markdownlint

I took a look at your markdownlint skill and wanted to share some thoughts.

Links:

• GitHub
• Your agentic skill in the SkillzWave marketplace

The TL;DR

You're at 62/100, solidly in D grade territory. This is based on Anthropic's best practices for agentic skills. Your strongest area is Ease of Use (19/25) — the triggers and metadata are genuinely good. But Progressive Disclosure Architecture (14/30) and Writing Style (5/10) are dragging things down. The good news? This is fixable with some focused restructuring.

What's Working Well

• Solid trigger coverage — "format", "clean", "lint", "validate" are all natural activation phrases. Users will find this when they need it.
• Good command examples — You've got lots of markdownlint-cli2 usage patterns scattered throughout, which shows real-world thinking.
• Clear troubleshooting section — You included a dedicated troubleshooting area, which shows you're thinking about failure modes.

The Big One: You're Fighting Architecture

Right now, everything lives in one 373-line SKILL.md file. That's the main momentum killer. When a skill gets over ~100 lines, it needs a references/ directory to distribute the content.

Here's what I'd do: Create two reference files:

1. references/rules.md — Move all 30+ rule descriptions here (MD001, MD002, etc.)
2. references/config-examples.md — Move the config templates and examples here

Then trim SKILL.md down to usage, basic workflow, and troubleshooting (~100 lines max). This gets you +8 points immediately on Progressive Disclosure Architecture, plus it makes the skill actually scannable.

The layered structure isn't just about score — it's about how Claude uses your skill. Short, focused entry points work bette...