Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →

breath57/dingtalk-skills

9 skills4.9k installs873 starsGitHub

Install

npx skills add https://github.com/breath57/dingtalk-skills

Skills in this repo

1Dingtalk DocumentThe dingtalk-document skill handles DingTalk wiki workspaces and document nodes with a strategy-first workflow before any API call. Core concepts include workspaces with workspaceId and rootNodeId, FILE or FOLDER nodes, docKey or dentryUuid identifiers for content APIs, and operatorId unionId requirements via scripts/dt_helper.sh. Each task validates only required config keys such as DINGTALK_APP_KEY, APP_SECRET, MY_USER_ID, and MY_OPERATOR_ID, collecting missing values once before execution. Multi-line commands must run from /tmp scripts because terminal tools truncate heredocs. references/api.md sections are grepped per operation for create, read, write, delete, and member management. Token cache uses --nocache on 401 responses. Credentials are never printed in full. Use when users mention DingTalk docs, knowledge bases, or dingtalk doc operations.1.7kinstalls2Dingtalk MessageThe dingtalk message skill 钉钉消息发送。当用户提到"钉钉消息"、"发消息"、"发通知"、"群通知"、"群消息"、"Webhook"、"机器人消息"、"机器人发消息"、"工作通知"、"单聊消息"、"群聊消息"、"撤回消息"、"消息已读"、"发送Markdown"、"发卡片消息"、"ActionCard"、"@某人"、"@员工"、"at某人"、"提醒某人"、"dingtalk message"、"send message"、"robot message"、"work notification"时使用此技能。支持:群自定义 Webhook 机器人(文本/Markdown/ActionCard/Link/FeedCard + 加签 + @某人)、企业内部应用机器人单聊和群聊发送、消息撤回、已读查询、工作通知等全部消息类操作。. Documentation covers workflows, commands, and guardrails agents should follow when users invoke this capability. Key documented areas include **识别通道** → 按 api.md「场景路由」判断属于哪个通道; **校验配置** → `bash scripts/dt_helper.sh --get KEY` 读取该通道所需键值; **收集缺失项** → 一次性询问并 `bash scripts/dt_helper.sh --set KEY=VALUE` 写入; **获取 Token** → 机器人用 `--token`;工作通知用 `--old-token`;Webhook/sessionWebhook 无需. Reference commands include set -e; HELPER="./scripts/dt_helper.sh". Use when developers or agents need structured guidance for dingtalk message tasks with evidence grounded in the bundled SKILL.md rather than generic advice. **识别通道** → 按 api.md「场景路由」判断属于哪个通道 **校验配置** → `bash scripts/dt_helper.sh --get KEY` 读取该通道所需键值 **收集缺失项** → 一次性询问并 `bash scripts/dt_helper.sh --set KEY=VALUE` 写入 **获取 Token** → 机器人用 `--token`;工作通知用 `--old-token`;Webho.1.5kinstalls3Dingtalk Ai Tabledingtalk-ai-table is a breath57/dingtalk-skills agent integration listed on skills.sh with 513 installs that lets coding agents interact with DingTalk AI Tables. Agents can read rows, write new records, and update existing structured table data inside DingTalk workflows without bespoke API clients for every automation script. Developers reach for dingtalk-ai-table when building internal bots, approval flows, or ops automations that must sync with DingTalk spreadsheets used by teams in China-centric enterprise chat environments. The skill targets agent-tooling scenarios where table state is the system of record for lightweight business processes.596installs4Dingtalk Tododingtalk-todo is a Claude Code skill from breath57/dingtalk-skills that connects agent sessions to DingTalk's todo APIs. The skill lets agents create tasks, assign owners, update status, and track completion while you stay inside a coding or review workflow. It targets teams on DingTalk who want engineering work—bug fixes, refactors, follow-ups—captured as trackable todos instead of chat-only promises. Typical flows start from a PR comment, incident note, or standup summary and end with structured todos linked to the right assignees. Reach for dingtalk-todo when you need programmatic task creation from Claude or Cursor during development, especially in enterprise environments where DingTalk is the system of record for cross-team handoffs. The skill maps coding-session context—stack traces, PR links, owner handles—into DingTalk fields so tasks stay traceable across sprints. It reduces context loss when agents finish a fix but follow-ups must persist in the enterprise task board.377installs5Dingtalk Contactdingtalk-contact is a breath57/dingtalk-skills module for connecting AI agents to DingTalk enterprise contact endpoints. It guides directory lookup, contact sync, and messaging workflow setup when building SaaS or internal tools that must read or act on DingTalk org data. Developers reach for dingtalk-contact when agents need authenticated calls to DingTalk contact APIs instead of manual OpenAPI exploration. The skill fits enterprise integrations where Claude or Cursor agents orchestrate HR directory queries, contact synchronization jobs, or notification flows against DingTalk backends.284installs6Dingtalk CalendarThe dingtalk-calendar skill helps developers integrate DingTalk’s enterprise calendar into automated workflows: listing events, creating meetings, updating times, and aligning reminders with DingTalk’s API expectations. It is aimed at teams using DingTalk for internal scheduling who want agents or backend jobs to manage calendars without manual UI steps or guessing payload formats.241installs7Dingtalk Ai Web SearchEnables Claude Code to integrate DingTalk AI assistants with web search providers so enterprise chat bots can fetch current information, format cited replies, and automate research workflows inside DingTalk channels.149installs8Dingtalk Skill CreatorA standardized workflow for packaging a DingTalk API domain into a reusable Claude skill. It runs SDK exploration, then Python SDK tests, then pure-HTTP requests tests, and only writes the SKILL.md once both test stages pass fully. It enforces DingTalk's new-vs-old API token rules and probes 403 responses to collect required permission scopes. A developer uses it to build tested DingTalk skills for to-dos, attendance, approvals, and similar. The documentation is written in Chinese.70installs9Skill CreatorCreates new Claude skills and iteratively improves existing ones. It walks a loop of capturing intent, writing a draft SKILL.md, generating test prompts, running them, evaluating results both qualitatively and quantitatively, and rewriting until the skill is good. It also runs a description improver to optimize how reliably the skill triggers. A developer uses it to author or optimize a skill from scratch or from an existing draft.43installs

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.

breath57/dingtalk-skills · 9 skills · Skillselion