Technical Analyst
tradermonty/claude-trading-skills
This skill should be used when analyzing weekly price charts for stocks, stock indices, cryptocurrencies, or forex pairs.
钉钉通讯录精确查询。Use when 已有 userId 后查详情、部门、职位或邮箱，按完整手机号反查用户，或查询自己、部门成员及角色。姓名模糊搜索、工号、职责、上下级走 dingtalk-aisearch，拿到 userId 后用本 skill 补详情。命令前缀：dws contact。
Install Dingtalk Contact
$ npx skills add DingTalk-Real-AI/dingtalk-workspace-cli --skill dingtalk-contact -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install DingTalk-Real-AI/dingtalk-workspace-cli dingtalk-contact --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/DingTalk-Real-AI/dingtalk-workspace-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/multi/dingtalk-contact .claude/skills/dingtalk-contact && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "dingtalk-contact" agent skill from https://github.com/DingTalk-Real-AI/dingtalk-workspace-cli/tree/main/skills/multi/dingtalk-contact into .claude/skills/dingtalk-contact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dingtalk-contact", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/DingTalk-Real-AI/dingtalk-workspace-cli/tree/main/skills/multi/dingtalk-contactType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add DingTalk-Real-AI/dingtalk-workspace-cli --skill dingtalk-contact -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install DingTalk-Real-AI/dingtalk-workspace-cli dingtalk-contact --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DingTalk-Real-AI/dingtalk-workspace-cli.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/multi/dingtalk-contact .agents/skills/dingtalk-contact && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "dingtalk-contact" agent skill from https://github.com/DingTalk-Real-AI/dingtalk-workspace-cli/tree/main/skills/multi/dingtalk-contact into .agents/skills/dingtalk-contact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dingtalk-contact", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add DingTalk-Real-AI/dingtalk-workspace-cli --skill dingtalk-contact -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install DingTalk-Real-AI/dingtalk-workspace-cli dingtalk-contact --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DingTalk-Real-AI/dingtalk-workspace-cli.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/multi/dingtalk-contact .cursor/skills/dingtalk-contact && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "dingtalk-contact" agent skill from https://github.com/DingTalk-Real-AI/dingtalk-workspace-cli/tree/main/skills/multi/dingtalk-contact into .cursor/skills/dingtalk-contact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dingtalk-contact", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/DingTalk-Real-AI/dingtalk-workspace-cli.git --path skills/multi/dingtalk-contact--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add DingTalk-Real-AI/dingtalk-workspace-cli --skill dingtalk-contact -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install DingTalk-Real-AI/dingtalk-workspace-cli dingtalk-contact --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DingTalk-Real-AI/dingtalk-workspace-cli.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/multi/dingtalk-contact .gemini/skills/dingtalk-contact && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "dingtalk-contact" agent skill from https://github.com/DingTalk-Real-AI/dingtalk-workspace-cli/tree/main/skills/multi/dingtalk-contact into .gemini/skills/dingtalk-contact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dingtalk-contact", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install DingTalk-Real-AI/dingtalk-workspace-cli dingtalk-contactInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add DingTalk-Real-AI/dingtalk-workspace-cli --skill dingtalk-contact -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/DingTalk-Real-AI/dingtalk-workspace-cli.