增加文档

Author: wwfyde

Agent.md

@@ -6,4 +6,35 @@
 
 ### Links
 
-- [微信::觉学社::智能体软件工程 #3 ｜重新思考版本控制](https://mp.weixin.qq.com/s/-kZ-xyj_RZgCB7JgMkAeOw)
+- [微信::觉学社::智能体软件工程 #3 ｜重新思考版本控制](https://mp.weixin.qq.com/s/-kZ-xyj_RZgCB7JgMkAeOw)
+
+
+
+## features
+
+- context engineering
+- state
+- Agent loop(Agent Runtime)
+    - ReAct Loop
+    - Native Tool Call
+        - 工具是一等公民
+- 事件驱动
+- 工具调用
+- 生命周期(lifetime)
+- MCP
+- Skills
+- Agents.md
+    - 全局指令: 约束, 边界, 命令
+
+## skills
+
+### Links
+
+- [docs::official::agent-skills](https://agentskills.io/home)
+
+### what
+
+- A skill is a set of instructions - packaged as a simple folder - that teaches Claude how to handle specific tasks or workflows. Skills are one of the most powerful ways to customize Claude for your specific needs. 
+
+
+

LLM.md

@@ -853,6 +853,13 @@ https://www.tensorflow.org/tutorials/images/data_augmentation?hl=zh-cn
 
 - [李宏毅:一堂课搞懂生成式人工智能原理](https://speech.ee.ntu.edu.tw/~hylee/GenAI-ML/2025-fall-course-data/LLM.pdf)
 
+
+
+## 认知
+
+- 大模型就是文字接龙
+- 大模型本身没有记忆, 不知道过去发生了什么
+
 ## 通过问题引导
 
 - 大模型的本质是什么?

ReadNotes

@@ -1108,6 +1108,10 @@ cargo install --path .  # cargo.toml 指定install.root = " ~/.local"
 # create workspace package
 cargo new —lib
 
