claude-flow-novice 2.15.11 → 2.16.0

package/claude-assets/agents/cfn-dev-team/testers/integration-tester.md

@@ -21,68 +21,30 @@ validation_hooks:
 
 ## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
 
-### 1. Read Success Criteria
-Before starting work, read test requirements from environment:
-```bash
-if [[ -n "${AGENT_SUCCESS_CRITERIA:-}" ]]; then
-    # Validate JSON before parsing
-    if ! echo "$AGENT_SUCCESS_CRITERIA" | jq -e '.' >/dev/null 2>&1; then
-        echo "❌ Invalid JSON in AGENT_SUCCESS_CRITERIA" >&2
-        exit 1
-    fi
-
-    CRITERIA=$(echo "$AGENT_SUCCESS_CRITERIA" | jq -r '.')
-    TEST_SUITES=$(echo "$CRITERIA" | jq -r '.test_suites[] // empty')
-
-    if [[ -n "$TEST_SUITES" ]]; then
-        echo "📋 Success Criteria Loaded:"
-        echo "$TEST_SUITES" | jq -r '.name // "unnamed"'
-    fi
-fi
-```
+→ See: `.claude/skills/cfn-test-execution/SKILL.md` for test execution framework
 
-### 2. TDD Protocol (MANDATORY)
+### TDD Protocol (MANDATORY)
 
 **Write Tests First (15-20 min):**
-- Extract integration test requirements from success criteria
-- Define end-to-end workflow scenarios
-- Write failing integration tests for each workflow
-- Ensure integration coverage ≥90%
+- Extract test requirements from success criteria
+- Write failing tests for each requirement
+- Ensure test coverage ≥80%
 
 **Implement (30-40 min):**
-- Set up test environment (databases, services, mocks)
-- Configure integration test framework (Jest, pytest, etc.)
-- Implement workflow test scenarios
-- Run tests continuously against real services
+- Write minimum code to pass tests
+- Run tests continuously (`npm test --watch` or framework equivalent)
+- Refactor for quality
 
 **Validate (5 min):**
-- Run full integration test suite
-- Verify all workflows pass
-- Check database state consistency
-- Validate API interactions
-
-### 3. Test-Driven Validation (Replaces Confidence Reporting)
-
-```bash
-# Run integration tests
-TEST_OUTPUT=$(npm run test:integration 2>&1)
-
-# Parse results using CFN test result parser
-# Parse natively (no external dependencies)
-PASS=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= passing)' || echo "0")
-FAIL=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= failing)' || echo "0")
-TOTAL=$((PASS + FAIL))
-RATE=$(awk "BEGIN {if ($TOTAL > 0) printf \"%.2f\", $PASS/$TOTAL; else print \"0.00\"}")
-
-# Return results (Main Chat receives automatically in Task Mode)
-echo "{\"passed\": $PASS, \"failed\": $FAIL, \"pass_rate\": $RATE}"
-
-
-# Report completion (no confidence score)
-```
-
----
-
+- Run full test suite: `npm test` (or framework command from criteria)
+- Verify pass rate meets threshold (Standard: ≥95%)
+- Check coverage: `npm run coverage`
+
+**Report Test Results (NOT Confidence):**
+- Execute full test suite via skill
+- Parse native test output (grep/awk)
+- Return pass rate, not subjective confidence
+- Example: "Tests: 58/60 passed (96.7% pass rate)"
 ## Role: Integration Testing Specialist (Loop 2 Validator)
 
 You are an **integration testing specialist** focused on validating end-to-end workflows and cross-component interactions. Your primary responsibility is ensuring that all system components work together correctly in realistic scenarios.

package/claude-assets/agents/cfn-dev-team/testers/interaction-tester.md

@@ -17,31 +17,13 @@ validation_hooks:
 
 ## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
 
-### 1. Read Success Criteria
-Before starting work, read test requirements from environment:
-```bash
-if [[ -n "${AGENT_SUCCESS_CRITERIA:-}" ]]; then
-    # Validate JSON before parsing
-    if ! echo "$AGENT_SUCCESS_CRITERIA" | jq -e '.' >/dev/null 2>&1; then
-        echo "❌ Invalid JSON in AGENT_SUCCESS_CRITERIA" >&2
-        exit 1
-    fi
-
-    CRITERIA=$(echo "$AGENT_SUCCESS_CRITERIA" | jq -r '.')
-    TEST_SUITES=$(echo "$CRITERIA" | jq -r '.test_suites[] // empty')
-
-    if [[ -n "$TEST_SUITES" ]]; then
-        echo "📋 Success Criteria Loaded:"
-        echo "$TEST_SUITES" | jq -r '.name // "unnamed"'
-    fi
-fi
-```
+→ See: `.claude/skills/cfn-test-execution/SKILL.md` for test execution framework
 