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/multi/dingtalk-contact .github/skills/dingtalk-contact && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "dingtalk-contact" agent skill from https://github.com/DingTalk-Real-AI/dingtalk-workspace-cli/tree/main/skills/multi/dingtalk-contact into .github/skills/dingtalk-contact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dingtalk-contact", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add DingTalk-Real-AI/dingtalk-workspace-cli --skill dingtalk-contact -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install DingTalk-Real-AI/dingtalk-workspace-cli dingtalk-contact --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DingTalk-Real-AI/dingtalk-workspace-cli.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/multi/dingtalk-contact .opencode/skills/dingtalk-contact && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "dingtalk-contact" agent skill from https://github.com/DingTalk-Real-AI/dingtalk-workspace-cli/tree/main/skills/multi/dingtalk-contact into .opencode/skills/dingtalk-contact/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dingtalk-contact", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
dingtalk-contact- GitHub stars
- 3.2k
- Token cost
- ~2.2k tokens
- SKILL.md length
- 748 words
- Files
- 7 (incl. scripts, references)
- Skills in repo
- 17
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
钉钉通讯录精确查询。Use when 已有 userId 后查详情、部门、职位或邮箱，按完整手机号反查用户，或查询自己、部门成员及角色。姓名模糊搜索、工号、职责、上下级走 dingtalk-aisearch，拿到 userId 后用本 skill 补详情。命令前缀：dws contact。
- Works in 3 steps: 切 aisearch（必须）：dws aisearch person… → 解析（必须）：从结果取… → 补详情（必须）：要完整部门/职位/邮箱/主管时 dws contact user…
- 已有 userId 后查详情、部门、职位或邮箱，按完整手机号反查用户，或查询自己、部门成员及角色。姓名模糊搜索、工号、职责、上下级走 dingtalk-aisearch，拿到 userId 后用本 skill 补详情。命令前缀：dws contact
- SKILL.md covers 前置条件 — 执行操作前必读, Shortcuts（无专用脚本/recipe 时优先）, 意图表 and 标准 SOP（必遵流程）, plus 3 more sections
- Runs Python scripts from its folder; calls python
What it does
Dingtalk Contact is an agent skill from DingTalk-Real-AI/dingtalk-workspace-cli. 钉钉通讯录精确查询。Use when 已有 userId 后查详情、部门、职位或邮箱，按完整手机号反查用户，或查询自己、部门成员及角色。姓名模糊搜索、工号、职责、上下级走 dingtalk-aisearch，拿到 userId 后用本 skill 补详情。命令前缀：dws contact。
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including scripts and reference files (for example `references/08-directory.md`, `references/contact.md` and `references/intent-guide.md`).
It sits in Business, Finance & HR. The repository describes itself as: DingTalk Workspace is an officially open-sourced cross-platform CLI tool from DingTalk. It unifies DingTalk’s full suite of product capabilities into a single package, is… The licence is Apache-2.0.
When your agent uses it
- 已有 userId 后查详情、部门、职位或邮箱，按完整手机号反查用户，或查询自己、部门成员及角色。姓名模糊搜索、工号、职责、上下级走 dingtalk-aisearch，拿到 userId 后用本 skill 补详情。命令前缀：dws contact
Example prompts
- “/dingtalk-contact”
Requirements
- Python 3
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- 切 aisearch（必须）：dws aisearch person --query "<关键词>" --dimension <维度> --format json（姓名→name、工号→jobNumber、手机号语义线索→phone、负责人→duty、部门→department…
- 解析（必须）：从结果取 userId、title；多人同名禁止默认选第一个，必须批量 dws contact user get --ids --format json 拿部门/职位后让用户确认。
- 补详情（必须）：要完整部门/职位/邮箱/主管时 dws contact user get --ids --format json。
What it can do on your machine
Read from SKILL.md and the folder at commit 0a813a9. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Dingtalk Contact loads about 2.2k tokens when it runs, and up to ~16k if it reads all its reference files. Until then it costs about 41 tokens; SKILL.md has 748 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from DingTalk-Real-AI/dingtalk-workspace-cli at commit 0a813a9, republished under its Apache-2.0 licence (© DingTalk-Real-AI). 748 words, ~2,235 tokens.
