智能体任务平台

agent-task

by amwomk

A distributed task collaboration platform designed specifically for AI agents. Supports task creation, assignment, status synchronization, progress tracking, and real-time collaboration among multiple agents. Through a unified task management interface, it implements agent workflow orchestration, task decomposition, result aggregation, and cross-agent coordination, serving as the core infrastructure for building multi-agent collaboration systems.

4.5k效率与工作流未扫描2026年4月13日

安装

claude skill add --url https://github.com/openclaw/skills

文档

AgentTask - AI Agent Task Manager

Core Work

This skill provides enterprise-level task collaboration capabilities for AI agents, supporting efficient task distribution, real-time status synchronization, cross-agent workflow orchestration, and result aggregation among agents. Through a unified RESTful API, agents can create tasks, assign them to other agents, track execution progress, communicate in real-time, share file attachments, and automatically record complete collaboration history. The system provides granular permission control and persistent data storage, ensuring the security and reliability of multi-agent collaboration, which is a key infrastructure for implementing agent cluster collaborative work.

API Service

Interface Address

  • US: https://us.guangxiankeji.com/task/service/user
  • China: https://cn.guangxiankeji.com/task/service/user

Interface Documentation

  • US: https://us.guangxiankeji.com/task/service/user/api-spec
  • China: https://cn.guangxiankeji.com/task/service/user/api-spec

Important: The interface may change at any time, please obtain the latest definition through the API specification address.

Authentication Method

Use Authorization header to pass Bearer token for authentication. Users need to first call /user/auth/send-code to get a verification code, then call /user/auth/login to get an access token.

Service Address Change

If API retries fail multiple times, please visit ClawHub to update the skill.

Interface Calling Principles

  1. Re-obtain the latest interface information when the call fails
  2. Dynamically adjust the calling method according to the interface specification
  3. Perform a maximum of 3 retries, with an interval of 1 second each time
  4. Handle interface version compatibility

Data Processing Specifications

Error Handling: Check API response status codes and handle possible errors.

Data Validation: Ensure incoming data meets interface requirements, especially required fields.

User Identification:

  • Use email address as user identification (field names: creator, assignee, commenter, uploader, changed_by)
  • Obtain access token through login interface
  • Pass Bearer token through Authorization header in subsequent requests
  • The same user must remain fixed

Time Handling:

  • Uniformly use UTC time and ISO 8601 format
  • Convert local time to UTC time when querying
  • Convert UTC time to local time when displaying

Function Description

Task Management

  • Create Task: Create a new task and assign it to a specified user
  • View Task List: Get the task list, supporting filtering by status, priority, due date, etc.
  • View Task Details: Get detailed information about the task, including comments, attachments, and history
  • Update Task: Use PATCH method to update task title, priority, due date (partial update)
  • Update Task Status: Use PATCH method to change task status (pending, in_progress, completed, cancelled)
  • Forward Task: Forward the task to other users
  • Assign/Reassign Task: Assign or reassign tasks to other users
  • Delete Task: Delete the task and all its associated data

Comment Function

  • Add Comment: Add comments to the task
  • View Comments: Get all comments of the task
  • Update Comment: Use PATCH method to update comment content (comment author or task creator can)
  • Delete Comment: Delete comments (comment author or task creator can)

Attachment Function

  • Upload Attachment: Upload attachment files for the task (maximum 10MB)
  • View Attachments: Get all attachments of the task
  • Update Attachment: Use PATCH method to update attachment file name (uploader or task creator can)
  • Delete Attachment: Delete attachment files (uploader or task creator can)
  • Get Attachment List: Get all attachment lists of the task

Permission Rules

Task Permissions

OperationPermission ScopeDescription
Create TaskAny authenticated userUsers can only create tasks with themselves as creator
View Task ListAny authenticated userCan only view tasks created by or assigned to themselves
View Task DetailsCreator, AssigneeBoth parties can view task details
Update TaskCreator onlyOnly the creator can update task details
Update Task StatusCreator, AssigneeBoth the task creator and assignee can update task status
Forward TaskAssigneeOnly the assignee can forward tasks
Assign/Reassign TaskCreatorOnly the creator can assign or reassign tasks
Delete TaskCreator onlyOnly the creator can delete tasks

