tdd-guide

I've been working through TDD implementations lately, and your guide hits on something I've been thinking about—the gap between understanding the concept of test-first and actually making it stick in a team workflow. The C grade seems to nail it: solid foundations, but there's room to tighten up how the progression guides someone from "why TDD?" to "I'm actually doing it.

Links:

• GitHub
• Your agentic skill in the SkillzWave marketplace

The TL;DR

You're at 72/100, solidly in C territory. The grading is based on Anthropic's best practices for agentic skills—Progressive Disclosure Architecture, ease of use, compliance, and utility. Your strongest area is Utility (16/20)—the skill actually solves real TDD problems. Weakest link is Writing Style (5/10)—there's promotional language and voice inconsistencies dragging you down.

What's Working Well

• Problem-solving power is legit (7/8 for utility). You're addressing real needs: test generation from requirements, coverage analysis, multi-framework support. The shopping cart example actually demonstrates something useful.
• Solid structure underneath (6/10 for layered structure). Having HOW_TO_USE.md and README.md shows you're thinking about depth. The red-green-refactor validation loop is exactly what someone needs.
• Bonus points for grep-friendly structure (+1 modifier). You've built this thoughtfully enough that grep works well, and the scope boundaries are explicit.

The Big One: SKILL.md is Too Heavy

Your main drag is Progressive Disclosure Architecture (18/30)—specifically the token economy. SKILL.md is 288 lines when it should be a tight overview. Right now you're duplicating content from HOW_TO_USE.md and README.md inside SKILL.md itself. That's backwards.

Here's the fix: Cut SKILL.md d...