Download SKILL.mdSave it as
.claude/skills/dingtalk-contact/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.- name
- dingtalk-contact
- description
- 钉钉通讯录精确查询。Use when 已有 userId 后查详情、部门、职位或邮箱，按完整手机号反查用户，或查询自己、部门成员及角色。姓名模糊搜索、工号、职责、上下级走 dingtalk-aisearch，拿到 userId 后用本 skill 补详情。命令前缀：dws contact。
- metadata.cli_version
- >=0.2.14
- metadata.category
- product
钉钉通讯录 Skill
前置条件 — 执行操作前必读
**CRITICAL — 执行任何
dws操作前，MUST 先用 Read 工具完整读取dingtalk-shared。**该轻量文件包含全局执行契约、安全底线及 shared references 的按需加载导航；不要预加载其全部 references。
命令参考：contact.md；剧本：08-directory.md。
<!-- VISIBLE_SHORTCUTS_START -->Shortcuts（无专用脚本/recipe 时优先）
以下 shortcut 同时进入公开 catalog 与 Runtime Schema。按本 skill/recipe 路由，命中时 Shortcut 优先于原子命令。参数只查 dws schema --cli-path "contact +<shortcut>" --compact --jq '{cli_path,parameters,constraints,confirmation}' -f json；仅需且已发布 result 时查 --jq '{cli_path,outcomes:.result.outcomes,pagination}'，字段级再查 data_schema；缺失不以 Help/样例推断。Schema 不可用才读一次已知 leaf Help；unknown flag 用同 leaf Help 修正一次。unknown command 禁 Help：错误 suggestion → 已加载 Skill/reference 明确入口；均无则报漂移。禁全 Catalog/root/parent/product Help；仅映射、接口或 provenance 审计省略 --compact。现有路由和 reference 均无法定位低频能力时，才用 dws shortcut list --service contact --format json 发现。
| Shortcut | 风险 | 适用场景 |
|---|---|---|
dws contact +by-mobile | read | 按手机号查询某人的完整资料（自动解析 userId 后取详情） |
dws contact +dept-members | read | 按部门名列出部门成员（自动解析 deptId） |
dws contact +friend-list | read | 查询当前用户的好友列表 |
dws contact +friend-remove | high-risk-write | 删除指定好友 |
dws contact +friend-request-accept | write | 同意指定用户发来的好友申请 |
dws contact +friend-request-list | read | 查询当前用户收到的好友申请列表 |
dws contact +friend-request-reject | write | 删除（忽略）指定用户发来的好友申请 |
dws contact +friend-request-send | write | 向指定用户发起好友申请 |
dws contact +list-dept-members | read | 查看部门成员（仅本部门，不含下级） |
dws contact +list-followings | read | 获取当前用户的特别关注列表 |
dws contact +list-role-members | read | 查询角色下的成员列表 |
dws contact +list-sub-depts | read | 查看指定部门的子部门 |
dws contact +lookup | read | 按姓名查询某人的完整资料（自动解析 userId 后取详情） |
dws contact +me | read | 查看我自己的通讯录资料（姓名/userId/手机/部门/组织，干净投影） |
dws contact +org | read | 按姓名查某人所在部门的详情（自动解析 userId 与 deptId） |
dws contact +resolve-dept | read | 按名称搜索部门并解析出唯一 deptId（只读） |
dws contact +search-mobile | read | 按手机号搜索通讯录用户 |
dws contact +search-user | read | 按关键词搜索通讯录用户 |
dws contact +team | read | 按姓名列出某人所在部门的成员（自动解析 userId 与 deptId） |
<!-- VISIBLE_SHORTCUTS_END -->意图表
| 用户说 | 命令 |
|---|---|
| "查我自己的信息" | dws contact user get-self |
| "按 userId 查详情" | dws contact user get --ids <userId1>,<userId2>,...（多个并行） |
| "完整手机号反查用户" | dws contact user search-mobile --mobile <手机号> |
| "按开放钉钉号ID（openDingTalkId）取 userId" | dws contact user get-by-open-dingtalk-id --id <openDingTalkId> |
| "我的好友 / 好友列表 / 有哪些好友" | dws contact +friend-list |
| "好友申请 / 谁加我 / pending 好友请求" | dws contact +friend-request-list |
