openclaw-learning-loop

name	openclaw-learning-loop
description	OpenClaw 学习循环与技能提炼：用于在非显而易见的问题解决后记录 learning、复盘并晋升为 skill；用于需要检查 self-improving-agent、生成学习记录、输出 dry-run 预览或执行一键式学习闭环时。

OpenClaw Learning Loop

Purpose

把一次问题解决，变成可复用的学习记录。

Workflow

1. Run scripts/bootstrap.sh to verify OpenClaw and self-improving-agent availability.
2. Run scripts/extract.sh <skill_name> <dry_run> to generate a learning prompt or record.
3. If the learning is high-value, promote it into a reusable skill.

Defaults

• skill_name: my-new-skill
• dry_run: true

Notes

• Use clawhub list as the source of truth for installed skills.
• Do not depend on a fixed local filesystem path for self-improving-agent.
• In dry-run mode, print the learning prompt instead of writing.
• In real mode, write only if the surrounding workflow explicitly defines a target.