chore: ai-config-toolkit 동기화

Author: kubrickcode

.claude/agents/claude-code-specialist.md

@@ -1,9 +1,9 @@
 ---
 name: claude-code-specialist
-description: Claude Code ecosystem optimization specialist. Diagnoses and improves CLAUDE.md, agents, skills, and commands configurations. Use PROACTIVELY when reviewing Claude Code setup, optimizing token costs, or eliminating redundancies and improving structure.
+description: Claude Code ecosystem optimization specialist. Diagnoses and improves CLAUDE.md, agents, skills, rules, and commands configurations. Use PROACTIVELY when reviewing Claude Code setup, optimizing token costs, or eliminating redundancies and improving structure.
 ---
 
-You are the Claude Code Specialist, a meta-cognitive agent specializing in diagnosing and optimizing the entire Claude Code ecosystem. Your expertise spans CLAUDE.md, agents, skills, commands, hooks, output-styles, settings.json, and MCP configurations.
+You are the Claude Code Specialist, a meta-cognitive agent specializing in diagnosing and optimizing the entire Claude Code ecosystem. Your expertise spans CLAUDE.md, agents, skills, rules, commands, hooks, output-styles, settings.json, and MCP configurations.
 
 ## Core Workflow
 
@@ -21,7 +21,7 @@ When invoked:
 Core knowledge areas:
 
 - **Frontmatter mechanics**: Auto-triggering patterns for agents and skills
-- **Tool selection criteria**: When to use agents vs skills vs commands vs direct tools
+- **Tool selection criteria**: When to use agents vs skills vs rules vs commands vs direct tools
 - **Token economics**: Cost measurement, optimization strategies, waste elimination
 - **Official compliance**: Latest code.claude.com/docs best practices and patterns
 - **Structural consistency**: Naming conventions, file organization, documentation alignment
@@ -31,7 +31,7 @@ Core knowledge areas:
 
 Identify and categorize issues:
 
-- **Redundancies**: Duplicate agents/skills serving same purpose
+- **Redundancies**: Duplicate agents/skills/rules serving same purpose
 - **Inefficiencies**: Suboptimal tool choices, excessive token usage, unnecessary nesting
 - **Gaps**: Missing best practices from official documentation
 - **Conflicts**: Inconsistent patterns or contradictory configurations

.claude/agents/code-reviewer.md

@@ -22,14 +22,7 @@ Identify work type:
 - **chore/config**: Minimal review (typos, config errors only)
 - **prototype**: Focus on core idea, skip detailed quality
 
-## Phase 2: Skill Loading
-
-1. List available skills: `ls .claude/skills/`
-2. Identify relevant skills based on changed file types/paths
-3. Read `SKILL.md` from each relevant skill directory
-4. Apply skill conventions during review
-
-## Phase 3: Scoped Review
+## Phase 2: Scoped Review
 
 1. Run `git diff` to see changes
 2. Focus ONLY on modified code
@@ -48,9 +41,9 @@ Identify work type:
 - Proper error handling
 - Test coverage
 - Performance considerations
-- Check for skill convention violations (from Phase 2)
+- Check for coding convention violations
 
-## Phase 4: Prioritized Feedback
+## Phase 3: Prioritized Feedback
 
 Format by priority:
 

.claude/agents/work-executor.md

@@ -1,6 +1,6 @@
 ---
 name: work-executor
-description: Principled work executor for general development tasks. Use when performing development work outside of workflow commands (workflow:analyze, workflow:plan, workflow:execute, workflow:validate). Ensures consistent quality standards through systematic task division, scope determination, testing strategies, and dependency management.
+description: Principled work executor for general development tasks. Use when performing development work outside of workflow commands (workflow-analyze, workflow-plan, workflow-execute, workflow-validate). Ensures consistent quality standards through systematic task division, scope determination, testing strategies, and dependency management.
 tools: Read, Write, Edit, Bash, Glob, Grep
 ---
 

.claude/commands/code-review.md

@@ -60,7 +60,7 @@ Focus areas:
 - Error handling: edge cases, error messages, recovery
 - Performance: obvious bottlenecks, inefficient patterns
 - Testing: coverage for critical paths
-- Skill compliance: verify against .claude/skills/ guidelines
+- Coding standards compliance
 
 Changes to review:
 {paste git diff or git show output}
@@ -194,7 +194,7 @@ Based on agent feedback, generate action items:
 
 - **Never modify code directly** - this command only performs review
 - **Agent autonomy**: code-reviewer and architect-reviewer may read files, run tests, or analyze dependencies as needed
-- **Skill guidelines**: code-reviewer automatically checks .claude/skills/ for violations
+- **Coding guidelines**: code-reviewer checks for coding standard violations
 - **Incremental reviews**: For large changes (>20 files), agents may focus on high-impact areas first
 - **Git safety**: All git commands are read-only (status, diff, log, show)