| "加好友 / 发送好友申请 / 添加某人为好友" | dws contact +friend-request-send --to <openDingTalkId> |
| "同意好友申请 / 接受加好友" | dws contact +friend-request-accept --from <openDingTalkId> |
| "拒绝好友申请 / 忽略好友申请" | dws contact +friend-request-reject --from <openDingTalkId> |
| "删除好友 / 移除好友" | dws contact +friend-remove --friend <openDingTalkId>（高风险，需用户确认） |
| "按部门名拉成员" | python scripts/contact_dept_members.py --query "<部门名>" |
| "搜部门" | dws contact dept search --query "<关键词>" |
| "部门成员列表" | dws contact dept list-members --ids <deptId> |
| "列出企业角色 / 有哪些角色" | dws contact label list |
| "按角色名查角色ID" | dws contact label get --names "<角色名>" |
| "查某角色下有哪些成员" | dws contact label list-members --id <labelId> |
标准 SOP（必遵流程）
命中以下意图必须按对应 SOP 顺序执行；禁止跳步、替换命令、编造 userId。每条命令必须带
--format json。姓名模糊搜索、工号、职责与上下级走dingtalk-aisearch；完整手机号精确反查走 contact；拿到 userId 后由 contact 补详情。
SOP-1 搜人（search-person）
触发：按姓名/工号/部门/职责/上下级找人，或用手机号线索做语义搜索。
- 切 aisearch（必须）：
dws aisearch person --query "<关键词>" --dimension <维度> --format json（姓名→name、工号→jobNumber、手机号语义线索→phone、负责人→duty、部门→department、上下级→supervisor/subordinate）。 - 解析（必须）：从结果取
userId、title；多人同名禁止默认选第一个，必须批量dws contact user get --ids <id1,id2,...> --format json拿部门/职位后让用户确认。 - 补详情（必须）：要完整部门/职位/邮箱/主管时
dws contact user get --ids <userId> --format json。
禁止：用 contact user search 做姓名或工号搜索、默认取首个候选、编造人员字段。完整手机号精确反查是 search-mobile 的唯一搜索例外。
SOP-1A 完整手机号精确反查（search-person-by-mobile）
触发：用户提供完整手机号并要求确认是谁或取得 userId。
- 执行（必须）：
dws contact user search-mobile --mobile "<完整手机号>" --format json。 - 补详情（按需）：从结果取
userId，需要部门、职位或邮箱时继续dws contact user get --ids <userId> --format json。
禁止：把完整手机号精确反查改走姓名搜索，或在未返回 userId 时猜测人员。
SOP-2 精确查人/补详情（search-user）
触发：已有 userId 要查完整详情，或要拿 userId 给下游（发消息/建待办/约日程）。
- 拿 userId（必须）：
dws aisearch person --query "<姓名>" --dimension name --format json→userId；多命中必须列候选请用户确认。 - 查详情（必须）：
dws contact user get --ids <userId> --format json，按返回字段（orgEmployeeModel下部门/职位/邮箱）答复。
禁止：用模糊关键词直接调 contact user search 凑数、编造未返回字段。
SOP-3 查自己（get-contact-self）
触发：我的信息/我的 userId/我的部门。
- 执行（必须）：
dws contact user get-self --format json，取orgEmployeeModel.userId/orgUserName/depts[].deptName/ 主管等。
禁止：把自己 userId 写死或猜测。
Show full SKILL.md (313 more words)Show less
SOP-4 查部门 / 角色（dept-and-relation）
触发：部门列表/部门成员/角色/角色成员。
- 执行（必须）：搜部门
dws contact dept search --query "<部门名>" --format json；某部门下子部门dws contact dept list-children --dept <父部门ID> --format json；部门成员dws contact dept list-members --ids <部门ID>[,<部门ID2>...] --format json；部门详情dws contact dept get-info --dept <部门ID> --format json。角色：dws contact label list/dws contact label get --names "<角色名>"/dws contact label list-members --id <labelId>。搜索企业根部门时服务端可能返回deptId=-1哨兵，后续list-children/list-members/get-info必须规范化为真实根部门deptId=1。 - 补详情（必须）：拿到 userId 后用
contact user get --ids补部门/职位；上下级关系优先经dingtalk-aisearch的supervisor/subordinate维度。
