatter and naming conventions are spot on). The biggest drag is Progressive Disclosure Architecture at 18/30 — you've got a single flat file with no layered structure, which hurts extensibility.

What's Working Well

• Solid spec compliance. Your YAML is valid, naming follows conventions (hyphen-case), and your description includes good trigger coverage. That's the foundation done right.
• Clear, concise metadata. You're not bloating the skill with marketing language — it's purely instructional, which is exactly what developers need.
• Good concrete examples. Your command examples for common patterns are practical and give users something to work with immediately.

The Big One: No Progressive Disclosure Structure

This is what's holding you back from a B grade. Right now, everything lives in a single 48-line SKILL.md with no references/ directory for complex scenarios.

Here's why it matters: as users hit edge cases (combining patterns, custom syntax, troubleshooting), they've got nowhere to go. You're forcing them into a flat file that doesn't scale.

The fix: Create references/advanced-patterns.md with guidance on:

• Pattern combination strategies
• Custom pattern syntax beyond the basics
• Common no-results scenarios and how to refine searches

This alone bumps you up ~3 points and signals you're thinking about user progression.

Other Things Worth Fixing

1. Redundant trigger documentation — You're repeating examples across your metadata description, "When to Use" section, AND "Example Triggers" section. Consolidate into metadata + one examples section. Clean up ~1 point.

2. No validation steps — Your 3-step workflow (Identify → Run → Returns) has no error handling. Add: "If pattern search returns no results, try broader pattern terms or check indexing status." This matters for utility scoring (~2 points).

3. Missing output example — You describe what users get but don't show actual command output with file paths or line numbers. One concrete before/after example goes a long way (~1 point).

Quick Wins

Most impactful first:

• Add references/advanced-patterns.md for layered structure (+3 points)
• Add validation/error handling step to workflow (+2 points)
• Consolidate trigger redundancy across sections (+1 point)
• Show actual command output example (+1 point)

These four changes get you close to 78/100 (solid B range).

---

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.