Deep Work Orchestrator

Integrates personal productivity data with deep work principles to create tailored focus schedules, optimize energy-task matching, and reduce distractions.

Security Scan

This is an instruction-only productivity assistant that stays consistent with its stated purpose and requests no credentials, installs, or file access.

Purpose & Capability

Name/description match the instructions: the skill describes building personalized deep-work schedules and the SKILL.md contains steps to ask about the user's day, design templates, and track weekly hours. It does not request unrelated resources (no cloud creds, no system binaries).

Instruction Scope

Runtime instructions are limited to asking the user about their routine, analyzing attention patterns, and producing schedules and environment-trigger recommendations. The SKILL.md does not instruct the agent to read system files, environment variables, calendars, or to transmit data externally.

Install Mechanism

No install spec and no code files — nothing is written to disk or fetched at install time. This minimizes installation risk.

Credentials

The skill declares no required environment variables, credentials, or config paths. The kinds of personal data it will ask for (daily schedule, energy curve, distraction patterns) are proportionate to its stated purpose but are user-supplied rather than pulled from the system.

Persistence & Privilege

always is false and the skill does not request persistent system presence or try to modify other skills/settings. Autonomous invocation is allowed by platform default but is not excessive here.

Assessment

This skill is instruction-only and appears internally consistent: it won't install code or request credentials. Before using it, consider what personal data you share — the agent will ask for your typical workday, energy curve, and distraction patterns, which may include sensitive health or schedule details. If you want automatic integration with calendars, task managers, or notifications, expect that to require explicit connectors and credentials (none are requested here). If you prefer the agent not to act autonomously on your calendar or devices, avoid granting external integrations and be cautious about enabling any automation that would access those systems.

深度工作编排器 — 将 Cal Newport 的深度工作理论与个人生产力数据结合，构建个性化的专注力管理系统。

Description

整合时间管理、注意力科学、环境设计和认知负荷理论，为知识工作者生成个性化的深度工作计划。通过分析个人工作模式、精力曲线和干扰模式，自动编排最优深度工作时段。

Usage

当用户需要：

• 规划深度工作时间块
• 分析自己的注意力模式
• 减少浅层工作占比
• 建立深度工作习惯
• 优化创作/编码时段

使用本 Skill。

Key Concepts

1. 注意力经济学框架

• 注意力预算模型：每天高质量注意力约4-5小时，需要像预算一样分配
• 注意力税：每次上下文切换消耗23分钟恢复时间（Gloria Mark研究）
• 复利专注：连续深度工作的认知收益呈非线性增长，前30分钟热身，30-90分钟为峰值区

2. 环境触发设计

• 感官锚定：固定音乐/光线/位置 → 触发"深度模式"的巴甫洛夫响应
• 数字护城河：三层防御（通知静默→应用屏蔽→网络隔离），每层对应不同深度级别
• 社交契约信号：耳机戴法/状态标记/物理信号让他人自动回避

3. 精力-任务匹配矩阵

        高精力    低精力
重要    深度区    防御区
不重要  流速区    丢弃区

• 深度区：创作、编码、写作、战略思考
• 流速区：学习新技能、探索性工作
• 防御区：关键决策（低精力时易出错，需额外检查）
• 丢弃区：委托、延迟或删除

Instructions

1. 询问用户典型工作日结构和精力曲线
2. 识别当前浅层工作占比（目标 <30%）
3. 设计3种深度工作模板（晨间型/午间型/晚间型）
4. 创建环境触发方案
5. 建立每周深度工作时数追踪

Examples

输入: "我是程序员，每天被会议打断很多" 输出: 会议批处理策略 + 编码深度块 + 异步沟通协议 + 精力低谷会议安排

Boundaries

• 不替代专业心理咨询（ADHD等注意力障碍需医学支持）
• 框架灵活适配，不教条执行
• 尊重用户现有工作约束

References

• Cal Newport《Deep Work》
• Gloria Mark 注意力切换研究（UC Irvine）
• Mihaly Csikszentmihalyi 心流理论