禁止：使用不存在的 contact dept list（已废弃/歧义）、编造 deptId/labelId、跳过 aisearch 维度直接猜上下级。
SOP-5 好友关系（friend）
触发：好友列表、好友申请、加好友、同意/拒绝申请、删除好友。
- 获取 openDingTalkId（必须）：好友命令全部以 开放钉钉号ID（openDingTalkId） 为身份键。openDingTalkId 的来源：①好友域自身数据——
dws contact +friend-list --format json/dws contact +friend-request-list --format json返回项的openDingTalkId字段，或好友事件消息体（user_contact_friend_request_received的src/dest_open_dingtalk_id、user_contact_friend_added的friend_open_dingtalk_id）；②按姓名等关键词搜人——dws contact user search --query "<姓名>" --format json（search_contact_by_key_word）结果同时返回userId与openDingTalkId。注意：aisearch person与contact user get-by-dingtalk-id只返回 userId、取不到 openDingTalkId；拿到openDingTalkId后如需 userId 再调dws contact user get-by-open-dingtalk-id --id <openDingTalkId> --format json。 - 查好友（必须）：
dws contact +friend-list --format json返回当前登录用户的好友名单（含昵称 nick、备注名 alias）、好友状态与分页信息；dws contact +friend-request-list --format json返回收到的好友申请（含申请人昵称 nick、申请留言、状态）与 pending 数量。向用户展示列表时优先用 nick / alias 标识好友，openDingTalkId 非必要不展示；汇报申请 status 时必须翻译为中文状态（1=待接受、3=已成为好友），不要直接显示数字。 - 写操作（必须）：发送申请
dws contact +friend-request-send --to <openDingTalkId> --remark "<验证留言>" --format json；同意dws contact +friend-request-accept --from <openDingTalkId> --format json；拒绝dws contact +friend-request-reject --from <openDingTalkId> --format json；删除好友dws contact +friend-remove --friend <openDingTalkId> --format json（最后一条为不可逆高风险写操作，必须先取得用户明确确认）。
禁止：把钉钉号（dingtalkId）与开放钉钉号ID（openDingTalkId）混用；在缺少 openDingTalkId 时直接执行写操作；删除好友不确认。
高频硬约束
- 通讯录问题必须调用
dws contact或dws aisearch获取实时结果；严禁只读USER.md、环境身份或静态上下文后直接回答。 - 查自己用
dws contact user get-self --format json，不要把me/self/current当作userId传给user get。 - 姓名模糊搜索、工号反查、职责或上下级搜索走
dws aisearch person；完整手机号精确反查走dws contact user search-mobile --mobile "<手机号>" --format json。拿到userId后按需dws contact user get --ids <userId> --format json补部门/职位/邮箱。 - 查询直属主管/上下级时，如果
contact user get没返回明确主管字段，必须继续dws aisearch person --query "<完整姓名或工号>" --dimension supervisor --format json，不要停在"可能需要进一步查询"。 - 多个同名候选时，批量
contact user get --ids id1,id2,... --format json获取部门/职位后再消歧；不要默认取第一个。 - 用户查询企业角色、角色ID、角色成员，或“管理员/财务/HR/主管”等角色类型人员时，走
contact label list/get/list-members；不要用dept list-members筛字段替代。 - 好友命令（
+friend-*）全部以 openDingTalkId 为身份键，不是 userId 也不是钉钉号；openDingTalkId 可从+friend-list/+friend-request-list响应、好友事件消息体，或contact user search（按关键词搜人，同时返回 userId 与 openDingTalkId）取得；aisearch person/get-by-dingtalk-id只返回 userId、取不到 openDingTalkId。 +friend-remove为不可逆高风险写操作，执行前必须向用户展示目标 openDingTalkId 并获取明确确认；确认后才可加--yes。
跨产品协作
- 姓名模糊搜索、上下级、谁负责、工号反查、手机号语义搜索 →
dingtalk-aisearch - 完整手机号精确反查 →
dws contact user search-mobile - 拿到 email 发邮件 → 切到
dingtalk-mail - 拿到 userId 发消息 → 切到
dingtalk-chat
局部意图与短流程
© DingTalk-Real-AI, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 6 other files (scripts, references) in skills/multi/dingtalk-contact of DingTalk-Real-AI/dingtalk-workspace-cli.
