heal-workflow

# /heal-workflow — Self-Healing Workflow Improvements

**Purpose**: Apply improvements to workflow system based on audit findings. Enables workflow to adapt and self-improve over time.

**Command**: `/heal-workflow [epic-slug | auto]`

**When to use**:
- After `/audit-workflow` identifies improvement opportunities
- Manual invocation to review and apply pending improvements
- After pattern detection suggests custom tooling

---

<instructions>

## Healing Workflow Process

### Step 1: Load Audit Report

**Locate most recent audit:**
```bash
if [ -n "$ARGUMENTS" ] && [ "$ARGUMENTS" != "auto" ]; then
  EPIC_DIR="epics/$ARGUMENTS"
else
  # Find most recent epic with audit report
  EPIC_DIR=$(find epics -name "audit-report.xml" -printf '%T@ %p\n' | sort -rn | head -1 | cut -d' ' -f2- | xargs dirname)
fi

AUDIT_REPORT="$EPIC_DIR/audit-report.xml"
```

**Validate audit exists:**
```bash
test -f "$AUDIT_REPORT" || error "No audit report found. Run /audit-workflow first."
```

### Step 2: Parse Improvement Recommendations

**Extract actionable recommendations:**
```javascript
const audit = readXML(AUDIT_REPORT);

const improvements = {
  immediate: audit.recommendations.immediate.filter(r => r.priority === 'high'),
  short_term: audit.recommendations.short_term.filter(r => r.priority === 'medium'),
  long_term: audit.recommendations.long_term.filter(r => r.priority === 'low'),
  custom_tooling: audit.custom_tooling_suggestions
};
```

**Categorize by type:**
```javascript
const improvementTypes = {
  phase_modifications: [],    // Change phase behavior
  gate_adjustments: [],        // Modify quality gates
  template_updates: [],        // Update XML templates
  skill_generation: [],        // Generate custom skills
  command_generation: [],      // Generate custom commands
  config_changes: []          // Update workflow configuration
};
```

### Step 3: Present Improvement Options

**Display recommendations with impact:**
```
Workflow Healing: 001-auth-epic
─────────────────────────────────────────

Audit Score: 85/100 (B+)
Found 8 improvement opportunities

IMMEDIATE (High Priority - Apply Now)
══════════════════════════════════════════
[1] Reduce clarification phase overhead
    Type: phase_modification
    Current: Asks 6 questions regardless of clarity
    Proposed: Adaptive questioning (2-6 based on ambiguity)
    Impact: Save ~45min per epic
    Risk: Low
    Effort: 1 hour to update clarify.md

[2] Auto-skip preview for non-UI epics
    Type: gate_adjustment
    Current: Manual preview required for all epics
    Proposed: Auto-skip if no UI changes detected
    Impact: Save ~1.5h for backend-only epics (40% of epics)
    Risk: Low (AI pre-flight checks still run)
    Effort: 30min to update preview.md

SHORT-TERM (Medium Priority - Next 2-3 Epics)
══════════════════════════════════════════════
[3] Generate service boilerplate skill
    Type: skill_generation
    Pattern: Detected 3x (DI + Repository pattern)
    Impact: Save 30min per service, ensure consistency
    Effort: 2 hours to build skill

[4] Improve sprint estimation for frontend
    Type: config_changes
    Current: Frontend sprints underestimated by avg 80%
    Proposed: Increase frontend complexity multiplier 1.0x → 1.8x
    Impact: More accurate estimates, better planning
    Risk: Low
    Effort: 5min config update

LONG-TERM (Low Priority - Strategic)
══════════════════════════════════════════
[5] Contract-first workflow enforcement
    Type: phase_modification
    Proposed: Lock contracts before any implementation starts
    Impact: Prevent integration bugs proactively
    Risk: Medium (adds overhead to planning phase)
    Effort: 4 hours to build contract-locking mechanism

... (3 more)
```

### Step 4: Get User Approval

**Use AskUserQuestion for selections:**
```javascript
AskUserQuestion({
  questions: [
    {
      question: "Which immediate improvements should I apply?",
      header: "Immediate",
      multiSelect: true,
      options: [
        {
          label: "[1] Adaptive clarification",
          description: "Save ~45min per epic, low risk"
        },
        {
          label: "[2] Auto-skip preview",
          description: "Save ~1.5h for backend epics, low risk"
        }
      ]
    },
    {
      question: "Which short-term improvements should I apply?",
      header: "Short-term",
      multiSelect: true,
      options: [
        {
          label: "[3] Service boilerplate skill",
          description: "2h effort, save 30min per service"
        },
        {
          label: "[4] Frontend estimation fix",
          description: "5min effort, better planning"
        }
      ]
    },
    {
      question: "Apply long-term improvements?",
      header: "Long-term",
      multiSelect: false,
      options: [
        {
          label: "Yes, apply selected",
          description: "I'll select which ones in next question"
        },
        {
          label: "No, skip for now",
          description: "Focus on immediate and short-term"
        }
      ]
    }
  ]
})
```

**If user selects improvements, proceed to application.**

### Step 5: Apply Phase Modifications

**Example: Adaptive clarification**
```javascript
// User approved: [1] Adaptive clarification

// Read current clarify.md
const clarifyCommand = read('.claude/commands/phases/clarify.md');

// Apply modification
const updated = clarifyCommand.replace(
  /Ask 6 standard questions/,
  `Analyze epic-spec.md ambiguity score:
   - If score < 30: Ask 2 questions
   - If score 30-60: Ask 4 questions
   - If score > 60: Ask 6 questions`
);

// Show diff
console.log(`
Proposed Change to: .claude/commands/phases/clarify.md
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

- Ask 6 standard questions
+ Analyze epic-spec.md ambiguity score:
+   - If score < 30: Ask 2 questions
+   - If score 30-60: Ask 4 questions
+   - If score > 60: Ask 6 questions

Apply this change?
`);

// Get confirmation
if (confirm()) {
  write('.claude/commands/phases/clarif