docs: sync README, CLAUDE.md, AGENTS.md with latest skill changes

- Add 93-tui-designer to all doc files and directory layouts
- Remove phantom 42-jamie-journal-editor (directory never existed)
- Update GTM directory names: 61-gtm-manager → 61-gtm-editor,
  62-gtm-guardian → 62-gtm-validator in CLAUDE.md layout
- Fix skill count: README 64→62, AGENTS.md 52→62
- Add .claude/commands/ slash command definitions
- Add SEO comprehensive audit gotcha notes (JHR, SLA)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

custom-skills/11-seo-comprehensive-audit/code/gotcha/JHR-josunhotel.md

@@ -0,0 +1,28 @@
+# JHR — josunhotel.com Gotchas
+
+Client: **JHR** (Josun Hotels & Resorts / 조선호텔앤리조트)
+Domain: josunhotel.com + subdomains (gjb, gjj, jpg, grp)
+
+---
+
+## 1. Intentionally Truncated Directory Names in robots.txt
+
+**Date discovered**: 2026-03-20
+**Audit ID**: COMP-20260320-001
+
+The following `Disallow` paths in robots.txt look like typos but are **intentional directory names** on the server:
+
+| robots.txt path | Looks like it should be | Actual status |
+|-----------------|------------------------|---------------|
+| `/cnfirm` | `/confirm` | **Intentional** — real directory name |
+| `/mber` | `/member` | **Intentional** — real directory name |
+
+**Do NOT recommend renaming these** in audit reports. The server-side application uses these truncated names by design.
+
+### Context
+
+The josunhotel.com backend (Java/.do endpoints) uses shortened directory names for certain internal paths. This is likely a legacy naming convention from the original application architecture.
+
+### Audit Impact
+
+When running Technical SEO audits (Stage 1), skip the "typo in Disallow paths" finding for `/cnfirm` and `/mber`. These are valid paths that correctly block crawler access to confirmation and member-related pages.