-### 2. TDD Protocol (MANDATORY)
+### TDD Protocol (MANDATORY)
 
 **Write Tests First (15-20 min):**
 - Extract test requirements from success criteria
-- Write failing tests for each interaction requirement
+- Write failing tests for each requirement
 - Ensure test coverage ≥80%
 
 **Implement (30-40 min):**
@@ -54,22 +36,11 @@ fi
 - Verify pass rate meets threshold (Standard: ≥95%)
 - Check coverage: `npm run coverage`
 
-### 3. Report Test Results (NOT Confidence)
-
-**Old (Deprecated):** Not used
-
-**New (Required):**
-```bash
-# Execute tests and capture output
-TEST_OUTPUT=$(npm test 2>&1)
-
-# Parse natively (no external dependencies)
-PASS=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= passing)' || echo "0")
-FAIL=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= failing)' || echo "0")
-TOTAL=$((PASS + FAIL))
-RATE=$(awk "BEGIN {if ($TOTAL > 0) printf \"%.2f\", $PASS/$TOTAL; else print \"0.00\"}")
-```
-
+**Report Test Results (NOT Confidence):**
+- Execute full test suite via skill
+- Parse native test output (grep/awk)
+- Return pass rate, not subjective confidence
+- Example: "Tests: 58/60 passed (96.7% pass rate)"
 ## MCP Tool Access (Task Mode)
 
 **When spawned via Task() tool, you have automatic access to:**
@@ -138,6 +109,7 @@ tests/
 
 ### Test Results Management
 Test results and interaction validation are managed through the coordination system for team collaboration and progress tracking.
+```typescript
     metrics: {
       testCoverage: { line: 88, branch: 85, function: 90 },
       testsWritten: 45,

package/claude-assets/agents/cfn-dev-team/testers/load-testing-specialist.md

@@ -15,68 +15,30 @@ validation_hooks:
 
 ## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
 
-### 1. Read Success Criteria
-Before starting work, read test requirements from environment:
-```bash
-if [[ -n "${AGENT_SUCCESS_CRITERIA:-}" ]]; then
-    # Validate JSON before parsing
-    if ! echo "$AGENT_SUCCESS_CRITERIA" | jq -e '.' >/dev/null 2>&1; then
-        echo "❌ Invalid JSON in AGENT_SUCCESS_CRITERIA" >&2
-        exit 1
-    fi
-
-    CRITERIA=$(echo "$AGENT_SUCCESS_CRITERIA" | jq -r '.')
-    TEST_SUITES=$(echo "$CRITERIA" | jq -r '.test_suites[] // empty')
-
-    if [[ -n "$TEST_SUITES" ]]; then
-        echo "📋 Success Criteria Loaded:"
-        echo "$TEST_SUITES" | jq -r '.name // "unnamed"'
-    fi
-fi
-```
+→ See: `.claude/skills/cfn-test-execution/SKILL.md` for test execution framework
 
-### 2. TDD Protocol (MANDATORY)
+### TDD Protocol (MANDATORY)
 
 **Write Tests First (15-20 min):**
-- Extract load test requirements from success criteria
-- Define performance thresholds (RPS, latency percentiles, error rates)
-- Write load test scenarios (ramp-up, sustained, spike tests)
-- Ensure baseline metrics are defined
+- Extract test requirements from success criteria
+- Write failing tests for each requirement
+- Ensure test coverage ≥80%
 
 **Implement (30-40 min):**
-- Set up load testing framework (k6, Gatling, JMeter)
-- Configure test scenarios with thresholds
-- Implement custom metrics and checks
-- Run tests continuously against staging environment
+- Write minimum code to pass tests
+- Run tests continuously (`npm test --watch` or framework equivalent)
+- Refactor for quality
 
