← Back to Skills Marketplace
Cym Zentao
by
15334615152
· GitHub ↗
· v1.0.2
· MIT-0
134
Downloads
0
Stars
1
Active Installs
3
Versions
Install in OpenClaw
/install cym-zentao
Description
禅道项目管理 CLI 工具 - 支持任务创建、执行查询等功能
README (SKILL.md)
cym-zentao - 禅道项目管理 CLI
命令
login
测试登录:
cym-zentao login
list-executions
列出执行(项目迭代):
cym-zentao list-executions [keyword]
create-task
创建任务:
cym-zentao create-task \x3CexecutionId|executionName> \x3Cname> \x3CassignedTo> [options]
参数说明:
executionId|executionName: 执行ID(数字)或执行名称(支持模糊匹配)name: 任务名称assignedTo: 指派给(用户名)options: JSON 字符串,可选参数
options 格式: JSON 字符串
pri: 优先级 (1-4)estimate: 预计工时type: 任务类型estStarted: 开始日期 (YYYY-MM-DD)deadline: 截止日期 (YYYY-MM-DD)desc: 描述
示例:
# 使用执行ID
cym-zentao create-task 6159 "测试功能" "陈跃美"
# 使用执行名称(支持模糊匹配)
cym-zentao create-task "日常事务-郑太相" "测试功能" "陈跃美"
# 带选项
cym-zentao create-task 6159 "测试功能" "陈跃美" '{"pri":2,"estimate":8,"type":"test"}'
create-tasks-batch
批量创建任务(从 JSON 文件):
cym-zentao create-tasks-batch \x3CexecutionId|executionName> \x3CtasksFile>
tasksFile 格式: JSON 数组,每个元素包含:
name: 任务名称(必填)assignedTo: 指派给(必填)estimate: 预计工时estStarted: 开始日期 (YYYY-MM-DD)deadline: 截止日期 (YYYY-MM-DD)type: 任务类型,默认 "test"pri: 优先级,默认 3desc: 描述
示例文件 tasks.json:
[
{"name": "调研功能", "assignedTo": "1010753", "estimate": 6, "estStarted": "2026-03-25", "deadline": "2026-03-25"},
{"name": "编写代码", "assignedTo": "1010753", "estimate": 6, "estStarted": "2026-03-26", "deadline": "2026-03-26"},
{"name": "测试功能", "assignedTo": "1010753", "estimate": 6, "estStarted": "2026-03-27", "deadline": "2026-03-27"},
{"name": "验收功能", "assignedTo": "004936", "estimate": 1, "estStarted": "2026-03-27", "deadline": "2026-03-27"}
]
使用示例:
cym-zentao create-tasks-batch "日常事务-郑太相" tasks.json
list-tasks
列出任务:
cym-zentao list-tasks \x3CexecutionId|executionName> [status]
示例:
# 使用执行ID
cym-zentao list-tasks 6159
# 使用执行名称
cym-zentao list-tasks "日常事务-郑太相"
# 按状态筛选
cym-zentao list-tasks 6159 "doing"
自然语言创建任务
你也可以用自然语言描述来创建任务,AI 会自动解析:
单任务创建
给陈跃美在日常事务-郑太相下面创建明天的任务,任务名称为"测试功能",任务预计耗时6小时
AI 会解析出:
- 执行名称:日常事务-郑太相
- 任务名称:测试功能
- 指派给:陈跃美
- 开始日期:明天
- 预计工时:6小时
批量任务创建
在禅道"日常事务-郑太相"下面创建任务:
时间2026-3-25,任务调研skills实现,预计耗时6小时,指派给陈跃美
时间2026-3-26,任务编写skills代码,预计耗时6小时,指派给陈跃美
时间2026-3-27,任务测试skills功能,预计耗时6小时,指派给陈跃美
时间2026-3-27,任务验收skills功能,预计耗时1小时,指派给郑太相
AI 会:
- 首先查找执行"日常事务-郑太相"的ID
- 批量创建4个任务,分别设置正确的日期、工时和指派给
- 返回创建结果汇总
Usage Guidance
This skill appears to implement a legitimate ZenTao CLI, but it quietly reads credentials from ~/.openclaw/workspace/TOOLS.md (parsing an "## 禅道 API (ZenTao API)" section for API URL, username, and password) even though the package metadata and SKILL.md don't declare any required credentials or config paths. Before installing: 1) inspect the TOOLS.md at that path (or avoid placing secrets there) and confirm you trust its contents and the configured apiUrl; 2) ask the author to document the credential source or switch to explicit environment variables or a secure config mechanism; 3) consider removing or questioning the always: true flag — don't enable this skill as always-on unless you understand why it must run in every agent session; 4) if you must try it, run it in a limited/sandboxed environment first and verify network endpoints the skill calls are your ZenTao server(s). The behavior is likely explainable (design choice), but the undisclosed credential access and always-on setting make this suspicious and worth extra caution.
