← 返回 Skills 市场
xfwgithub

Task Management

作者 xinye · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
160
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install ai-task-management
功能描述
零依赖、高性能的任务管理技能。当用户需要创建、查询、更新、删除任务或获取任务统计时使用此技能。
使用说明 (SKILL.md)

触发条件

当用户提到以下关键词或意图时触发此技能:

创建任务

  • "创建任务"、"新建任务"、"添加一个任务"、"帮我记个事"
  • "我要做一个..."、"记得做..."、"提醒我..."

查询任务

  • "查看任务"、"查询任务"、"我的任务"、"有什么任务"
  • "待处理的任务"、"未完成的任务"

更新任务

  • "更新任务"、"提交初审"、"取消任务"、"修改任务"
  • "完成初核"
  • "标记为已完成"、"删除任务"

任务统计

  • "任务统计"、"任务概况"、"有多少任务"
  • "完成情况如何"

任务详情

  • "任务详情"、"查看某个任务"、"任务信息"

回收任务

  • "回收任务"、"任务到期"、"重置任务状态"

删除任务

  • "彻底删除"、"物理删除"、"删除任务"

更新技能

  • "更新技能"、"升级技能"、"检查更新"

安装

方式一:通过 pip 安装(推荐)

# 从 GitHub 安装最新版本
pip install git+https://github.com/xfwgithub/aitask-skill.git

# 或从本地源码安装
git clone https://github.com/xfwgithub/aitask-skill.git
cd aitask-skill
pip install -e .

方式二:直接下载二进制

# 下载最新版本的完整包(包含 Web UI 静态资源)
wget https://github.com/xfwgithub/aitask-skill/releases/latest/download/task-skill.zip
unzip task-skill.zip
cd task-skill
./task-skill --version

# 或者下载指定版本
# wget https://github.com/xfwgithub/aitask-skill/releases/download/v0.4.3/task-skill-v0.4.3.zip

配置 AI Agent 技能

安装完成后,将 SKILL.md 复制到你的 AI Agent 技能目录:

# 复制 SKILL.md 到技能目录(只复制这个文件!)
cp /path/to/SKILL.md \x3C你的技能目录>/task-management/

# 验证
ls \x3C你的技能目录>/task-management/
# 应该只看到 SKILL.md 文件

重要说明

  • ✅ 技能目录只需要 SKILL.md 文件
  • ✅ 二进制文件和静态资源会自动下载到 Python 包目录
  • 不要把整个 task-skill 包复制到技能目录
  • ℹ️ 技能目录位置取决于你使用的 IDE/Agent 配置

初始化

安装完成后,验证安装:

# 查看版本
task-skill --version

# 查看帮助
task-skill --help

# 启动 Web 服务器(用于人机协作界面)
task-skill --server

工具函数

create-task

创建新任务

参数:

  • --title (string, 必需): 任务标题
  • --project (string, 必需): 项目名称
  • --description (string, 可选): 任务描述
  • --priority (int, 可选): 优先级 1-4(1=Critical/2=High/3=Medium/4=Low),默认 3
  • --assignee (string, 可选): 负责人姓名
  • --parent (string, 可选): 父任务 UUID(创建子任务时使用)

调用示例:

# 创建普通任务
task-skill create-task --title "审查文档" --project "aitask-skill" --priority 2 --description "检查完整性"

# 创建子任务
task-skill create-task --title "子任务-收集资料" --project "demo" --parent abc-123

list-tasks / ls

查询任务列表

参数:

  • --status (string, 可选): 状态筛选(pending/agent_working/agent_review/human_review/done/cancelled)
  • --project (string, 可选): 项目筛选
  • --limit (int, 可选): 返回数量限制

调用示例:

task-skill list-tasks --status pending
task-skill ls --project demo --limit 10

get-task

获取任务详情

参数:

  • uuid (string, 必需): 任务 UUID

调用示例:

task-skill get-task abc-123

claim-task

领取任务(pending → agent_working)

参数:

  • uuid (string, 必需): 任务 UUID

调用示例:

task-skill claim-task abc-123

submit-review

提交初审(agent_working → agent_review)

参数:

  • uuid (string, 必需): 任务 UUID

调用示例:

task-skill submit-review abc-123

review-task

提交人工审核(agent_review → human_review)

参数:

  • uuid (string, 必需): 任务 UUID

调用示例:

task-skill review-task abc-123

approve-task

人工审核通过(human_review → done)

⚠️ 警告: 此命令属于人工审核步骤。除非用户明确指示“审核通过”或“标记为已完成”,否则 AI Agent 绝对不能自动调用此命令!