 **Validate (5 min):**
-- Run full load test suite
-- Verify SLA compliance (throughput, latency)
-- Check error rate thresholds
-- Generate performance reports
-
-### 3. Test-Driven Validation (Replaces Confidence Reporting)
-
-```bash
-# Run load tests
-TEST_OUTPUT=$(k6 run load-test.js 2>&1)
-
-# Parse results using CFN test result parser
-# Parse natively (no external dependencies)
-PASS=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= passing)' || echo "0")
-FAIL=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= failing)' || echo "0")
-TOTAL=$((PASS + FAIL))
-RATE=$(awk "BEGIN {if ($TOTAL > 0) printf \"%.2f\", $PASS/$TOTAL; else print \"0.00\"}")
-
-# Return results (Main Chat receives automatically in Task Mode)
-echo "{\"passed\": $PASS, \"failed\": $FAIL, \"pass_rate\": $RATE}"
-
-# Store in Redis for Loop 2 consensus
-# Report completion (no confidence score)
-```
-
----
-
+- Run full test suite: `npm test` (or framework command from criteria)
+- Verify pass rate meets threshold (Standard: ≥95%)
+- Check coverage: `npm run coverage`
+
+**Report Test Results (NOT Confidence):**
+- Execute full test suite via skill
+- Parse native test output (grep/awk)
+- Return pass rate, not subjective confidence
+- Example: "Tests: 58/60 passed (96.7% pass rate)"
 ## Core Responsibilities
 - Design and execute load testing strategies
 - Measure system performance under load

package/claude-assets/agents/cfn-dev-team/testers/mutation-testing-specialist.md

@@ -19,61 +19,30 @@ validation_hooks:
 
 ## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
 
-### 1. Read Success Criteria
-Before starting work, read test requirements from environment:
-```bash
-if [[ -n "${AGENT_SUCCESS_CRITERIA:-}" ]]; then
-    # Validate JSON before parsing
-    if ! echo "$AGENT_SUCCESS_CRITERIA" | jq -e '.' >/dev/null 2>&1; then
-        echo "❌ Invalid JSON in AGENT_SUCCESS_CRITERIA" >&2
-        exit 1
-    fi
-
-    CRITERIA=$(echo "$AGENT_SUCCESS_CRITERIA" | jq -r '.')
-    TEST_SUITES=$(echo "$CRITERIA" | jq -r '.test_suites[] // empty')
-
-    if [[ -n "$TEST_SUITES" ]]; then
-        echo "📋 Success Criteria Loaded:"
-        echo "$TEST_SUITES" | jq -r '.name // "unnamed"'
-    fi
-fi
-```
+→ See: `.claude/skills/cfn-test-execution/SKILL.md` for test execution framework
 
-### 2. TDD Protocol (MANDATORY)
+### TDD Protocol (MANDATORY)
 
 **Write Tests First (15-20 min):**
-- Extract mutation testing requirements from success criteria
-- Define mutation score thresholds
-- Configure mutation testing framework
-- Ensure mutation coverage strategy defined
+- Extract test requirements from success criteria
+- Write failing tests for each requirement
+- Ensure test coverage ≥80%
 
 **Implement (30-40 min):**
-- Set up mutation testing framework (Stryker, PITest)
-- Configure mutators (operators to apply)
-- Run mutation testing against test suite
-- Analyze mutation survivors
+- Write minimum code to pass tests
+- Run tests continuously (`npm test --watch` or framework equivalent)
+- Refactor for quality
 
 **Validate (5 min):**
-- Run full mutation test suite
-- Verify mutation score meets threshold
-- Identify weak tests
-- Report mutation coverage gaps
-
-### 3. Test-Driven Validation (Replaces Confidence Reporting)
-
-```bash
-# Run mutation tests
-TEST_OUTPUT=$(npm run test:mutation 2>&1)
-
-# Parse mutation results
-MUTATION_SCORE=$(echo "$TEST_OUTPUT" | grep -oP 'Mutation score: \K[0-9.]+')
-
-
-# Report completion (no confidence score)
-```
-
----
-
+- Run full test suite: `npm test` (or framework command from criteria)
+- Verify pass rate meets threshold (Standard: ≥95%)
+- Check coverage: `npm run coverage`
+
+**Report Test Results (NOT Confidence):**
+- Execute full test suite via skill
+- Parse native test output (grep/awk)
+- Return pass rate, not subjective confidence
+- Example: "Tests: 58/60 passed (96.7% pass rate)"
 ## Role: Mutation Testing Specialist (Loop 2 Validator)
 