Capability Analysis
Type: OpenClaw Skill
Name: cym-zentao
Version: 1.0.2
The skill is a legitimate ZenTao project management tool that allows an AI agent to create and list tasks via the ZenTao API. It retrieves necessary credentials (API URL, username, and password) from the standard OpenClaw configuration file (~/.openclaw/workspace/TOOLS.md) and uses them solely for authenticated requests to the user-specified ZenTao instance. The code in cli.js and index.js follows the stated purpose without any signs of data exfiltration, malicious execution, or harmful prompt injection.
Capability Assessment
Purpose & Capability
The code implements ZenTao API operations (login, list executions, create tasks, etc.) which matches the skill's stated purpose. However the skill does not declare required credentials or config paths even though both index.js and cli.js require a local file (~/.openclaw/workspace/TOOLS.md) containing API address, username, and password. That credential-source design is not documented in SKILL.md or registry metadata, an incoherence a user should be aware of.
Instruction Scope
SKILL.md describes CLI commands and natural-language behaviors but does not disclose that the runtime will read the user's HOME (USERPROFILE/HOME) .openclaw/workspace/TOOLS.md to extract ZenTao API URL, username, and password. The code will fail or throw if that file/section is missing, and the behavior (reading a specific local config file for secrets) is not documented in the instructions.
Install Mechanism
There is no install spec (instruction-only install), so nothing is downloaded at runtime. Code files are bundled with the skill and require node to run; this is expected for a Node.js CLI. No remote installation URLs or archive extraction are present.
Credentials
The registry lists no required environment variables or credentials, but the implementation expects credentials to be stored in a local file under the user's home directory. This mismatch means secrets are accessed indirectly from a specific path instead of via declared env vars, and the skill does not advertise that it needs or will use those credentials. The only env usage is for locating HOME/USERPROFILE; no other unrelated credentials are requested.
Persistence & Privilege
The skill is marked always: true (also in SKILL.md metadata). That means it will be included in every agent run. Combined with the hidden behavior of reading a user-local file for credentials, this raises concern about broad exposure of local credential data to an always-enabled skill. There is no documented justification for always: true in the metadata.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install cym-zentao - After installation, invoke the skill by name or use
/cym-zentao - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
- Added batch task creation command (create-tasks-batch) supporting JSON file input.
- Enhanced task creation commands to accept execution name (supports fuzzy matching) in addition to execution ID.
- Updated documentation with new examples and natural language usage tips.
- Included example-tasks.json file for batch operations.
- Improved overall usability and flexibility of task-related commands.
v1.0.1
- Added CLI entry point (cli.js) for command-line usage.
- Updated documentation to reflect new CLI commands and usage examples.
- Refined package metadata for CLI support.
- No changes to core API functionality.
v1.0.0
Initial release of Zentao skill for project management:
- Supports user login and token acquisition.
- Lists project executions (iterations), with optional keyword search.
- Creates tasks with flexible options (priority, estimate, type, start/end dates, description, assignee).
- Lists tasks within an execution, with status filtering.
- Configuration details provided for connecting to the Zentao API.
Metadata
Frequently Asked Questions
What is Cym Zentao?
禅道项目管理 CLI 工具 - 支持任务创建、执行查询等功能. It is an AI Agent Skill for Claude Code / OpenClaw, with 134 downloads so far.
How do I install Cym Zentao?
Run "/install cym-zentao" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Cym Zentao free?
Yes, Cym Zentao is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Cym Zentao support?
Cym Zentao is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Cym Zentao?
It is built and maintained by 15334615152 (@15334615152); the current version is v1.0.2.
More Skills