tanstack-start

I took a look at your tanstack-start skill and wanted to share some thoughts.

Links:

• GitHub
• Your agentic skill in the SkillzWave marketplace

The TL;DR

You're at 84/100, solid B-grade territory. This is based on Anthropic's skill best practices rubric. Your strongest area is Spec Compliance (14/15) — your frontmatter and naming are dialed in. The weakest spot is Progressive Disclosure Architecture (23/30) — mostly about how you're organizing the content rather than what's in it.

What's Working Well

• Trigger coverage is excellent — You've got explicit mentions, API patterns, intents, and even common typos (tankstack, tan stack). That's how you get found.
• Spec Compliance is nearly perfect — Your YAML is clean, naming follows convention, and your description actually tells people when to use this.
• Real problem-solving chops — You're addressing actual TanStack Start patterns: file-based routing, SSR, server functions, auth flows. This fills a real gap in the docs.
• Code examples throughout — Multiple patterns covering routing, data loading, and server functions. The file_structure section gives people a clear template to start from.

The Big One: Your File Structure Is Hitting a Wall

At 370 lines, your SKILL.md is crossing the threshold where a single monolithic file starts working against you. Right now, everything is inline — which is fine for discovery but inefficient for deep dives.

The fix: Split into references. Keep mcp_first and quick_start in SKILL.md (the hook), but move the meaty stuff into references/:

• references/routing_patterns.md — nested routes, dynamic segments, search params
• references/data_loading.md — loaders, server functions, streaming
• references/authentication.md — auth pattern...