← 返回 Skills 市场
Todokan
作者
Banana-Tea-Labs
· GitHub ↗
· v1.3.2
466
总下载
0
收藏
0
当前安装
6
版本数
在 OpenClaw 中安装
/install todokan
功能描述
Manage tasks, boards, thoughts, and reviews in Todokan via MCP
安全使用建议
This skill appears coherent, but review these practical points before installing: 1) Only provide the minimum-scoped API key you need — use a worker (read/comment) key if you don't require create/update/delete. 2) Double-check TODOKAN_MCP_URL to ensure you point to the intended environment (production vs staging). 3) The skill can delete and modify data; the SKILL.md requires confirmation, but you should still be cautious and avoid granting broad keys to automated agents unless you trust the skill. 4) Rotate keys periodically and treat the API key like any secret (don't paste it into chat windows). 5) If you want extra safety, test the skill against a staging key/endpoint first.
功能分析
Type: OpenClaw Skill
Name: todokan
Version: 1.3.2
The OpenClaw Todokan skill bundle is classified as benign. The `SKILL.md` file, which dictates agent behavior, includes robust guardrails such as explicit confirmation for destructive actions (e.g., `delete_task`), warnings against storing sensitive data, and clear scope awareness for different API endpoints. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts designed to bypass user intent or security. The required environment variables (`TODOKAN_API_KEY`, `TODOKAN_MCP_URL`) are standard for API integrations, and the listed external endpoints (`https://todokan.com/mcp`, `https://staging--todokan.netlify.app/mcp`) appear legitimate for the stated purpose.
能力评估
Purpose & Capability
Name/description (manage Todokan via MCP) match the declared env vars (TODOKAN_API_KEY, TODOKAN_MCP_URL) and the SKILL.md focuses on MCP tool calls (list/create/update/delete tasks, boards, documents). Nothing requested appears unrelated to the stated functionality.
Instruction Scope
SKILL.md is an instruction-only runtime spec that confines actions to MCP endpoints and agent-facing operations (list, search, get_events_since, create/update/delete tasks/documents). It does not instruct reading arbitrary host files, unrelated environment variables, or exfiltration to unknown endpoints. Guardrails (confirm before delete, avoid storing secrets) are explicitly present.
Install Mechanism
No install spec or code files are present; this is instruction-only, so nothing will be downloaded or written to disk by an installer. Low installation risk.
Credentials
Only two env vars are required (API key and MCP URL), which are appropriate and expected for a remote API integration. The SKILL.md references passing the API key via Authorization header — consistent with declared env vars. No unrelated credentials or secret-sounding variables are requested.
Persistence & Privilege
The skill can perform full CRUD when pointed at the planner endpoint; however 'always' is false and the SKILL.md requires explicit confirmation for destructive actions. Consider principle of least privilege: if you only need read/comment behavior, use the worker endpoint / a read-only key rather than a planner key.
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 todokan - 安装完成后，直接呼叫该 Skill 的名称或使用
/todokan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
v1.3.2
bump version after duplicate 1.3.1
v1.3.1
sync VERSION with SKILL.md and frontmatter cleanup
v1.3.0
Add AI visibility gate enforcement, settings toggle for AI controls, updated docs
v1.2.0
todokan 1.2.0
- Added explicit documentation of required environment variables and their purpose to prerequisites section.
- Clarified the need for MCP server and setup instructions reference.
- Minor formatting and wording updates for clarity in prerequisites.
- No changes to functionality or tool ordering—docs and metadata only.
v1.1.0
Todokan 1.1.0 is a major documentation update, now entirely in English.
- SKILL.md rewritten in English for global usability (was previously German).
- All activation triggers, tool instructions, output examples, guardrails, and data model descriptions are now clear and accessible for non-German speakers.
- No logic or code changes; documentation content only.
- Role of endpoints, safe handling of sensitive data, and confirmation procedures clarified for broader audiences.
v1.0.0
Todokan 1.0.0 — Initial Release
- Introduces kanban-style task and project management via MCP integration.
- Supports managing tasks, boards, habitats (workspaces), documents, and reviews.
- Enforces safe actions with clear confirmation steps before creating, updating, or deleting items.
- Implements guardrails to prevent hallucinated data, protect sensitive information, and ensure correct tool usage.
- Provides structured output formats for briefings, task drafts, and document drafts.
- Requires TODOKAN_API_KEY and TODOKAN_MCP_URL environment variables for operation.
元数据
常见问题
Todokan 是什么？
Manage tasks, boards, thoughts, and reviews in Todokan via MCP. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 466 次。
如何安装 Todokan？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install todokan」即可一键安装，无需额外配置。
Todokan 是免费的吗？
是的，Todokan 完全免费（开源免费），可自由下载、安装和使用。
Todokan 支持哪些平台？
Todokan 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 Todokan？
由 Banana-Tea-Labs（@banatealab）开发并维护，当前版本 v1.3.2。
推荐 Skills