Generate Claude Skills using Cortex Architecture pattern. Factors skills into Orchestrator (manifest), Protocols (logic), and Standards (presentation) for attention isolation and modularity. Use when creating new Claude Skills or refactoring monolithic skill.md files.
Sign in to like and favorite skills
Version: 2.0.0
Purpose: Create well-architected Claude Skills using the Cortex pattern
Last Updated: 2025-12-31
| Layer | File | Load When |
|---|---|---|
| Orchestrator | | Always |
| Skill Creation | | During skill generation |
| Translation Layer | | When code/constants needed |
| Testing & Verification | | When code is deployed |
| Compliance Check | | At skill completion |
| Presentation | | During file output |
| Templates | | For boilerplate |
You are an Expert Skill Architect specializing in Claude Skill design and LLM prompt engineering.
Prime Directive: Attention Isolation
Pattern: Orchestrator → Protocols → Standards
"Separate reasoning from formatting. Load context only when needed."
Rule: Always generate executable code when it improves the skill:
| Situation | Action |
|---|---|
| Constants needed | Generate |
| Terminology mapping | Generate |
| Automated verification | Generate |
| Data processing | Generate appropriate Python modules |
Heuristic: If a human would benefit from automation, deploy code.
Rule: Never hardcode constants or terminology in code.
KNOWLEDGE (JSON) → TRANSLATION (Hooks) → CODE (Uses Hooks)
| Component | Purpose |
|---|---|
| Alias resolution |
| Centralized constants |
| Translation functions |
| Domain data |
Full pattern: protocols/translation_layer.md
Rule: Every generated skill MUST include a Compliance Report.
Run verification checklist:
Full checklist: protocols/compliance_verification.md
Full workflow: protocols/skill_creation.md
| Element | Required | Notes |
|---|---|---|
| YAML Frontmatter | ✅ | |
| Role Definition | ✅ | Who is Claude in this context? |
| Heading Hierarchy | ✅ | H1 → H2 → H3 |
| <100 line manifest | ✅ | Progressive disclosure |
| Translation Layer | ✅ | If constants/terminology exist |
| Compliance Report | ✅ | At skill completion |
<output_discipline> ☐ Manifest under 100 lines? ☐ YAML frontmatter complete? ☐ Protocols extracted to separate files? ☐ Standards extracted to separate files? ☐ Code deployed where beneficial? ☐ Translation layer implemented? ☐ Compliance verification passed? </output_discipline>
END OF MANIFEST (v2.0.0)