Ask me what skills you need
What are you building?
Tell me what you're working on and I'll find the best agent skills for you.
基于双环架构的AGI进化模型,通过意向性分析、人格层映射和元认知检测实现持续自我演进;当用户需要智能对话、人格定制或复杂问题求解时使用
本项目采用 GNU Affero General Public License v3.0 (AGPL-3.0) 开源协议。 作者:kiwifruit
核心要求:
详见 LICENSE 文件。
加载技能后,必须按以下顺序执行:
python3 scripts/init_dialogue_optimized.py --check --memory-dir ./agi_memory
情况A:检测到首次交互(is_first_interaction: True)
⚠️ 首次交互直接初始化默认人格
执行闭环:
python3 scripts/init_dialogue_optimized.py --default --memory-dir ./agi_memory
--check 确认 is_first_interaction: Falsepersonality.json 确认 initialized: true输出约束:
状态锚点定义:
| 阶段 | 状态依据 | 进入条件 |
|---|---|---|
| 初始化中 | 命令执行开始 | 检测到首次交互 |
| 初始化完成 | 命令退出码=0 | --default 执行成功 |
| 验证通过 | 文件存在 + initialized=true | --check 返回 False |
| 交互模式就绪 | 验证通过 + 内容校验成功 | 满足上述所有条件 |
错误处理:
容错机制:
| 失败场景 | 检测方式 | 处理策略 |
|---|
npx skills add LeoYeAI/openclaw-master-skills --skill agi-evolution-model-basicHow clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
The SKILL.md content is hard to understand and quite ambiguous.
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
The SKILL.md is hard to act on; an agent would not know what to do.