← 返回 Skills 市场
ianen

dingtalk-cli

作者 MianPeng Zheng · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
261
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install dingtalk-cli
功能描述
当用户提到钉钉知识库、钉钉文档、读取/写入文档、知识库目录、文档成员、`.axls` 表格、workbook、dingtalk doc、wiki workspace 时使用。通过本地 `dingtalk-cli` 命令调用钉钉开放平台 API，适合 agent 直接执行。
使用说明 (SKILL.md)

dingtalk-cli

dingtalk-cli 是面向 agent 的钉钉文档 CLI，覆盖：

  • 知识库列表与详情
  • 节点查询、URL 反查
  • 文档创建、正文读取、Markdown 覆盖写入、删除
  • .axls 钉钉表格的 workbook/sheet/range 读取
  • 文档成员添加、更新、移除

安装

pip install dingtalk-cli

如需从源码开发安装：

pip install -e .

启动前配置

优先使用命令保存配置：

dingtalk-cli auth setup \
  --app-key \x3CAPP_KEY> \
  --app-secret \x3CAPP_SECRET> \
  --operator-union-id \x3CUNION_ID>

如果只有 userId：

dingtalk-cli auth setup \
  --app-key \x3CAPP_KEY> \
  --app-secret \x3CAPP_SECRET> \
  --operator-user-id \x3CUSER_ID>

配置会写到 ~/.dingtalk-cli/config.json。也可用环境变量覆盖：

  • DINGTALK_APP_KEY
  • DINGTALK_APP_SECRET
  • DINGTALK_OPERATOR_ID
  • DINGTALK_CLI_CONFIG_DIR

注意：

  • 写操作必须带真实用户身份 operatorId，且应为 unionId
  • 输出中不会打印完整凭证，只显示脱敏值

常用命令

# 看知识库
dingtalk-cli workspace list --all

# 用 URL 反查节点
dingtalk-cli node resolve-url "https://alidocs.dingtalk.com/i/nodes/xxx"

# 读取文档正文
dingtalk-cli doc read --url "https://alidocs.dingtalk.com/i/nodes/xxx"

# 覆盖写入文档
dingtalk-cli doc overwrite --doc-key \x3CDOC_KEY> --content-file /abs/path/content.md --yes

# 若立即删除刚创建的文档，优先使用 create 返回的 workspace_id + node_id
dingtalk-cli doc delete --workspace-id \x3CWORKSPACE_ID> --node-id \x3CNODE_ID> --yes

# 读取 .axls 表格
dingtalk-cli workbook read --node-id \x3CNODE_ID> --range A1:Z80

# 添加成员
dingtalk-cli member add --node-id \x3CNODE_ID> --member-id \x3CUSER_ID> --role editor

Agent 使用约定

  • 优先使用 --json
  • 对破坏性命令显式传 --yes
  • 读取普通文档用 doc
  • 读取 .axls 用 workbook
  • 若 doc read 返回“目标节点是 .axls”，不要重试同一命令，直接切到 workbook
  • 对创建命令返回的结果，立即读写时优先使用 doc_key
  • 对创建后立即删除的场景，优先使用返回的 workspace_id + node_id

错误提示

  • MissingoperatorId：未配置 operator unionId
  • paramError：把 userId 当成 unionId 传了
  • Forbidden.AccessDenied.AccessTokenPermissionDenied：应用权限不够
  • Target document should be doc.：目标不是普通文档，通常应改走 workbook
安全使用建议
This skill's instructions require DingTalk app credentials and will write them to ~/.dingtalk-cli/config.json or read them from environment variables, but the registry entry does not declare those requirements — that's an inconsistency you should resolve before installing. Before using: (1) verify the dingtalk-cli package source (PyPI project page, GitHub repo) and review its code or install in an isolated environment; (2) prefer providing a scoped service account or short-lived credentials, not a full human account; (3) check and restrict ~/.dingtalk-cli/config.json file permissions; (4) if you need metadata declared for audits, ask the publisher to list required env vars/config paths and justify them. If you cannot verify the underlying pip package, treat this skill as higher-risk.
功能分析
Type: OpenClaw Skill Name: dingtalk-cli Version: 1.0.0 The skill bundle provides documentation and metadata for a DingTalk CLI tool designed for AI agents to interact with the DingTalk Open Platform. The SKILL.md file contains functional instructions for managing documents, workspaces, and permissions, including standard configuration steps for API credentials (APP_KEY/SECRET). No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; the instructions are clearly aligned with the stated purpose of providing a document management interface.
能力评估
⚠ Purpose & Capability
The SKILL.md clearly intends to drive a local dingtalk-cli binary (read/write docs, workbooks, members). That purpose is coherent with the name/description. However the instructions require DingTalk credentials (app key/secret and operator id) and a config file at ~/.dingtalk-cli/config.json, but the skill metadata declares no required environment variables or config paths — an inconsistency between what the skill needs at runtime and what is advertised.
⚠ Instruction Scope
Runtime instructions tell the agent to run local CLI commands that will read/write documents and to save credentials via `dingtalk-cli auth setup` which writes to ~/.dingtalk-cli/config.json (or use env vars). The actions are within the described purpose, but they include storing and reading sensitive credentials from the user's home directory and rely on a separately-installed binary; the SKILL.md does not describe how long-lived tokens are handled or file permissions, which is relevant for security.
ℹ Install Mechanism
There is no formal install spec in the registry (skill is instruction-only). SKILL.md recommends `pip install dingtalk-cli`. Installing a third-party pip package is a moderate-risk action (it fetches and executes remote code). The skill metadata does not provide a vetted source/URL or checksum; users should verify the PyPI package and its source before installing.
⚠ Credentials
The instructions reference sensitive environment variables (DINGTALK_APP_KEY, DINGTALK_APP_SECRET, DINGTALK_OPERATOR_ID) and require a real operator identity for write operations. Those variables are appropriate for the stated purpose, but the skill metadata lists no required env vars or primary credential; this omission reduces transparency about what secrets are needed and should raise caution.
ℹ Persistence & Privilege
The CLI stores configuration under ~/.dingtalk-cli/config.json (persistence limited to the user's home). always is false and the skill does not request system-wide privileges. Still, storing credentials locally creates a persistent credential surface the agent or CLI can later use; users should be aware of where credentials are written and protect that file (permissions, scope-limited credentials).
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install dingtalk-cli
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /dingtalk-cli 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial public release of the dingtalk-cli agent skill.
元数据
Slug dingtalk-cli
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

dingtalk-cli 是什么？

当用户提到钉钉知识库、钉钉文档、读取/写入文档、知识库目录、文档成员、`.axls` 表格、workbook、dingtalk doc、wiki workspace 时使用。通过本地 `dingtalk-cli` 命令调用钉钉开放平台 API，适合 agent 直接执行。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 261 次。

如何安装 dingtalk-cli？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install dingtalk-cli」即可一键安装，无需额外配置。

dingtalk-cli 是免费的吗？

是的，dingtalk-cli 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

dingtalk-cli 支持哪些平台？

dingtalk-cli 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 dingtalk-cli？

由 MianPeng Zheng（@ianen）开发并维护，当前版本 v1.0.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论