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 Explore

liuzhengdongfortest/codestable
914 installs890 stars
Summary

This one helps you explore a codebase and turn your investigation into searchable evidence, so the second time you ask "how does X work here" you find the answer in five minutes instead of two hours. It writes structured exploration docs in three flavors: answering a specific question, mapping out a module, or doing a lightweight technical spike. The format forces you to put conclusions first, then back them with actual file and line references. It checks for overlapping explorations before you start, can update old ones when code changes, and won't let you write "looks like" without proof. Good for onboarding or when you need to build shared knowledge before making design decisions.

Install to Claude Code

npx -y skills add liuzhengdongfortest/codestable --skill cs-explore --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-explore

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。

同一个问题第一次花两小时查代码,第二次应该五分钟内找到答案——前提是第一次做完留下证据化的记录。cs-explore 把"提问 → 读代码 → 得结论"沉淀成可检索的探索文档。


适用场景

  • 新人入仓快速理解模块边界 / 调用链 / 入口
  • 用户提具体问题但暂时不要求直接产出方案 / 修复
  • feature-design / issue-analyze / issue-fix 前先补一轮证据化探索
  • 技术方向还在讨论,需要轻量 spike(只探索不拍板)

本技能只负责"看到了什么"的证据化记录。用户意图是别的(拍板 / 处方 / 修 bug)让用户按场景选对应子技能。

共享路径与命名约定看 .codestable/reference/shared-conventions.md。产物写入 .codestable/compound/,命名 YYYY-MM-DD-explore-{slug}.md,frontmatter 带 doc_type: explore。


三种探索类型

frontmatter 的 type 字段:

类型适用情境
question围绕一个具体问题查代码并给结论
module-overview快速梳理某模块结构 / 边界 / 入口 / 依赖
spike对多个可能方向做轻量技术探查(不做最终决策)

文档格式

frontmatter / 正文结构 / 各节写法说明和示例见同目录 reference.md。流程约束:

  • 速答必须先于证据出现——读者打开先看到结论再决定要不要往下看证据
  • 结论必须可回溯到证据,不允许纯猜测
  • 证据不足时 confidence 必须降为 medium 或 low
  • 旧探索过期:旧文档标 outdated,新增当前版本

工作流阶段

Phase 1:收敛探索问题

最多两个问题:

  1. "你最想先回答的一个问题是什么?"
  2. "希望聚焦哪个模块 / 目录?"

用户描述已清楚直接进 Phase 1.5。

Phase 1.5:查重叠与意图分流(必做)

按 shared-conventions.md §6 第 5/6 条执行:

  • 含"更新 / 复查 / 某次 explore / 这个模块之前探过"或指向某份旧 explore → 走更新或 supersede。explore 特性:代码已变导致旧结论失效时旧文档 status: outdated + 新建一份(supersede);只补证据 / 收紧结论但核心结论未变时走"更新已有"
  • 否则用搜索工具按关键词 / 模块查一遍,命中相近旧 explore 时先读它,能直接回答就告诉用户"已有一份在 {路径},复用还是重探一遍?"

更新路径:读旧文档 → 按 Phase 2 补证据 → 改写速答节 → 写回原文件 + updated: YYYY-MM-DD。

Phase 2:证据化探索

  • 用 Glob / Grep / Read 真实读代码不靠猜
  • 边读边积累证据;同步思考每条证据支撑哪个结论——不支撑任何结论的证据不记录
  • 关键证据 3-8 条,每条都标注 文件:行号
  • 多模块协作或 module-overview / spike 类型 → 准备一张 Mermaid 图放在速答节里
  • 形成初步结论后主动检查:已有证据能否说服持怀疑态度的人?够了就停不必扩大搜索

为什么"够了就停":探索不是穷举,是建立到"读者能信"为止的证据链。继续扩大只会让文档变长而不变可信。

Phase 3:起草与确认

  • 先写速答节,再回填关键证据——这个顺序很重要:先有结论再回头看证据是否真支持,能逼你检查每条证据的实际效力
  • AI 一次性起草完整文档,用户 review 后确认
  • 有修改按反馈修订后再落盘

Phase 4:归档

  • 新建:写入 .codestable/compound/YYYY-MM-DD-explore-{slug}.md,frontmatter 带 doc_type: explore
  • 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;旧文档 status: outdated + superseded-by

Phase 5:给出下一步建议

证据收齐后一句话提示下一步方向("要不要基于这份 explore 去设计方案")。用户说"不用"就跳过——下一步由用户自己决定。


搜索工具

完整语法见 .codestable/reference/tools.md。

# 按类型筛选

python .codestable/tools/search-yaml.py --dir .codestable/compound --filter doc_type=explore --filter type=module-overview --filter status=active

# 归档后查重叠

python .codestable/tools/search-yaml.py --dir .codestable/compound --filter doc_type=explore --query "{关键词}" --json

退出条件

  • 已明确探索问题与范围
  • 速答节给出核心结论(结论前置)
  • 关键证据 3-8 条,每条标 file:line 并说明支撑哪个结论
  • 多模块或 module-overview / spike 类型时速答节有 Mermaid 图
  • 文档已归档到 compound/
  • 已给出后续建议

守护规则

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

  • 不读代码直接给结论
  • 证据只写"看起来像"不写 file:line
  • 结论写在证据之后——速答节必须在关键证据节之前
  • 证据节比速答节长数倍——精简证据,不支撑结论的删掉
  • 跨模块流程没 Mermaid 图,只靠文字描述
  • 提前拍板——explore 只记"看到了什么"不下"以后应该怎么做"
  • 直接给处方没证据链——每条结论必须回溯到 file:line
  • 历史 explore 已过期却继续引用,不做 status 标注
  • 读写非 doc_type=explore 的文档——本技能只负责 explore
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 →
First SeenMay 16, 2026
View on GitHub

Recommended

caveman

juliusbrussee/caveman

Ultra-compressed communication mode cutting token usage ~75% while preserving technical accuracy.
203.4k
67.8k
grill-me

mattpocock/skills

Relentless interviewing skill that stress-tests plans and designs through systematic questioning.
250.9k
114.5k
improve

shadcn/improve

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for other models/agents to execute.
10
205
systematic-debugging

obra/superpowers

Structured debugging methodology that mandates root cause investigation before attempting any fixes.
124.6k
215.9k
karpathy-guidelines

forrestchang/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.
13.9k
165.4k
find-skills

vercel-labs/skills

Discover and install specialized agent skills from the open ecosystem when users need extended capabilities.
1.8M
21.1k