skill-opt-lite

# SkillOpt-Lite: Agent-Native Skill Training Working directory: any Train your skill documents the way neural networks train weights — iterative rollout, reflection, and validation. No external API keys. You are both the worker and the optimizer. ## When to Use - You have a skill that doesn't work well and want to systematically improve it - You want to create a new skill from scratch using data-driven iteration - You want to know whether a skill change actually helps or hurts MUST NOT use for: - One-off skill fixes (just edit the skill directly) - Skills that can't be objectively evaluated (purely subjective quality) ## Quick Start 1. Prepare a task set (JSON array of tasks with verifiable outcomes) 2. Point this skill at your draft skill document 3. Run the training loop 4. Get an optimized `best_skill.md` ## Training Loop ``` for epoch in 1..N: for step in 1..steps_per_epoch: ① ROLLOUT — run tasks with current skill, record pass/fail ② REFLECT — analyze failures, propose edits (≤ edit_budget) ③ AGGREGATE — deduplicate, failure-first merge ④ SELECT — pick top-L edits by impact ⑤ UPDATE — apply edits to skill document ⑥ GATE — re-run validation, accept only if score improves SLOW_UPDATE — epoch-end strategic review into protected region ``` Read `references/training-protocol.md` for the full detailed protocol before starting a training run. ## Required Inputs | Input | Description | Format | |---|---|---| | skill_path | ...