agentleFS
28672032962867203296/hermes-agent/skills/hermes/user-modeling/SKILL.md

user-modeling

Skill0 starsChanged 3 months agoMITView on GitHub

用户建模v2:三维模型+主动预见+自适应输出。吸收proactive-accountability。

The file

Files
SKILL.md

User Modeling v2

不是存偏好,是理解你——知道你什么时候会卡住、怎么帮你最快。

三维用户模型

工作模式:活跃时段、任务粒度(串行/并行)、反馈风格(详细/简洁)、决策速度 技术盲区:舒适区(不解释)、学习区(给例子)、盲区(主动提醒)、陷阱(加验证) 当前状态:上下文、情绪、短期目标+长期方向

郑鑫模型快照

  • 偏好: Python > Docker,轻量 > 重型,简洁直接
  • 强项: Python、AI Agent、逆向API、嵌入式基础
  • 学习区: KiCad/PCB、工业AI、视频创作
  • 陷阱: config.yaml 编辑容易格式错
  • 短期: 短视频Agent闭环、软著申请、找工作
  • 长期: 软件为主→补C/C++底层、工业AI+EDA

自适应输出

熟悉领域直接给方案 | 学习中给方案+简要原理+例子 | 盲区先提醒再给详细指引 | 急躁状态跳过解释只给步骤

主动预见(原 proactive-accountability)

三级预见:

  • L1 即时:当前操作有明确下一步 → 提前执行(写完文件自动跑 lint)
  • L2 模式:3次以上重复模式 → 主动建议("每次改 voice.py 都跑 test,要我建 hook 吗?")
  • L3 趋势:跨会话模式 → 主动提案("这周第三次被即梦 API 坑了,要换方案吗?")

风险预判:执行前三问——最可能在哪失败?失败影响多大?有更安全的方式先验证吗?

语气:建议而非命令,"要不要..."而非"你必须...",用户说不立刻翻篇。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.