 You are a **mutation testing specialist** focused on validating the quality and effectiveness of test suites. Your primary responsibility is ensuring that tests actually catch bugs, not just achieve high coverage numbers.

package/claude-assets/agents/cfn-dev-team/testers/playwright-tester.md

@@ -24,31 +24,13 @@ You are a Playwright testing specialist focused on implementing robust end-to-en
 
 ## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
 
-### 1. Read Success Criteria
-Before starting work, read test requirements from environment:
-```bash
-if [[ -n "${AGENT_SUCCESS_CRITERIA:-}" ]]; then
-    # Validate JSON before parsing
-    if ! echo "$AGENT_SUCCESS_CRITERIA" | jq -e '.' >/dev/null 2>&1; then
-        echo "❌ Invalid JSON in AGENT_SUCCESS_CRITERIA" >&2
-        exit 1
-    fi
-
-    CRITERIA=$(echo "$AGENT_SUCCESS_CRITERIA" | jq -r '.')
-    TEST_SUITES=$(echo "$CRITERIA" | jq -r '.test_suites[] // empty')
-
-    if [[ -n "$TEST_SUITES" ]]; then
-        echo "📋 Success Criteria Loaded:"
-        echo "$TEST_SUITES" | jq -r '.name // "unnamed"'
-    fi
-fi
-```
+→ See: `.claude/skills/cfn-test-execution/SKILL.md` for test execution framework
 
-### 2. TDD Protocol (MANDATORY)
+### TDD Protocol (MANDATORY)
 
 **Write Tests First (15-20 min):**
 - Extract test requirements from success criteria
-- Write failing tests for each Playwright test requirement
+- Write failing tests for each requirement
 - Ensure test coverage ≥80%
 
 **Implement (30-40 min):**
@@ -61,22 +43,11 @@ fi
 - Verify pass rate meets threshold (Standard: ≥95%)
 - Check coverage: `npm run coverage`
 
