360 Secure SkillHub
360 安全技能中心

Flow State Monitoring

该 Skill 在本地传感器遥测显示深度专注时触发工作流:先调用 llm_classify_intent 子代理对活动分类并校验结果,若判定为 Deep Work,则执行 gog calendar create primary 命令在 Google 日历创建“Busy - In Flow”事件以屏蔽打扰;失败时等待 3 秒重试最多 3 次,否则报错停止,最终返回 JSON 确认。

zvirb
zvirb
热度 49.70
最近更新 2026-05-11 17:45:54
分类:自动化依赖:内部调用大模型 / 第三方 API应用场景:工作流 / 自动化脚本 / 日程安排 / 任务管理

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add flow-state-monitoring
Metadata
name
flow-state-monitoring
description
Workflow-driven skill that infers deep focus and autonomously mutes interruptions.
os
all
requires
{"bins":["gog"]}

Lean Philosophy (Principles)

  • Kaizen (改善): This skill is an atomic node, broken down into its simplest, smallest component to eliminate waste and ensure perfection.
  • Standardized Work (Hyojun Sagyo): This node represents the most efficient, standardized path for this specific task before automation.
  • Jidoka (自働化): This node includes autonomous defect detection. It will stop immediately and report if it cannot achieve the expected outcome.

Flow State Monitoring

This skill orchestrates a workflow to analyze focus telemetry and autonomously update your status in Google Workspace to protect your flow state.

Cognitive Directives

WHEN [telemetry from local sensors indicates deep focus] THEN [ Execute the following Jidoka-validated loop:

  1. Execute llm_classify_intent (Sub-Agent) to classify the activity.
    • Verification Step (Jidoka): Verify the sub-agent returns a valid classification (e.g., "Deep Work"). IF it hallucinates text, retry classification.
  2. IF classified as "Deep Work", Execute the native terminal command gog calendar create primary --summary "Busy - In Flow" to block interruptions.
    • Verification Step (Jidoka): Check if the calendar event creation returns a successful JSON response. IF it fails, wait 3 seconds and retry (max 3 times). IF it still fails, report the error and STOP. ]

Expected Output

A JSON confirmation of the calendar status update.