📝 docs: add mandatory skill usage guidelines for reliable proactive invocation

Add critical section to CLAUDE.md covering:
- Skill vs Agent vs Direct Tools decision matrix
- Mandatory skill invocation rules with trigger conditions
- Proactive usage framework with right/wrong examples
- Skill chaining and coordination patterns
- Context management for skills (load → apply → unload)
- Failure handling for skill conflicts
- Decision tree for tool selection

CLAUDE.md

@@ -22,6 +22,115 @@ This file contains meta-instructions for how Claude should work with the ISA-Fro
 - Use bullet points and structured formatting for clarity
 - Only provide detailed explanations when complexity requires it
 
+## 🔴 CRITICAL: Mandatory Skill Usage
+
+**Skills are project-specific tools that MUST be used proactively for their domains.**
+
+### Skill vs Agent vs Direct Tools
+
+| Tool Type | Purpose | When to Use | Context Management |
+|-----------|---------|-------------|-------------------|
+| **Skills** | Domain-specific workflows (Angular, testing, architecture) | Writing/reviewing code in skill's domain | Load skill → follow instructions → unload |
+| **Agents** | Research & knowledge gathering | Finding docs, searching code, analysis | Use agent → extract findings → discard output |
+| **Direct Tools** | Single file operations | Reading specific known files | Use tool → process → done |
+
+### Mandatory Skill Invocation Rules
+
+**ALWAYS invoke skills when:**
+
+| Trigger | Required Skill | Why |
+|---------|---------------|-----|
+| Writing Angular templates | `angular-template` | Modern syntax (@if, @for, @defer) |
+| Writing HTML with interactivity | `html-template` | E2E attributes (data-what, data-which) + ARIA |
+| Applying Tailwind classes | `tailwind` | Design system consistency |
+| Writing Angular code | `logging` | Mandatory logging via @isa/core/logging |
+| Creating new library | `library-scaffolder` | Proper Nx setup + Vitest config |
+| Regenerating API clients | `swagger-sync-manager` | All 10 clients + validation |
+| Migrating to standalone | `standalone-component-migrator` | Complete migration workflow |
+| Migrating tests to Vitest | `test-migration-specialist` | Jest→Vitest conversion |
+| Fixing `any` types | `type-safety-engineer` | Add Zod schemas + type guards |
+| Checking architecture | `architecture-enforcer` | Import boundaries + circular deps |
+| Resolving circular deps | `circular-dependency-resolver` | Graph analysis + fix strategies |
+| API changes analysis | `api-change-analyzer` | Breaking change detection |
+| Git workflow | `git-workflow` | Branch naming + conventional commits |
+
+### Proactive Skill Usage Framework
+
+**"Proactive" means:**
+1. **Detect task domain automatically** - Don't wait for user to say "use skill X"
+2. **Invoke before starting work** - Load skill first, then execute
+3. **Apply throughout task** - Keep skill active for entire domain work
+4. **Validate with skill** - Use skill to review your own output
+
+**Example - WRONG:**
+```
+User: "Add a new Angular component with a form"
+Assistant: [Writes component without skills]
+User: "Did you use the Angular template skill?"
+Assistant: "Oh sorry, let me reload with the skill"
+```
+
+**Example - RIGHT:**
+```
+User: "Add a new Angular component with a form"
+Assistant: [Invokes angular-template skill]
+Assistant: [Invokes html-template skill]
+Assistant: [Invokes logging skill]
+Assistant: [Writes component following all skill guidelines]
+```
+
+### Skill Chaining & Coordination
+
+**Multiple skills often apply to same task:**
+
+| Task | Required Skill Chain | Order |
+|------|---------------------|-------|
+| New Angular component | `angular-template` → `html-template` → `logging` → `tailwind` | Template syntax → HTML attributes → Logging → Styling |
+| New library | `library-scaffolder` → `architecture-enforcer` | Scaffold → Validate structure |
+| API sync | `api-change-analyzer` → `swagger-sync-manager` | Analyze changes → Regenerate clients |
+| Component migration | `standalone-component-migrator` → `test-migration-specialist` | Migrate component → Migrate tests |
+
+**Skill chaining rules:**
+- Load ALL applicable skills at task start (via Skill tool)
+- Skills don't nest - they provide instructions you follow
+- Skills stay active for entire task scope
+- Validate final output against ALL loaded skills
+
+### Skill Context Management
+
+**Skills expand instructions into your context:**
+
+- ✅ **DO**: Load skill → internalize rules → follow throughout task
+- ❌ **DON'T**: Re-read skill instructions multiple times
+- ❌ **DON'T**: Quote skill instructions back to user
+- ❌ **DON'T**: Keep skill "open" after task completion
+
+**After task completion:**
+1. Verify work against skill requirements
+2. Summarize what was applied (1 sentence)
+3. Move on (skill context auto-clears next task)
+
+### Skill Failure Handling
+
+| Issue | Action |
+|-------|--------|
+| Skill not found | Verify skill name; ask user to check available skills |
+| Skill conflicts with user request | Note conflict; ask user for preference |
+| Multiple skills give conflicting rules | Follow most specific skill for current file type |
+| Skill instructions unclear | Use best judgment; document assumption in code comment |
+
+### Skills vs Agents - Decision Tree
+
+```
+Is this a code writing/reviewing task?
+├─ YES → Check if skill exists for domain
+│         ├─ Skill exists → Use Skill
+│         └─ No skill → Use direct tools
+└─ NO → Is this research/finding information?
+          ├─ YES → Use Agent (docs-researcher/Explore)
+          └─ NO → Use direct tools (Read/Edit/Bash)
+```
+
 ## Researching and Investigating the Codebase
 
 **🔴 MANDATORY: You MUST use subagents for research. Direct file reading/searching.**