peggy

I've been digging into parser generators lately, and peggy's approach to grammar-driven parsing caught my attention. Your B-grade implementation shows solid fundamentals, but I'm curious about some of the design choices around error recovery and token handling.

Links:

• GitHub
• Your agentic skill in the SkillzWave marketplace

The TL;DR

You're at 81/100, solidly in B territory. This is based on Anthropic's skill grading rubric across five pillars. Your Ease of Use is the strongest area (21/25)—the metadata and triggers are dialed in. But Utility (16/20) is where you're losing points, mainly because there's no error handling or debugging guidance.

What's Working Well

• Triggers are spot-on. "PEG grammars", "parser generation", and "syntax definition" will activate exactly when someone needs this. That's the kind of discoverability that makes a skill actually get used.
• Token efficiency is excellent. 85 lines that pack real value—every section (Core Syntax, Rule Definitions, Built-in Functions) delivers with practical tables and examples. No fluff.
• Quick Start example is solid. Shows a complete arithmetic parser grammar and working TypeScript usage back-to-back. That's the right call for getting people rolling fast.

The Big One: Missing Error Handling & Debugging

This is holding you back 3+ points. Right now you're only showing the happy path—successful parsing. But in reality, grammars fail, parse errors happen, and people need guidance.

What to add: New section called "Error Handling" after CLI Usage. Show:

• The error object structure (e.location, e.expected, e.found)
• Try/catch wrapper example
• Common gotchas: left recursion causing infinite loops, rule order mattering, whitespace handling

Why it matters: Utility is about feedback loops—can someone debug when things...