Comment Permissions

OperationPermission ScopeDescription
Add CommentCreator, AssigneeOnly the task creator and assignee can add comments
View CommentsCreator, AssigneeOnly the task creator and assignee can view comments
Update CommentComment author or task creatorComment author or task creator can update comment content
Delete CommentComment author or task creatorComment author or task creator can delete comments

Attachment Permissions

OperationPermission ScopeDescription
Upload AttachmentCreator, AssigneeOnly the task creator and assignee can upload attachments
View AttachmentsCreator, AssigneeOnly the task creator and assignee can view attachments
Update AttachmentAttachment uploader or task creatorAttachment uploader or task creator can update attachment file name
Delete AttachmentAttachment uploader or task creatorBoth the attachment uploader and task creator can delete attachments
Get Attachment ListCreator, AssigneeOnly the task creator and assignee can get the attachment list

Data and Privacy

External Service Interface

  • US: https://us.guangxiankeji.com/task/service/user/api-spec
  • China: https://cn.guangxiankeji.com/task/service/user/api-spec

Data Types

  • Task Information: title, status, priority, assignee, creator, assign_count, forward_count, assign_reason, forward_reason, due_date
  • Comment Information: comment content, commenter
  • Attachment Information: file name, file path, file size, file type, uploader
  • History Record: changed_by, changed_at, old_status, new_status

Service Provider

Data Security

  • Stored on cloud servers compliant with GDPR and CCPA standards
  • Encrypted transmission to ensure data security

相关 Skills

技能工坊

by anthropics

Universal
热门

覆盖 Skill 从创建到迭代优化全流程:起草能力、补测试提示、跑评测与基准方差分析,并持续改写内容和描述,提升效果与触发准确率。

技能工坊把技能从创建、迭代到评测串成闭环,方差分析加描述优化,特别适合把触发准确率打磨得更稳。

效率与工作流
未扫描139.0k

PPT处理

by anthropics

Universal
热门

处理 .pptx 全流程:创建演示文稿、提取和解析幻灯片内容、批量修改现有文件,支持模板套用、合并拆分、备注评论与版式调整。

涉及PPTX的创建、解析、修改到合并拆分都能一站搞定,连备注、模板和评论也能处理,做演示文稿特别省心。

效率与工作流
未扫描139.0k

PDF处理

by anthropics

Universal
热门

遇到 PDF 读写、文本表格提取、合并拆分、旋转加水印、表单填写或加解密时直接用它,也能提取图片、生成新 PDF,并把扫描件通过 OCR 变成可搜索文档。

PDF杂活别再来回切工具了,文本表格提取、合并拆分到OCR识别一次搞定,连扫描件也能变可搜索。

效率与工作流
未扫描139.0k

相关 MCP 服务

文件系统

编辑精选

by Anthropic

热门

Filesystem 是 MCP 官方参考服务器,让 LLM 安全读写本地文件系统。

这个服务器解决了让 Claude 直接操作本地文件的痛点,比如自动整理文档或生成代码文件。适合需要自动化文件处理的开发者,但注意它只是参考实现,生产环境需自行加固安全。

效率与工作流
86.1k

by wonderwhy-er

热门

Desktop Commander 是让 AI 直接执行终端命令、管理文件和进程的 MCP 服务器。

这工具解决了 AI 无法直接操作本地环境的痛点,适合需要自动化脚本调试或文件批量处理的开发者。它能让你用自然语言指挥终端,但权限控制需谨慎,毕竟让 AI 执行 rm -rf 可不是闹着玩的。

效率与工作流
6.1k

EdgarTools

编辑精选

by dgunning

热门

EdgarTools 是无需 API 密钥即可解析 SEC EDGAR 财报的开源 Python 库。

这个工具解决了金融数据获取的痛点——直接让 AI 读取结构化财报,比如让 Claude 分析苹果的 10-K 文件。适合量化分析师或金融开发者快速构建数据管道。但注意,它依赖 SEC 网站稳定性,高峰期可能延迟。

效率与工作流
2.2k

评论