Skill Iter Tune

┌──────────────────────────────────────────────────────────────────────────┐
│  Skill Iter Tune Orchestrator (SKILL.md)                                 │
│  → Parse input → Setup workspace → Iteration Loop → Final Report         │
└────────────────────────────┬─────────────────────────────────────────────┘
                             │
         ┌───────────────────┼───────────────────────────────────┐
         ↓                   ↓                                   ↓
    ┌──────────┐      ┌─────────────────────────────┐     ┌──────────┐
    │ Phase 1  │      │  Iteration Loop (2→3→4)     │     │ Phase 5  │
    │ Setup    │      │  ┌─────┐  ┌─────┐  ┌─────┐ │     │ Report   │
    │          │─────→│  │ P2  │→ │ P3  │→ │ P4  │ │────→│          │
    │ Backup + │      │  │Exec │  │Eval │  │Impr │ │     │ History  │
    │ Init     │      │  └─────┘  └─────┘  └─────┘ │     │ Summary  │
    └──────────┘      │       ↑               │     │     └──────────┘
                      │       └───────────────┘     │
                      │    (if score < threshold    │
                      │     AND iter < max)         │
                      └─────────────────────────────┘

Chain Mode (execution_mode === "chain"):

Phase 2 runs per-skill in chain_order:
  Skill A → ccw cli → artifacts/skill-A/
       ↓ (artifacts as input)
  Skill B → ccw cli → artifacts/skill-B/
       ↓ (artifacts as input)
  Skill C → ccw cli → artifacts/skill-C/

Phase 3 evaluates entire chain output + per-skill scores
Phase 4 improves weakest skill(s) in chain

// ★ Auto mode detection
const autoYes = /\b(-y|--yes)\b/.test($ARGUMENTS)

if (autoYes) {
  workflowPreferences = {
    autoYes: true,
    maxIterations: 5,
    qualityThreshold: 80,
    executionMode: 'single'
  }
} else {
  const prefResponse = AskUserQuestion({
    questions: [
      {
        question: "选择迭代调优配置：",
        header: "Tune Config",
        multiSelect: false,
        options: [
          { label: "Quick (3 iter, 70)", description: "快速迭代，适合小幅改进" },
          { label: "Standard (5 iter, 80) (Recommended)", description: "平衡方案，适合多数场景" },
          { label: "Thorough (8 iter, 90)", description: "深度优化，适合生产级 skill" }
        ]
      }
    ]
  })

  const configMap = {
    "Quick": { maxIterations: 3, qualityThreshold: 70 },
    "Standard": { maxIterations: 5, qualityThreshold: 80 },
    "Thorough": { maxIterations: 8, qualityThreshold: 90 }
  }
  const selected = Object.keys(configMap).find(k =>
    prefResponse["Tune Config"].startsWith(k)
  ) || "Standard"
  workflowPreferences = { autoYes: false, ...configMap[selected] }

  // ★ Mode selection: chain vs single
  const modeResponse = AskUserQuestion({
    questions: [{
      question: "选择调优模式：",
      header: "Tune Mode",
      multiSelect: false,
      options: [
        { label: "Single Skill (Recommended)", description: "独立调优每个 skill，适合单一 skill 优化" },
        { label: "Skill Chain", description: "按链序执行，前一个 skill 的产出作为后一个的输入" }
      ]
    }]
  });
  workflowPreferences.executionMode = modeResponse["Tune Mode"].startsWith("Skill Chain")
    ? "chain" : "single";
}

$ARGUMENTS → Parse:
  ├─ Skill path(s): first arg, comma-separated for multiple
  │   e.g., ".claude/skills/my-skill" or "my-skill" (auto-prefixed)
  │   Chain mode: order preserved as chain_order
  ├─ Test scenario: --scenario "description" or remaining text
  └─ Flags: --max-iterations=N, --threshold=N, -y/--yes

// Orchestrator iteration loop
while (true) {
  // Increment iteration
  state.current_iteration++;
  state.iterations.push({
    round: state.current_iteration,
    status: 'pending',
    execution: null,
    evaluation: null,
    improvement: null
  });

