Layers Orient

This is the diagnostic entry point for the seven-layer design framework. It runs a fast audit across all layers (observed behaviour through to surface design), identifies which layer is the actual bottleneck, and tells you which specific skill to run next. The key insight is distinguishing between layers that are genuinely strong versus ones that just look solid because they're built on assumptions. You answer a few questions about your design situation, get a state table showing where decisions are weak or missing, and walk away with a named bottleneck and a specific recommendation. It's meant to be quick, not a deep dive into any one layer.

skills.sh installs: 2K
GitHub stars: 314
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add jamiemill/layers-skills --skill layers-orient --agent claude-code

Installs into .claude/skills of the current project.

Files

/layers-orient

Assumes /layers-intro has been loaded for framework context.

Orient is a rapid diagnostic — the front door for finding the live decisions the other skills then work. It maps the current state of decisions across all seven layers, identifies the bottleneck — the lowest layer with unresolved or risky decisions — and recommends where to focus next.

It is not a deep dive into any layer. That's what the individual layer skills are for. Orient answers the prior question: which layer deserves attention most urgently? Keep it fast and light — the output is a short audit and one recommendation, not a report.

What it assesses:

Whether key decisions have been made at each layer, and how solidly
Whether decisions treated as solid are actually assumptions
Which layer is the most foundational with unresolved work, creating risk for everything above

Quality signals — when orient is done well:

The bottleneck layer is specifically named, not vaguely gestured at
Assumed layers are distinguished from Strong ones — they require different responses
The recommendation connects to a specific skill with a clear reason