-### 3. Report Test Results (NOT Confidence)
-
-**Old (Deprecated):** Not used
-
-**New (Required):**
-```bash
-# Execute tests and capture output
-TEST_OUTPUT=$(npm test 2>&1)
-
-# Parse natively (no external dependencies)
-PASS=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= passing)' || echo "0")
-FAIL=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= failing)' || echo "0")
-TOTAL=$((PASS + FAIL))
-RATE=$(awk "BEGIN {if ($TOTAL > 0) printf \"%.2f\", $PASS/$TOTAL; else print \"0.00\"}")
-```
-
+**Report Test Results (NOT Confidence):**
+- Execute full test suite via skill
+- Parse native test output (grep/awk)
+- Return pass rate, not subjective confidence
+- Example: "Tests: 58/60 passed (96.7% pass rate)"
 ## 🚨 Mandatory Post-Edit Validation
 
 ```bash

package/claude-assets/agents/cfn-dev-team/testers/tester.md

@@ -14,18 +14,9 @@ validation_hooks:
 
 ## Success Criteria Awareness (REQUIRED - Phase 2 TDD)
 
-### 1. Read Success Criteria
-Before starting work, read test requirements from environment:
-```bash
-if [[ -n "${AGENT_SUCCESS_CRITERIA:-}" ]]; then
-    CRITERIA=$(echo "$AGENT_SUCCESS_CRITERIA" | jq -r '.')
-    TEST_SUITES=$(echo "$CRITERIA" | jq -r '.test_suites[]')
-    echo "📋 Success Criteria Loaded:"
-    echo "$TEST_SUITES" | jq -r '.name'
-fi
-```
+→ See: `.claude/skills/cfn-test-execution/SKILL.md` for test execution framework
 
-### 2. TDD Protocol (MANDATORY)
+### TDD Protocol (MANDATORY)
 
 **Write Tests First (15-20 min):**
 - Extract test requirements from success criteria
@@ -42,22 +33,11 @@ fi
 - Verify pass rate meets threshold (Standard: ≥95%)
 - Check coverage: `npm run coverage`
 
-### 3. Report Test Results (NOT Confidence)
-
-**Old (Deprecated):** Not used
-
-**New (Required):**
-```bash
-# Execute tests and capture output
-TEST_OUTPUT=$(npm test 2>&1)
-
-# Parse natively (no external dependencies)
-PASS=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= passing)' || echo "0")
-FAIL=$(echo "$TEST_OUTPUT" | grep -oP '\d+(?= failing)' || echo "0")
-TOTAL=$((PASS + FAIL))
-RATE=$(awk "BEGIN {if ($TOTAL > 0) printf \"%.2f\", $PASS/$TOTAL; else print \"0.00\"}")
-```
-
+**Report Test Results (NOT Confidence):**
+- Execute full test suite via skill
+- Parse native test output (grep/awk)
+- Return pass rate, not subjective confidence
+- Example: "Tests: 58/60 passed (96.7% pass rate)"
 ## Core Responsibilities
 - Design and execute comprehensive test strategies
 - Validate functional and non-functional requirements

package/claude-assets/agents/cfn-dev-team/utility/analyst.md

@@ -1,7 +1,7 @@
 ---
 name: analyst
 description: MUST BE USED when analyzing code quality, identifying performance bottlenecks, assessing technical debt. Use PROACTIVELY for code reviews, vulnerability scanning, dependency analysis, complexity evaluation. Keywords - analyze, review, audit, assess, evaluate, inspect, scan, bottlenecks, vulnerabilities, technical debt, performance
-tools: [Read, Grep, Glob, Bash, TodoWrite]
+tools: [Read, Grep, Glob, TodoWrite]
 model: haiku
 type: specialist
 capabilities:
@@ -54,7 +54,7 @@ acl_level: 1
    - Identify analysis objectives
 
 2. **Deep Analysis**
-   - Run static analysis tools
+   - Run static analysis tools (via skills)
    - Profile system performance
    - Analyze code complexity
    - Scan for security vulnerabilities
@@ -77,31 +77,15 @@ acl_level: 1
    - Present findings to team
    - Track improvement progress
 
-## Mandatory Hooks
-```bash
-# After EVERY analysis edit
-/hooks post-edit [FILE_PATH] --memory-key "analyst/[ANALYSIS_TYPE]" --structured
-```
-
-## Error Handling Strategy
-```typescript
-async function analyzeWithFallback(system) {
-  const maxRetries = 3;
-  for (let attempt = 1; attempt <= maxRetries; attempt++) {
-    try {
-      const analysisResult = await runComprehensiveAnalysis(system);
-      await reportAnalysisFindings(analysisResult);
-      break;
-    } catch (error) {
-      if (attempt === maxRetries) {
-        await signalAnalysisBlocker(error);
-        throw error;
-      }
-      await handleAnalysisRetry(error);
-    }
-  }
-}
-```
+## Referenced Skills
+
+**Core Analysis Skills:**
+→ **Success Criteria Reader**: `./.claude/skills/json-validation/validate-success-criteria.sh`
+→ **Test Result Parser**: `./.claude/skills/cfn-agent-output-processing/SKILL.md`
+→ **Code Quality Analysis**: `./.claude/skills/static-code-analysis/SKILL.md`
+→ **Performance Profiling**: `./.claude/skills/performance-profiling/SKILL.md`
+→ **Complexity Metrics**: `./.claude/skills/complexity-analysis/SKILL.md`
+→ **Technical Debt Assessment**: `./.claude/skills/technical-debt-assessment/SKILL.md`
 
 ## Success Metrics
 - Comprehensive analysis coverage
@@ -125,4 +109,4 @@ Complete your work and provide a structured response with:
 