  // Update TodoWrite
  TaskUpdate(iterationTask, {
    subject: `Iteration ${state.current_iteration}/${state.max_iterations}`,
    status: 'in_progress',
    activeForm: `Running iteration ${state.current_iteration}`
  });

  // === Phase 2: Execute ===
  // Read: phases/02-execute.md
  // Single mode: one ccw cli call for all skills
  // Chain mode: sequential ccw cli per skill in chain_order, passing artifacts
  // Snapshot skill → construct prompt → ccw cli --tool claude --mode write
  // Collect artifacts

  // === Phase 3: Evaluate ===
  // Read: phases/03-evaluate.md
  // Construct eval prompt → ccw cli --tool gemini --mode analysis
  // Parse score → write iteration-N-eval.md → check termination

  // Check termination
  if (shouldTerminate(state)) {
    break;  // → Phase 5
  }

  // === Phase 4: Improve ===
  // Read: phases/04-improve.md
  // Agent applies suggestions → write iteration-N-changes.md

  // Update TodoWrite with score
  // Continue loop
}

User Input (skill paths + test scenario)
    ↓ (+ execution_mode + chain_order if chain mode)
    ↓
Phase 1: Setup
    ↓ workDir, targetSkills[], testScenario, iteration-state.json
    ↓
┌─→ Phase 2: Execute (ccw cli claude)
│   ↓ artifacts/ (skill execution output)
│   ↓
│   Phase 3: Evaluate (ccw cli gemini)
│   ↓ score, dimensions[], suggestions[], iteration-N-eval.md
│   ↓
│   [Terminate?]─── YES ──→ Phase 5: Report → final-report.md
│   ↓ NO
│   ↓
│   Phase 4: Improve (Agent)
│   ↓ modified skill files, iteration-N-changes.md
│   ↓
└───┘ next iteration

// Initial state
TaskCreate({ subject: "Phase 1: Setup workspace", activeForm: "Setting up workspace" })
TaskCreate({ subject: "Iteration Loop", activeForm: "Running iterations" })
TaskCreate({ subject: "Phase 5: Final Report", activeForm: "Generating report" })

// Chain mode: create per-skill tracking tasks
if (state.execution_mode === 'chain') {
  for (const skillName of state.chain_order) {
    TaskCreate({
      subject: `Chain: ${skillName}`,
      activeForm: `Tracking ${skillName}`,
      description: `Skill chain member position ${state.chain_order.indexOf(skillName) + 1}`
    })
  }
}

// During iteration N
// Single mode: one score per iteration (existing behavior)
// Chain mode: per-skill status updates
if (state.execution_mode === 'chain') {
  // After each skill executes in Phase 2:
  TaskUpdate(chainSkillTask, {
    subject: `Chain: ${skillName} — Iter ${N} executed`,
    activeForm: `${skillName} iteration ${N}`
  })
  // After Phase 3 evaluates:
  TaskUpdate(chainSkillTask, {
    subject: `Chain: ${skillName} — Score ${chainScores[skillName]}/100`,
    activeForm: `${skillName} scored`
  })
} else {
  // Single mode (existing)
  TaskCreate({
    subject: `Iteration ${N}: Score ${score}/100`,
    activeForm: `Iteration ${N} complete`,
    description: `Strengths: ... | Weaknesses: ... | Suggestions: ${count}`
  })
}

// Completed — collapse
TaskUpdate(iterLoop, {
  subject: `Iteration Loop (${totalIters} iters, final: ${finalScore})`,
  status: 'completed'
})

function shouldTerminate(state) {
  // 1. Quality threshold met
  if (state.latest_score >= state.quality_threshold) {
    return { terminate: true, reason: 'quality_threshold_met' };
  }
  // 2. Max iterations reached
  if (state.current_iteration >= state.max_iterations) {
    return { terminate: true, reason: 'max_iterations_reached' };
  }
  // 3. Convergence: ≤2 points improvement over last 2 iterations
  if (state.score_trend.length >= 3) {
    const last3 = state.score_trend.slice(-3);
    if (last3[2] - last3[0] <= 2) {
      state.converged = true;
      return { terminate: true, reason: 'convergence_detected' };
    }
  }
  // 4. Error limit
  if (state.error_count >= state.max_errors) {
    return { terminate: true, reason: 'error_limit_reached' };
  }
  return { terminate: false };
}