- SKILL.md
- references/08-directory.md
- references/contact.md
- references/intent-guide.md
- references/lite-recipes.md
- references/recipes/conventions.md
- scripts/contact_dept_members.py
Open the folder on GitHubat commit 0a813a9
Compare with similar skills
Dingtalk Contact next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Dingtalk Contact this skillDingTalk-Real-AI/dingtalk-workspace-cli | 3.2k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Technical Analysttradermonty/claude-trading-skills | 3k | 4 repos | ~4.6k | Automated safety check: Pass | MIT | |
| Theme Detectortradermonty/claude-trading-skills | 3k | 2 repos | ~4.9k | Automated safety check: Pass | MIT | |
| Creating Financial ModelsChen-zexi/open-ptc-agent | 729 | 3 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Stock APIzhangxiangliang/stock-api | 2k | — | ~507 | Automated safety check: Pass | MIT | |
| Itr Walakaranb192/itr-wala | 871 | — | ~3.6k | Automated safety check: Pass | MIT |
Similar skills
Theme Detector
tradermonty/claude-trading-skills
Detect and analyze trending market themes across sectors. An agent skill from tradermonty/claude-trading-skills.
Creating Financial Models
Chen-zexi/open-ptc-agent
This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions
Stock API
zhangxiangliang/stock-api
Fetch real-time stock quotes, K-line (candlestick) history, and search symbols for China A-shares, Hong Kong, and US markets.
Itr Wala
karanb192/itr-wala
File Indian income tax returns (ITR) for FY 2025-26 / AY 2026-27.
Tushare Data
zillionare/zillionare
面向中文自然语言的 Tushare 数据研究技能。用于把“看看这只股票最近怎么样”“帮我查财报趋势”“最近哪个板块最强”“北向资金在买什么”“给我导出一份行情数据”这类请求，转成可执行的数据获取、清洗、对比、筛选、导出与简要分析流程。适用于 A 股、指数、ETF/基金、财务、估值、资金流、公告新闻、板块概念与宏观数据等研究场景。
More from DingTalk-Real-AI/dingtalk-workspace-cli
All 17 skills in this repoDingtalk Minutes
DingTalk-Real-AI/dingtalk-workspace-cli
钉钉 AI 听记。Use when 查询或修改听记摘要、完整逐字稿、关键词、标签、行动项、录音、上传、思维导图、发言人洞察、ASR 热词/识别词配置或分享权限。写文档走 dingtalk-doc；建待办走 dingtalk-todo；日程走 dingtalk-calendar。命令前缀：dws minutes。
Dingtalk Aitable
DingTalk-Real-AI/dingtalk-workspace-cli
钉钉 AI 表格（多维表）业务操作。Use when 用户需要操作 AI 表格/多维表/Base/Table、应用模式/App 页面/Widget、建表、查写记录、字段、记录评论、评论回复、访问密钥（API Key）、SQL/PostgreSQL/SELECT/JOIN、筛选、排序、公式、模板、批量导入 CSV 或 JSON、导出、仪表盘、图表、上传附件、数据源配置与同步、按任务 ID…
Dingtalk Aicard
DingTalk-Real-AI/dingtalk-workspace-cli
Create, edit, and validate DingTalk AI Card (A2UI) JSON files offline.
