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

Dws

stvlynn/dingtalk-wukong-skills
145 installs114 stars
Summary

This is a comprehensive interface to DingTalk's entire product suite, from AI spreadsheets and calendars to approvals, meetings, and file storage. What stands out is the detailed intent routing system that helps Claude distinguish between easily confused operations like钉盘 file storage versus 文档 content editing, or personal chat messages versus bot webhooks. The skill enforces strict rules like always using JSON format flags, never fabricating UUIDs, and confirming destructive operations. It covers 17 different DingTalk products through a single CLI, which means you can build workflows that span spreadsheets, calendars, approvals, and notifications without switching contexts. The decision tree and intent guide are thorough enough to handle ambiguous requests properly.

Install to Claude Code

npx -y skills add stvlynn/dingtalk-wukong-skills --skill dws --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

钉钉全产品 Skill

通过 dws 命令管理钉钉产品能力。

严格禁止 (NEVER DO)

  • 不要使用 dws 命令以外的方式操作(禁止 curl、HTTP API、浏览器)
  • 不要编造 UUID、ID 等标识符,必须从命令返回中提取
  • 不要猜测字段名/参数值,操作前必须先查询确认

严格要求 (MUST DO)

  • 所有命令必须加 --format json 以获取可解析输出
  • 删除操作前必须加 --yes 并和用户确认
  • 单次批量操作不超过 100 条记录
  • 所有命令必须严格遵循对应产品参考文档里面规定的参数格式(如:如果有参数值,则参数和参数值之间至少用一个空格隔开)

产品总览

产品用途参考文件
aitableAI表格:表格/数据表/字段/记录增删改查/模板搜索aitable.md
calendar日历:日程/参与者/会议室/闲忙查询calendar.md
contact通讯录:用户查询(当前用户/搜索/详情)/部门查询(搜索/子部门/成员列表)contact.md
doc文档:搜索/浏览/读取/创建/更新文档/文件夹管理/块级编辑doc.md
chat群聊:群管理(建群/搜索/成员增删/改群名)/消息(拉取/发送/机器人群发/Webhook)/机器人搜索chat.md
todo待办:创建(含优先级/截止时间)/查询/修改/标记完成/删除todo.md
mail邮箱:查询邮箱/搜索/查看/发送邮件mail.md
minutesAI听记:列表/摘要/转写/关键字/标题修改minutes.md
report日志:收件箱/已发送/模版查看/详情/已读统计report.md
drive钉盘:浏览文件/元数据/下载/创建文件夹/上传文件drive.md
dingDING消息:发送/撤回(应用内/短信/电话)ding.md
devdoc开放平台文档:搜索开发文档simple.md
conference视频会议:预约会议simple.md
aiappAI应用:创建/查询/修改AI应用aiapp.md
live直播:查看直播列表simple.md
oaOA审批:待处理/详情/同意/拒绝/撤销/记录/已发起/任务oa.md
attendance考勤:打卡记录/排班查询attendance.md

意图判断决策树

用户提到"表格/多维表/AI表格/记录/数据" → aitable 用户提到"日程/日历/会议室/约会" → calendar 用户提到"通讯录/同事/部门/组织架构" → contact 用户提到"文档/知识库/写文档" → doc 用户提到"待办/TODO/任务提醒" → todo 用户提到"邮件/邮箱" → mail 用户提到"听记/会议录音/转写/AI摘要以及用户传入听记URL(如 https://shanji.dingtalk.com/*)" → minutes 用户提到"帮我做/建/生成/生成系统/AI应用/创建应用/智能应用" → aiapp 用户提到"DING/紧急消息/电话提醒" → ding 用户提到"考勤/打卡/排班" → attendance 用户提到"群聊/群消息/群成员/聊天记录/建群/机器人发消息/Webhook/通知" → chat 用户提到"审批/OA" → oa 用户提到"开发/API/调用错误 文档" → devdoc 用户提到“校招/发布职位/我的候选人” → ai_sincere_hire 用户提到"视频会议/预约会议" → conference 用户提到"直播" → live 用户提到"日志/日报/周报/日志统计" → report 用户提到"钉盘/文件/网盘/下载文件/上传文件" → drive 用户提到"企业信用/工商信息/股东/裁判文书/风险/商标/专利/招投标/联系方式/KP" → credit 用户提到"法律咨询/法规/案例/法条/判例/法律依据" → law

关键区分: aitable(数据表格) vs doc(文档编辑) 关键区分: report(钉钉日志/日报周报) vs doc(文档编辑) vs todo(待办任务) 关键区分: drive(钉盘文件存储/上传/下载) vs doc(钉钉文档内容读写/知识库空间) 关键区分: conference(视频会议预约) vs calendar event(日历日程管理) 关键区分: chat message send(个人身份群发) vs send-by-bot(机器人发消息) vs send-by-webhook(Webhook告警)

更多易混淆场景及用户表达示例,见 intent-guide.md

核心流程

作为一个智能助手,你的首要任务是理解用户的真实、完整的意图,而不是简单地执行命令。在选择 dws 的产品命令前,必须严格遵循以下三步流程:

  1. 意图分类:首先,判断用户指令的核心 动词/动作 属于哪一类。这比关注名词更重要。
  2. 歧义处理与信息追问:如果用户指令模糊或包含多个产品的关键字,严禁猜测。必须主动向用户追问以澄清意图。这是你作为智能助手而非命令执行器的核心价值。
  3. 精准产品映射:在完成前两步,意图已经清晰后,参考产品总览和意图判断决策树 来选择产品。
  4. 充分阅读产品参考文件,通过编写代码或直接调用指令实现用户意图。

错误处理

  1. 遇到错误,加 --verbose 重试一次
  2. 仍然失败,报告错误信息给用户
  3. 禁止自行尝试替代方案
  4. 如果出现身份校验失败,可以使用 dws auth login 进行登录

详细参考 (按需读取)

  • references/products/ — 各产品命令详细参考
  • references/intent-guide.md — 意图路由指南(易混淆场景对照)
  • references/global-reference.md — 全局标志、认证、输出格式
  • references/field-rules.md — AI表格字段类型规则
  • references/error-codes.md — 错误码 + 调试流程
  • scripts/ — AI表格批量操作脚本
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 SeenJun 3, 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