skill-iter-tune

Skill Iter Tune

Iterative skill refinement through execute-evaluate-improve feedback loops. Each iteration runs the skill via Claude, evaluates output via Gemini, and applies improvements via Agent.

Architecture Overview

┌──────────────────────────────────────────────────────────────────────────┐
│  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 Extension

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

Key Design Principles

1. Iteration Loop: Phases 2-3-4 repeat until quality threshold, max iterations, or convergence
2. Two-Tool Pipeline: Claude (write/execute) + Gemini (analyze/evaluate) = complementary perspectives
3. Pure Orchestrator: SKILL.md coordinates only — execution detail lives in phase files
4. Progressive Phase Loading: Phase docs read only when that phase executes
5. Skill Versioning: Each iteration snapshots skill state before execution
6. Convergence Detection: Stop early if score stalls (no improvement in 2 consecutive iterations)