Claude Code architecture advisor. Classifies knowledge and delegates to appropriate skills. Use when deciding where to put new knowledge or restructuring components.
/plugin marketplace add wayne930242/Reflexive-Claude-Code/plugin install wayne930242-ace-core-plugins-ace-core@wayne930242/Reflexive-Claude-CodeThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Classify knowledge and delegate to the right skill. You are an advisor, not an executor.
You MUST invoke the Skill tool to delegate to the appropriate skill. NEVER perform the work yourself.
When you identify a task type:
Example delegation flow:
User: "Create a skill for handling PDF files"
→ Classify: This is a CAPABILITY → delegate to write-skill
→ Action: Invoke Skill tool with skill="write-skill"
→ DO NOT: Write the SKILL.md yourself
| Task | Delegate To | Reviewer |
|---|---|---|
Create/update CLAUDE.md with <law> | write-claude-md skill | - |
| Create/update skill | write-skill skill | agent-architect |
| Create/update command | write-command skill | agent-architect |
| Create/update subagent | write-subagent skill | agent-architect |
| Create/update rule (convention) | write-rules skill | agent-architect |
| Create/update hook | write-hook skill | - |
| Improve existing skill | /improve-skill command | - |
| Reflect on learnings | /reflect command | agent-architect |
| Refactor all skills | /refactor-skills command | agent-architect |
┌─────────────────────────────────────────────────────────────────┐
│ Must Claude display this at the START of EVERY response? │
│ (To prevent context drift over long conversations) │
├─────────────────────────────────────────────────────────────────┤
│ YES → IMMUTABLE LAW │
│ Delegate: write-claude-md skill │
│ Format: <law> block with Self-Reinforcing Display │
│ Examples: Communication discipline, Skill discovery, │
│ Parallel processing, Self-reinforcing display │
├─────────────────────────────────────────────────────────────────┤
│ NO → Continue to Step 2 │
└─────────────────────────────────────────────────────────────────┘
┌─────────────────────────────────────────────────────────────────┐
│ A. CAPABILITY - "How to do something" │
│ ─────────────────────────────────────────────────────────────│
│ Delegate: write-skill skill │
│ Format: SKILL.md < 200 lines, references/ for details │
│ Trigger: Description contains "Use when..." │
│ Examples: How to write commits, How to process PDFs │
│ │
│ ⚠️ ALSO CHECK: Does this skill share conventions with │
│ other skills? If YES → Also delegate to write-rules │
├─────────────────────────────────────────────────────────────────┤
│ B. USER WORKFLOW - "Explicit /command invocation" │
│ ─────────────────────────────────────────────────────────────│
│ Delegate: write-command skill │
│ Format: Orchestrate skills, don't duplicate content │
│ Trigger: User types /command-name │
│ Examples: /reflect, /refactor-skills, /improve-skill │
│ │
│ ⚠️ RULE: Commands MUST reference skills, not duplicate │
│ "Use the `write-skill` skill to..." NOT inline steps │
├─────────────────────────────────────────────────────────────────┤
│ C. SPECIALIZED AGENT - "Isolated context for large tasks" │
│ ─────────────────────────────────────────────────────────────│
│ Delegate: write-subagent skill │
│ Format: Limited tools, auto-loads skills via skills: field │
│ Trigger: Task tool with subagent_type │
│ Examples: code-reviewer, test-runner, explore agent │
├─────────────────────────────────────────────────────────────────┤
│ D. STATIC CHECK - "Quality gate / automated enforcement" │
│ ─────────────────────────────────────────────────────────────│
│ Delegate: write-hook skill │
│ Format: Script in .claude/hooks/, config in settings.json │
│ Trigger: Event-based (PreToolUse, PostToolUse, etc.) │
│ Examples: Linting, formatting, type checking │
│ │
│ ⚠️ Exit code 2 = block action, other = warning only │
├─────────────────────────────────────────────────────────────────┤
│ E. SHARED CONVENTION - "Guideline used by multiple skills" │
│ ─────────────────────────────────────────────────────────────│
│ Delegate: write-rules skill │
│ Format: < 50 lines, paths: for domain-specific │
│ Trigger: Auto-injected into context │
│ Examples: Code style, API conventions, testing guidelines │
│ │
│ ⚠️ Rules are CONVENTIONS, not LAWS │
│ Lower priority, no Self-Reinforcing Display │
└─────────────────────────────────────────────────────────────────┘
After delegation, agent-architect reviews:
□ Single Source of Truth - Knowledge lives in ONE place only
□ No Duplication - Commands reference skills, not duplicate
□ Correct Priority - Laws > Skills > Rules
□ Proper Triggers - Skills have "Use when...", Commands are explicit
□ Size Limits - Rules < 50 lines, Skills < 200 lines
| Component | Location | Key Rule |
|---|---|---|
| CLAUDE.md | ./CLAUDE.md | <law> for constitution |
| Skills | .claude/skills/*/SKILL.md | < 200 lines |
| Commands | .claude/commands/*.md | Orchestrate, don't duplicate |
| Subagents | .claude/agents/*.md | Isolated context |
| Hooks | .claude/hooks/ | Exit 2 blocks |
| Rules | .claude/rules/*.md | < 50 lines, conventions only |
<law>Will:
Will NOT:
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.