Best use case
task-patrol-skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
巡查 Skill — 通过 CLI 工具巡查任务状态、标记异常、发送告警
Teams using task-patrol-skill should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/task-patrol-skill/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How task-patrol-skill Compares
| Feature / Agent | task-patrol-skill | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
巡查 Skill — 通过 CLI 工具巡查任务状态、标记异常、发送告警
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# Task Patrol Skill 你可以使用 `task-cli.py` 工具来巡查任务状态。该工具位于本 Skill 目录下。 ## 认证信息 - API_KEY: `<注册后填入>` ## 工作流程 1. 获取规则 → 2. 检查积分 → 3. 扫描异常任务 → 4. 标记 blocked → 5. 发送告警 → 6. 记录日志 ## 可用命令 > 所有命令前缀:`python task-cli.py --key <API_KEY>` ### 规则 ```bash rules # 获取合并后的规则提示词(执行前必须调用) ``` ### 任务巡查 ```bash task list # 查看所有任务 st list --status in_progress # 查看执行中的子任务(检查是否超时/卡住) st list --status assigned # 查看已分配但未开始的(检查是否长期未启动) st list --status blocked # 查看已标记异常的 st get <sub_task_id> # 查看子任务详情 ``` > 📄 列表命令默认返回全部数据。如数据较多,可加 `--page N --page-size M` 分页查看。返回结果包含 `total`(总数)和 `has_more`(是否还有更多)。 ### 异常标记 ```bash st block <sub_task_id> # 标记子任务异常(in_progress/assigned/rework → blocked) ``` ### Agent 查看 ```bash agents # 查看已注册 Agent(ID、角色、状态、积分) agents --role executor # 按角色过滤 ``` > 💡 巡查时可通过 `agents` 了解各 Agent 状态,便于在告警中标注相关责任人。 ### 积分 ```bash score me # 查看自己的积分 score logs --page 1 --page-size 10 # 查看积分明细(建议分页,避免数据过多) score agent-logs <agent_id> --page 1 --page-size 10 # 查看指定 Agent 的积分明细(排查连续扣分趋势) score leaderboard # 积分排行榜 ``` > 📄 `score logs` 默认返回全部明细。如数据较多,可加 `--page N --page-size M` 分页查看。 ### 通知 ```bash notification # 查看通知渠道配置 ``` ### 日志 ```bash log create "patrol" "巡查发现xxx子任务超时,已标记blocked" --sub-task-id <id> log mine # 回顾工作记录(默认最近7天,最多20条) log mine --action reflection # 只看自省笔记 log list --sub-task-id <id> # 查看某子任务的所有日志 log list --action blocked --days 3 # 扫描执行者求助日志 log list --days 30 --limit 50 # 最近30天,最多50条 ``` ## 注意事项 - 每次执行前先运行 `rules` 获取最新规则 - 每次唤醒时检查 `score logs`,分析自己的表现 - 重点巡查:超时未完成、长期未启动、会话断开的子任务 - 标记 blocked 后需发送告警到通知渠道 - 不要直接修改子任务的内容或状态(除 block 外),交给规划师处理
Related Skills
task-reviewer-skill
审查者 Skill — 通过 CLI 工具审查子任务、评分、驳回返工
task-planner-skill
任务规划师 Skill — 通过 CLI 工具创建任务、拆分模块、分配子任务
task-executor-skill
任务执行者 Skill — 通过 CLI 工具领取子任务、提交成果、处理返工
wordpress-skill
WordPress 站点管理 Skill — 通过 CLI 工具管理文章、页面、媒体、分类、标签和搜索
local-web-search
Use when the user asks for web search that should run via the local-160 Responses API with web_search tool (base URL like https://proxy.example.com, model gpt-5.2-codex(xhigh)). Includes script to query the local endpoint and return summary + citations; use for periodic news monitoring and on-demand searches.
antigravity-gemini-image
Generate or edit images using the Antigravity-hosted Gemini image model via the local gateway. Use when the user asks to create an image, generate an avatar, or edit/transform an existing image with text instructions. Supports text-to-image and image-to-image editing.
azure-resource-manager-durabletask-dotnet
Azure Resource Manager SDK for Durable Task Scheduler in .NET.
task-decomposer
Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.
task-intelligence
Protocolo de Inteligência Pré-Tarefa — ativa TODOS os agentes relevantes do ecossistema ANTES de executar qualquer tarefa solicitada pelo usuário.
task-management
Simple task management using a shared TASKS.md file. Reference this when the user asks about their tasks, wants to add/complete tasks, or needs help tracking commitments.
webiny-api-tasks-catalog
api/tasks — 2 abstractions.
gh-agent-task
GitHub CLI Agent Task Extension