参数:

  • uuid (string, 必需): 任务 UUID

调用示例:

task-skill approve-task abc-123

cancel-task

取消任务(任意状态 → cancelled)

参数:

  • uuid (string, 必需): 任务 UUID

调用示例:

task-skill cancel-task abc-123

任务状态说明

  • pending - 待办(等待 agent 领取)
  • agent_working - Agent 工作中(agent 已领取,正在处理)
  • agent_review - Agent 审核中(agent 提交初审后,等待 agent 自己审核确认)
  • human_review - 人工审核中(agent 审核通过后,提交给人工审核)
  • done - 完成(人工审核通过。注意:AI Agent 不得擅自将任务变更为此状态,必须由人类明确授权
  • cancelled - 已取消

delete-task

物理删除任务(彻底删除)

注意: 此操作不可恢复,请谨慎使用!建议先使用 cancel-task 将任务状态改为 cancelled(取消),确认不再需要后再使用此功能彻底删除。

参数:

  • uuid (string, 必需): 任务 UUID

调用示例:

task-skill delete-task abc-123

recycle-tasks

回收到期未完成的 Agent 任务

逻辑:

  • 回收 due_date 之前创建的、状态为 agent_working 的任务
  • 回收后任务状态变为 pending(重新进入待办池)

参数:

  • --due-date (string, 可选): 截止时间,回收此日期前创建的超时任务

调用示例:

task-skill recycle-tasks --due-date 2026-03-22

stats

获取仪表盘统计信息

参数: 无

调用示例:

task-skill stats
安全使用建议
Do not install or run this skill until the following are clarified: 1) Confirm the canonical source repository and whether the project is a Go program or a Python package — the SKILL.md pip instructions conflict with the included Go sources and build scripts. 2) Verify where the task-skill binary should live (claude.json expects it in the skill cwd but SKILL.md says only SKILL.md should be copied). 3) Validate prebuilt binaries (if using releases) by checking GitHub release signatures or building locally in an isolated environment; the build.sh/start.sh assume macOS ARM64 but the registry declares no OS restriction. 4) Inspect getDatabasePath (not shown in full) to confirm the DB file location and ensure it won't overwrite sensitive files. 5) Be aware the web UI loads third-party JS (unpkg.com); if you need to avoid remote content, host static assets locally. 6) Run the binary in a sandbox (container/VM) or with restricted network access until you trust the repo. If the developer cannot explain the pip instruction and the 'automatic download' claim, treat the package as untrusted.
功能分析
Type: OpenClaw Skill Name: ai-task-management Version: 1.0.0 The 'ai-task-management' skill bundle is a legitimate task management system featuring a Go-based CLI and a Web UI (using the Echo framework). The code implements standard CRUD operations for tasks stored in a local SQLite database (~/.task-skill/tasks.db) and includes safety instructions in SKILL.md to prevent the AI agent from automatically approving tasks without human consent. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found across the source code (main.go, server.go, db.go) or the documentation.
能力评估
Purpose & Capability
The skill is described as a 'zero-dependency' task manager with simple CLI usage, but the repository contains Go source, build scripts, and a web UI. The SKILL.md recommends installing via pip (a Python installer) or downloading prebuilt binaries from GitHub — pip for a Go program is incoherent. claude.json expects a './task-skill' binary in the skill cwd while SKILL.md instructs users to copy only SKILL.md into their skill directory and claims other artifacts will be 'automatically downloaded' to a Python package directory. These contradictions are disproportionate to a simple task-management description and warrant clarification.
Instruction Scope
Runtime instructions in SKILL.md ask the user/agent to run local binaries (./task-skill --server) and to copy only SKILL.md to the agent's skill folder. There are explicit warnings (e.g., do not let the AI auto-approve human reviews) which are good, but instructions implying automatic download of binaries/resources are vague. The skill's web UI loads external JS (htmx from unpkg.com), adding a remote dependency at runtime not declared in the metadata. The agent instructions give broad discretion about installing/building (pip vs wget vs building Go), which grants the agent ambiguous power to fetch/run code from the network.
Install Mechanism
No formal install spec in the registry but the package includes build.sh and start.sh that invoke 'go build', implying a Go build/install flow. SKILL.md suggests pip install of a GitHub repo (incompatible with included Go sources) or downloading ZIPs from GitHub releases (reasonable if releases actually exist). This mismatch is suspicious — either the pip instructions are incorrect/leftover or the package packaging is inconsistent. The included build script is limited to macOS/ARM64 which conflicts with 'OS restriction: none'.
Credentials
The registry declares no required env vars, but the code reads TASK_SKILL_PORT and will create a local SQLite DB. There are no API keys or other secrets requested. However, SKILL.md and templates load external scripts (unpkg.com/htmx), which introduces a remote dependency (content fetched at runtime) not reflected in requires.env. The codebase otherwise does not appear to request unrelated credentials.
Persistence & Privilege
The skill does not request 'always: true' and does not appear to modify other skills or global agent configuration. It runs as a local CLI/web server and stores data in a local SQLite DB — normal for this kind of tool. Autonomous invocation is enabled (default) but not by itself a red flag here.
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 ai-task-management
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /ai-task-management 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 release of ai-task-management skill: - Provides zero-dependency, high-performance task management for macOS (Apple Silicon). - Supports task creation, querying, updating, deletion, and statistics via command line or integration. - Includes detailed CLI usage instructions for all task lifecycle operations. - Triggers on common Mandarin task management phrases and intent. - Binary and pip install options are both supported, with a simple SKILL.md-based activation. - Clear separation of agent and human review steps, with safeguards on critical actions.
元数据
Slug ai-task-management
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

Task Management 是什么?

零依赖、高性能的任务管理技能。当用户需要创建、查询、更新、删除任务或获取任务统计时使用此技能。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 160 次。

如何安装 Task Management?

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

Task Management 是免费的吗?

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

Task Management 支持哪些平台?

Task Management 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 Task Management?

由 xinye(@xfwgithub)开发并维护,当前版本 v1.0.0。

💬 留言讨论