Simulating an openclaw-style personal assistant on Claude Code. Three additions — heartbeat, memory, evolution — plus a knowledge base following Karpathy's LLM Wiki idea.

From context management to harness design, 10 practical habits that eliminate context rot and dramatically improve your coding agent's success rate.

Agent 写代码很快，但做 ML 实验却异常困难——代码写完只是开始，真正的验证要等几天甚至几周。一个实现 bug 可能让你放弃整条研究路线，一个 checkpoint 没保存让几天训练白费。本文介绍 Superpowers-ML：将软件工程的 TDD、code review、verification 延伸到 ML 领域，通过四层 Validation Pyramid 在几分钟内抓出问题，用 Watchdog 守护长时间训练，让 agent 每次出手都更准确。

AI agents write code fast, but ML experiments operate on a different timescale — real verification takes days or weeks. One implementation bug can invalidate a promising research direction. One unsaved checkpoint wastes days of training. Superpowers-ML extends software engineering discipline into ML through a four-layer Validation Pyramid that catches problems in minutes, plus a Watchdog system for long-running training — making every attempt count.

从 Vibe Coding 到 Agentic Engineering 的演进，系统梳理 Claude Code 命令体系、Skills 系统、Hooks、Subagents、MCP 服务器、辅助工具生态及核心工作流。

这不是一篇教大家怎么实操文章，不谈具体的工具和技术，我们来谈谈Vibe Coding的心法。 Vibe Coding 本质是利用 Agent 编码，Agent 背后是 LLM，LLM 是人类的”幽灵“，这出自 Karpathy 2025 年终总结**：”we're not evolving animals. We're summoning ghosts.“，**语言是人类世界的投影，LLM 是人类的幽灵。 工具和技术层出不穷，这是历史上从未出现过的新技术，没有人有经验。但是人性是一致的，拿捏住 Agent 的"人性"，把 Agent 当人来管，会让Vibe Coding 从迷茫走向有迹可循。

This isn't about tools or techniques — it's about the mental model. Vibe Coding is essentially managing Agents, and managing Agents is essentially managing teams. From context rot to organizational architecture, the parallels between leading a team and orchestrating AI agents reveal why the best vibe coders think like managers, not programmers.