CAT
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Cs Learn

liuzhengdongfortest/codestable
912 installs890 stars
Summary

Captures lessons learned and pitfalls from your development work into searchable markdown files in `.codestable/compound/`. Two tracks: pitfalls (what broke and why) and knowledge (better practices you discovered). Triggers when you say "沉淀知识" or "learning", or automatically at the end of feature/issue workflows when cs-feat-accept or cs-issue-fix ask if you want to record what happened. The interview is intentionally brief, one question at a time, and skips sections if you say "nothing to add". What makes this useful is it distinguishes between specs (what you built) and learning docs (what you figured out the hard way), so teams stop solving the same problem twice. Checks for duplicates before creating new files and can update existing learning docs instead.

Install to Claude Code

npx -y skills add liuzhengdongfortest/codestable --skill cs-learn --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Files
SKILL.mdView on GitHub

cs-learn

启动必读

开始任何判断或动作前,先读取 .codestable/attention.md;缺失则视为骨架不完整,提示先补齐或运行 cs-onboard,不要回退到外部 AI 入口文件。

每次做 feature 或修 issue 都会留下 spec 文件。但 spec 记录的是"做了什么"和"怎么做的",不会记录"踩了什么坑"和"发现了什么更好的做法"。没有沉淀的团队总在重复解决同一个问题。

两条轨道:

  • 坑点轨道(pitfall):记录问题 / 根因 / 解法,防止下次再掉进同一个坑
  • 知识轨道(knowledge):记录最佳实践 / 工作流改进 / 可复用模式

两者都写入 .codestable/compound/(共享目录见 shared-conventions.md 第 1 节"归档类文档")。本技能产出 frontmatter 带 doc_type: learning,命名 YYYY-MM-DD-learning-{slug}.md。


什么时候触发

情境说明
完成 feature 工作流cs-feat-accept 主动问"要记录这次的学习点吗?"
完成 issue 工作流cs-issue-fix 主动问"要把这个坑记录下来吗?"
用户主动"记录一下"、"沉淀知识"、"learning"等
解决了一次性难题不在 feature / issue 内但花了大量时间才解决的工程问题

主动推荐一句话即可,用户说"不用了"立刻跳过——重复推可能让用户觉得 AI 在加戏。


两条轨道各写什么

坑点:调试过的 bug / 绕过的配置陷阱 / 环境问题 / 集成失败……一切"本来应该好但没好"的经历。

知识:发现的最佳实践 / 工作流改进 / 架构洞见 / 可复用设计模式……一切"以后应该默认这样做"的学习。

frontmatter / 正文模板 / 完整示例见同目录 reference.md。


工作流阶段

Phase 1:识别来源(自动)

从对话上下文提取:

  • 来源类型:feature 工作流 / issue 工作流 / 独立问题
  • 关联产物:feature 目录 / issue 目录路径(如有)
  • 粗分轨道:坑点 or 知识。"修了什么坏了的东西" = 坑点;"发现了什么更好做法" = 知识。两者都有就分两条

来源不明确问用户一个问题澄清不要猜。

Phase 1.5:查重叠与意图分流(必做)

按 shared-conventions.md §6 第 5/6 条:

  • 含"改 / 更新 / 补充 / 某条 learning"或指向某份旧文档 → 直接走更新已有
  • 否则用搜索工具按 --filter tags~= 或 --query 查一遍,命中相近旧文档时把候选列给用户

更新路径:读旧文档 → 和用户对齐要改哪几节(常见是补新踩的坑、补当时"没找到原因"的根因)→ 起草 diff → 写回原文件 + updated: YYYY-MM-DD,不新建。

Phase 2:提炼要点(一次一个问题)

坑点轨道问:

  1. "你最开始观察到的现象是什么?"
  2. "哪些解法试过但没用?"(鼓励写,失败的尝试是后人最宝贵的信息——知道哪条路不通能省下大量时间)
  3. "最终怎么发现真正原因的?"
  4. "下次可以更早发现吗?怎么发现?"

知识轨道问:

  1. "你发现的这个模式,在什么情境下最有价值?"
  2. "不这样做会出什么问题?"
  3. "有没有不适用的反例?"

用户对某问题说"没什么"或"跳过"就跳过——宁可少一节也不用空话填充。

Phase 3:起草 + 用户 review

AI 一次性起草完整文档(YAML frontmatter + 所有正文节)。一次性展示给用户。

Phase 4:归档

  • 新建:写入 compound/YYYY-MM-DD-learning-{slug}.md(日期取归档当天),frontmatter 带 doc_type: learning
  • 更新:写回 Phase 1.5 定位的原文件 + updated: YYYY-MM-DD
  • supersede:按 shared-conventions.md §6 第 5 条处理

Phase 5:可发现性检查

写完若发现一两行"每次 CodeStable 技能启动都该知道"的项目硬约束,提示用户用 cs-note 追加到 .codestable/attention.md。不要自作主张改 attention,也不要写外部 AI 入口。


搜索工具

完整语法见 .codestable/reference/tools.md。

# 按轨道筛选坑点

python .codestable/tools/search-yaml.py --dir .codestable/compound --filter doc_type=learning --filter track=pitfall --filter severity=high

# 按组件查相关学习点

python .codestable/tools/search-yaml.py --dir .codestable/compound --filter doc_type=learning --filter component~={组件名}

# 归档后查重叠

python .codestable/tools/search-yaml.py --dir .codestable/compound --filter doc_type=learning --filter tags~={主要 tag} --json

守护规则

归档类共享规则见 shared-conventions.md 第 6 节。本技能特有:

  1. 不混入 spec——learning 不放进 features/ 或 issues/;spec 也不放进 compound/
  2. 只认自己的 doc_type——只读写 doc_type: learning
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Categories
Documentation
First SeenMay 16, 2026
View on GitHub

Recommended

More Documentation →
blog-writing-guide

getsentry/skills

blog writing guide
1.3k
761
technical-writing

supercent-io/skills-template

Create clear, comprehensive technical documentation for specs, architecture, runbooks, and APIs.
11.7k
88
user-guide-writing

supercent-io/skills-template

Create clear, user-focused documentation with step-by-step guides, screenshots, and FAQ sections.
10.7k
88
doc-writing

huangjia2019/claude-code-engineering

Generate API documentation from a route manifest. Use when you have a list of discovered routes and need to produce markdown documentation.
826
docs-sandpack

reactjs/react.dev

If you're working on React documentation with live code examples, this skill gives you the Sandpack patterns the React team actually uses.
11.7k
docs-writer-learn

reactjs/react.dev

If you're contributing to React documentation or building similar technical learning content, this skill knows the patterns cold.
11.7k