Dingtalk Aisearch
DingTalk-Real-AI/dingtalk-workspace-cli
AI搜问：人员语义搜索、跨源主题检索与行为回溯。Use when 语义找人，或目标未知时按主题或行为发现内容。原生最近列表走所属产品；完整手机号精确反查走 dingtalk-contact。前缀：dws aisearch。
Dingtalk Calendar
DingTalk-Real-AI/dingtalk-workspace-cli
钉钉日历与会议室。Use when 用户说 约会议/查日程/订会议室/查闲忙/加参会人/改期/取消会议/今天的日程/本周日程/共同空闲。不做视频会议发起/邀请入会/会中控制（走 dingtalk-misc）、AI 听记（走 dingtalk-minutes）、待办任务（走 dingtalk-todo）。命令前缀：dws calendar。
Dingtalk Mail
DingTalk-Real-AI/dingtalk-workspace-cli
钉钉邮箱读写、搜索、回复与转发。Use when 用户说发邮件/查邮件/回邮件/转发邮件/未读邮件/邮件搜索/邮箱附件。一句话发邮件时先用 dingtalk-contact 解析并确认收件人，再由本 skill 发送；不做钉钉消息（走 dingtalk-chat）、紧急通知（走 dingtalk-misc）。命令前缀：dws mail。
Related
Categories
Questions about Dingtalk Contact
What does Dingtalk Contact do?
钉钉通讯录精确查询。Use when 已有 userId 后查详情、部门、职位或邮箱，按完整手机号反查用户，或查询自己、部门成员及角色。姓名模糊搜索、工号、职责、上下级走 dingtalk-aisearch，拿到 userId 后用本 skill 补详情。命令前缀：dws contact。. Dingtalk Contact is an agent skill from DingTalk-Real-AI/dingtalk-workspace-cli.
When should I use Dingtalk Contact?
Dingtalk Contact fits situations like: 已有 userId 后查详情、部门、职位或邮箱，按完整手机号反查用户，或查询自己、部门成员及角色。姓名模糊搜索、工号、职责、上下级走 dingtalk-aisearch，拿到 userId 后用本 skill 补详情。命令前缀：dws contact.
How do I install Dingtalk Contact in Claude Code?
Run `npx skills add DingTalk-Real-AI/dingtalk-workspace-cli --skill dingtalk-contact -a claude-code`. Or copy the skill folder (skills/multi/dingtalk-contact in DingTalk-Real-AI/dingtalk-workspace-cli) into .claude/skills/dingtalk-contact in your project. Claude Code loads it when a task matches its description.
How do I install Dingtalk Contact in Codex?
Run `npx skills add DingTalk-Real-AI/dingtalk-workspace-cli --skill dingtalk-contact -a codex`. Or copy the skill folder (skills/multi/dingtalk-contact in DingTalk-Real-AI/dingtalk-workspace-cli) into .agents/skills/dingtalk-contact in your project. Codex loads it when a task matches its description.
Can I use Dingtalk Contact in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add DingTalk-Real-AI/dingtalk-workspace-cli --skill dingtalk-contact -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dingtalk-contact, .gemini/skills/dingtalk-contact, .github/skills/dingtalk-contact and .opencode/skills/dingtalk-contact in your project.
What does Dingtalk Contact need to run?
Going by SKILL.md and its folder, Dingtalk Contact needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Dingtalk Contact access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Dingtalk Contact safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Dingtalk Contact use?
Dingtalk Contact is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Dingtalk Contact use?
About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 14k tokens, read only when the agent opens those files.
What are the alternatives to Dingtalk Contact?
Skills that share tags, products or a category with Dingtalk Contact: Technical Analyst (tradermonty/claude-trading-skills, 3k stars), Theme Detector (tradermonty/claude-trading-skills, 3k stars), Creating Financial Models (Chen-zexi/open-ptc-agent, 729 stars) and Stock API (zhangxiangliang/stock-api, 2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Dingtalk Contact?
DingTalk-Real-AI (a GitHub organization) maintains it in DingTalk-Real-AI/dingtalk-workspace-cli, which has 3,246 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 10, 2026.
Source: DingTalk-Real-AI/dingtalk-workspace-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.