← 返回 Skills 市场
Teamwork Crm
作者
Vlad Ursul
· GitHub ↗
· v1.0.3
· MIT-0
324
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install teamwork-crm
功能描述
Teamwork CRM integration. Manage Deals, Persons, Organizations, Leads, Projects, Activities and more. Use when the user wants to interact with Teamwork CRM d...
安全使用建议
This skill appears to do what it says: it uses the Membrane CLI to access Teamwork CRM. Before installing or running it: (1) verify the @membranehq/cli npm package is the official package and maintained by the expected vendor; (2) avoid installing global npm packages on sensitive/production hosts—use an isolated environment or container if possible; (3) review how Membrane stores and uses authentication tokens (local files / keychain) so you understand where CRM credentials will reside; (4) confirm the Org policy for granting third-party tooling access to CRM data, since the CLI/session will be able to read and modify CRM records; and (5) if you need higher assurance, inspect the Membrane CLI source at the referenced repository or consult your security team before enabling broad agent-driven access.
功能分析
Type: OpenClaw Skill
Name: teamwork-crm
Version: 1.0.3
The skill bundle provides instructions for an AI agent to integrate with Teamwork CRM via the Membrane CLI. It outlines standard procedures for installation (npm install), authentication (membrane login), and data management (listing and running actions) through the Membrane platform. The instructions (SKILL.md) promote secure practices by advising the agent to use Membrane's centralized credential management rather than handling raw API keys, and no evidence of malicious intent, data exfiltration, or deceptive prompt injection was found.
能力评估
Purpose & Capability
The name/description (Teamwork CRM) matches the instructions: all runtime steps are about installing and using the Membrane CLI to connect to Teamwork CRM and run CRM-related actions. Required capabilities (network access, Membrane account) are appropriate for this purpose.
Instruction Scope
SKILL.md confines runtime behavior to installing/using the Membrane CLI, logging in via Membrane, creating connections, searching and running actions. It does not instruct the agent to read arbitrary local files or access unrelated environment variables. It documents interactive and headless auth flows.
Install Mechanism
No install spec in bundle (instruction-only), but the guide instructs the user to run `npm install -g @membranehq/cli@latest`. Installing a global npm CLI is a reasonable and expected step for a CLI-based integration, but npm packages carry supply-chain risk — the package should be verified (official package, correct maintainer) before global installation, especially on shared or production hosts.
Credentials
The skill declares no required environment variables or credentials. Authentication is delegated to Membrane's CLI flow; no unrelated secrets are requested by the skill instructions.
Persistence & Privilege
Skill is instruction-only and not always-enabled. It does not request persistent agent privileges or modify other skills' configurations. Autonomous invocation is allowed (platform default) but not elevated by this skill.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install teamwork-crm - 安装完成后,直接呼叫该 Skill 的名称或使用
/teamwork-crm触发 - 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
v1.0.3
Auto sync from membranedev/application-skills
v1.0.2
Revert refresh marker
v1.0.1
Refresh update marker
v1.0.0
Auto sync from membranedev/application-skills
元数据
常见问题
Teamwork Crm 是什么?
Teamwork CRM integration. Manage Deals, Persons, Organizations, Leads, Projects, Activities and more. Use when the user wants to interact with Teamwork CRM d... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 324 次。
如何安装 Teamwork Crm?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install teamwork-crm」即可一键安装,无需额外配置。
Teamwork Crm 是免费的吗?
是的,Teamwork Crm 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Teamwork Crm 支持哪些平台?
Teamwork Crm 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 Teamwork Crm?
由 Vlad Ursul(@gora050)开发并维护,当前版本 v1.0.3。
推荐 Skills