+# cargo tree
+
+cargo tree
+
 
 
 ```

Rust最佳实践.md

@@ -0,0 +1,45 @@
+---
+title: Agentic Engineering
+description:  Agentic Engineering(aka. agentic coding)
+tags:
+    - architecture
+keywords: 
+    - vibe coding
+    - agentic coding
+    - context engineering
+---
+
+# Agentic Engineering
+
+
+
+## Principle
+
+- Parallel agent conversation
+- 从技术转向了对审美和创意的关注
+- transfer
+
+## concerns
+
+- 测试
+- 文档
+- 质量
+- 评估
+- 错误处理
+- 调试
+- 功能
+- 审美和创意(aesthetic and creative)
+- 
+
+## Agentic Coding最佳实践
+
+> AI提效手册, 思维方式迁移
+
+
+
+
+
+
+
+
+

agentic-engineering.md

@@ -0,0 +1,84 @@
+# OpenClaw
+
+
+
+
+
+## 特性
+
+- 自主运行, 运行在本地
+- 能帮你干活
+
+
+
+
+
+
+
+## 核心
+
+- LLM
+
+- LLM Agent
+
+- 网关(控制访问层)
+
+    - 记忆(Memory)
+    - 技能(Skills)
+        - 操作流程, 规范, 注意事项
+        - 自动化办公, 创作, 编码等
+    - 工具(Tools)
+        - 外部功能支持
+
+- 插件(plugin)
+
+    - 能力扩展
+
+- 通讯软件接入(聊天控制, 频道隔离)
+
+    - 钉钉
+    - 飞书
+
+    
+
+    
+
+## 安全相关
+
+
+
+容器部署(docker/podman)
+
+
+
+
+
+brew 
+
+
+
+docker 
+
+Cmd-line -tool
+
+
+
+
+
+## 条件限制
+
+
+
+- 长期运行
+    - caffeinate
+    - lungo
+
+
+
+## 常见问题
+
+
+
+- 平台不一样
+- 
+

openclaw.md

@@ -0,0 +1,9 @@
+# Skills
+
+## links
+
+- [Ahthropics/Skills](https://github.com/anthropics/skills)
+
+## 为什么需要skills
+
+- 解决私域知识和专属技能问题

skills/README.md

@@ -3845,7 +3845,11 @@ note Note NOTE 格式均可
 > [!CAUTION]
 > Negative potential consequences of an action.
 
-
+> [!example]
+>
+> this is example
+>
+> 
 
 样式修改 
 

参考手册.md

@@ -147,6 +147,28 @@ log, trace, metric
 
 掌握这些基础知识和理论，将有助于你从高层次进行程序和系统设计，确保系统的可靠性、可维护性和性能。
 
+
+
+
+
+# 概念
+
+
+
+## 指针
+
+> "计算机科学中的任何问题都可以通过增加一个间接层来解决。"
+
+指针是一种数据类型, 指针也是一个实体
+
+### 多维视角
+
+- 从硬件层面看
+- 从内存模型看
+- 从程序
+
+
+
 # 编程思想
 
 

程序原理.md

@@ -591,12 +591,63 @@ helper
 
 # 代码质量
 
+
+
+```markdown
+Good code still has a cost #
+好的代码仍然有成本 #
+
+- Delivering new code has dropped in price to almost free... but delivering good code remains significantly more expensive than that.
+- 交付新代码的成本已经降至几乎免费...但交付好的代码仍然比那贵得多。
+
+Here's what I mean by "good code":
+我所说的"好的代码"是指：
+
+The code works. It does what it's meant to do, without bugs.
+代码能正常工作。它能完成预期的功能，没有 bug。
+We know the code works. We've taken steps to confirm to ourselves and to others that the code is fit for purpose.
+我们知道代码是有效的。我们已经采取措施向自己和他人确认代码符合用途。
+It solves the right problem.
+它解决了正确的问题。
+It handles error cases gracefully and predictably: it doesn't just consider the happy path. Errors should provide enough information to help future maintainers understand what went wrong.
+它优雅且可预测地处理错误情况：它不只是考虑了顺利的路径。错误应该提供足够的信息，以帮助未来的维护者理解出了什么问题。
+It’s simple and minimal - it does only what’s needed, in a way that both humans and machines can understand now and maintain in the future.
+它简洁且精简——它只做所需之事，以一种人类和机器现在都能理解并在未来可以维护的方式。
+It's protected by tests. The tests show that it works now and act as a regression suite to avoid it quietly breaking in the future.
+它受到测试的保护。测试表明它现在可以正常工作，并作为回归测试套件，以避免它在未来悄无声息地失效。
+It's documented at an appropriate level, and that documentation reflects the current state of the system - if the code changes an existing behavior the existing documentation needs to be updated to match.
+它在适当的层面上有文档记录，并且该文档反映了系统的当前状态——如果代码改变了现有行为，现有的文档需要更新以匹配。
+The design affords future changes. It's important to maintain YAGNI - code with added complexity to anticipate future changes that may never come is often bad code - but it's also important not to write code that makes future changes much harder than they should be.
+设计允许未来的变更。维护 YAGNI（你永远不需要它）很重要——添加了复杂性的代码以预期可能永远不会发生的未来变更通常是坏代码——但是编写让未来的变更比应该的更难的代码也同样重要。
+All of the other relevant "ilities" - accessibility, testability, reliability, security, maintainability, observability, scalability, usability - the non-functional quality measures that are appropriate for the particular class of software being developed.
+所有其他相关的"能力"——可访问性、可测试性、可靠性、安全性、可维护性、可观察性、可扩展性、可用性——适用于正在开发的特定类别的软件的非功能性质量指标。
+Coding agent tools can help with most of this, but there is still a substantial burden on the developer driving those tools to ensure that the produced code is good code for the subset of good that's needed for the current project.
+编码代理工具可以解决大部分问题，但仍然有相当大的负担落在驱动这些工具的开发者身上，以确保生成的代码是当前项目所需的良好代码子集中的良好代码。
+
+We need to build new habits #
+我们需要建立新的习惯 #
+The challenge is to develop new personal and organizational habits that respond to the affordances and opportunities of agentic engineering.
+挑战在于培养新的个人和组织习惯，以应对代理工程提供的便利和机会。
+
+These best practices are still being figured out across our industry. I'm still figuring them out myself.
+这些最佳实践仍在整个行业中被探索。我自己仍在探索它们。
+
+For now I think the best we can do is to second guess ourselves: any time our instinct says "don't build that, it's not worth the time" fire off a prompt anyway, in an asynchronous agent session where the worst that can happen is you check ten minutes later and find that it wasn't worth the tokens.
+目前我认为我们能做的最好的事情就是反问自己：每当我们的直觉说“不要构建那个，不值得花时间”时，仍然在异步代理会话中发送一个提示，最坏的情况是十分钟后再检查发现不值得消耗代币。
+```
+
+
+
 ## 基本原则
 
 ### 模块化
 
 ### 分层架构
 
+
+
+
+
 # 测试
 
 # 开发规范