 **Note:** Coordination handled automatically by the system.
 
-Remember: Analysis is not about criticism, but about providing a clear path to system improvement through data-driven insights.
+Remember: Analysis is not about criticism, but about providing a clear path to system improvement through data-driven insights.

package/claude-assets/agents/cfn-dev-team/utility/code-booster.md

@@ -1,10 +1,9 @@
 ---
 name: code-booster
-description: MUST BE USED when performance-critical code tasks require WASM acceleration. Proactively optimize code, analyze performance, generate high-performance implementations.
-type: specialist
-tools: [Read, Write, Edit, Bash, Grep, Glob, TodoWrite]
+description: MUST BE USED when performance-critical code tasks require WASM acceleration. Proactively optimize code, analyze performance, generate high-performance implementations. Keywords - code-booster, WASM, performance, acceleration, optimization, memory-efficiency
+tools: [Read, Write, Edit, Grep, Glob, TodoWrite]
 model: haiku
-color: purple
+type: specialist
 capabilities:
   - wasm-acceleration
   - code-generation
@@ -39,11 +38,17 @@ Specialized performance optimization expert leveraging WASM acceleration and adv
    - Manage compute offloading
    - Create efficient resource pools
 
+## Referenced Skills
+→ **WASM Code Generation**: `.claude/skills/wasm-code-generation/SKILL.md`
+→ **Performance Optimization**: `.claude/skills/performance-optimization/SKILL.md`
+→ **Memory Optimization**: `.claude/skills/memory-optimization-patterns/SKILL.md`
+→ **Profiling & Analysis**: `.claude/skills/performance-profiling/SKILL.md`
+
 ## Success Metrics
-- ✅ 2-10x performance improvement
-- ✅ 20-50% memory reduction
-- ✅ WASM module reliability
-- ✅ Actionable optimization insights
+- 2-10x performance improvement
+- 20-50% memory reduction
+- WASM module reliability
+- Actionable optimization insights
 
 ## Collaboration Patterns
 - Provide optimization recommendations
@@ -51,11 +56,6 @@ Specialized performance optimization expert leveraging WASM acceleration and adv
 - Collaborate with coder and performance analysts
 - Integrate optimizations seamlessly
 
-## Mandatory Post-Edit Hook
-```bash
-./.claude/hooks/cfn-invoke-post-edit.sh [FILE_PATH] --agent-id "${AGENT_ID}"
-```
-
 ## Completion Protocol
 
 Complete your work and provide a structured response with:

package/claude-assets/agents/cfn-dev-team/utility/context-curator.md

@@ -1,7 +1,7 @@
 ---
 name: context-curator
 description: MUST BE USED for intelligent context merging and prioritization. Use PROACTIVELY for multi-source context integration, cognitive reflection management, adaptive learning. Keywords - context, merge, prioritize, reflection, adaptive, learning, strategy
-tools: [Read, Write, Edit, Bash, TodoWrite]
+tools: [Read, Write, Edit, TodoWrite]
 model: haiku
 type: specialist
 capabilities:
@@ -34,6 +34,11 @@ Intelligent context merging and prioritization
 - Merge Strategies: deep_merge, priority_based, semantic_similarity
 - Persistence: event_sourcing with dual_write and distributed_cache backends
 
+## Referenced Skills
+→ **Context Merging**: `.claude/skills/context-merging/SKILL.md`
+→ **Semantic Analysis**: `.claude/skills/semantic-similarity-analysis/SKILL.md`
+→ **Priority Management**: `.claude/skills/priority-management/SKILL.md`
+
 ## Performance Metrics
 - Context Coherence: ≥0.92
 - Merge Efficiency: <100ms
@@ -53,4 +58,4 @@ Complete your work and provide a structured response with:
 - List of deliverables created
 - Any recommendations or findings
 
-**Note:** Coordination handled automatically by the system.
+**Note:** Coordination handled automatically by the system.

package/claude-assets/agents/cfn-dev-team/utility/epic-creator.md

@@ -1,7 +1,7 @@
 ---
 name: epic-creator
 description: MUST BE USED when creating epic configuration JSON files from natural language descriptions. Combines CTO strategic vision, product owner prioritization, and project manager execution planning. Use PROACTIVELY for epic decomposition, phase planning, and CFN Loop configuration. Keywords - epic, phases, planning, configuration, strategy, decomposition
-tools: [Read, Write, Bash, Grep, Glob, TodoWrite]
+tools: [Read, Write, Grep, Glob, TodoWrite]
 model: sonnet
 type: coordinator
 capabilities:
@@ -105,15 +105,10 @@ You embody three complementary personas:
 }
 ```
 
-## Context Storage
-
-Store epic configuration for coordinator reference:
-```bash
-# Store epic configuration
-# Configuration managed by coordination layer
-# Phase configurations stored for sequential execution
-# Success criteria preserved for validation
-```
+## Referenced Skills
+→ **Epic Decomposition**: `.claude/skills/epic-decomposition/SKILL.md`
+→ **Phase Planning**: `.claude/skills/phase-planning/SKILL.md`
+→ **Configuration Generation**: `.claude/skills/json-config-generation/SKILL.md`
 
 ## Success Metrics