菜单
Agent 后台监控协议技能：用于长时间任务的后台启动、wait 轮询、进度文件监控、日志监控、卡死判定、自动续跑、失败重试、最终收口和无人值守实验托管。Use when: 后台监控、agent wait、长任务、无人值守、watchdog、自动续跑、卡死恢复、进度轮询、MATLAB长任务、Python长任务、PowerShell后台任务、manifest、checkpoint、结果文件监控。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
Tests in real browsers. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data via Chrome DevTools MCP.
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.
| name | agent-wait-monitor-zh |
| description | Agent 后台监控协议技能：用于长时间任务的后台启动、wait 轮询、进度文件监控、日志监控、卡死判定、自动续跑、失败重试、最终收口和无人值守实验托管。Use when: 后台监控、agent wait、长任务、无人值守、watchdog、自动续跑、卡死恢复、进度轮询、MATLAB长任务、Python长任务、PowerShell后台任务、manifest、checkpoint、结果文件监控。 |
只要本工作流将初始化或重组项目，或新建、移动应用、服务、包、模块、页面、API、研究步骤、实验、流水线、测试、文档或多文件产物树，必须先使用 project-structure-architect。
AGENTS.md、PROJECT_STRUCTURE.md、.project-structure.yaml 和现有文件树，锁定项目类型、蓝图及唯一合理路径。BLOCK 时停止结构性写入并先修正或询问用户。纯内容编辑且目标路径已由用户或现有规范唯一确定时，可不重复调用。
把长任务从“开着终端盯输出”改成可恢复的后台协议：启动后通过 process + log + result files + manifest 四类信号判断是否健康，并在卡死或失败时按规则续跑。
pending：等待运行。running：当前正在运行。completed：结果文件存在且可读。failed_retryable：失败但可重试。hard_failed：超过重试上限或确定不可恢复。stalled：进程存在但结果/日志长期无变化。waitInterval = 30s，stallMinutes = 10。waitInterval = 60s，stallMinutes = 30。waitInterval = 300s，stallMinutes = 120。maxRetries = 3。实际使用时按任务平均耗时调整，不能把合法慢任务误杀。
每次建立监控协议时，输出：
references/background-monitor-protocol.mdassets/powershell-watchdog-template.ps1assets/manifest-schema-template.md