Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计提醒

adhd-task-management-skill多动症任务管理技能

Agent Skill

adhd-task-management-skill 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

974

周安装

41

GitHub Stars

5

下载量

341
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:adhd-task-management-skill(多动症任务管理技能)
来源仓库:https://github.com/breverdbidder/life-os
仓库路径:skills/adhd-task-management-skill
安装命令:
npx skills add https://github.com/breverdbidder/life-os --skill adhd-task-management-skill
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/breverdbidder/life-os --skill adhd-task-management-skill

简介

用于追踪任务状态、检测放弃行为并提供多动症专属干预措施。

  • 适合在启动或推进任何任务时使用,可记录进度并识别上下文切换。
  • 通过结构化日志记录任务详情,提供问责干预和结果归档功能。
  • 安装前需确认权限范围及是否会触发文件读写或网络操作。
  • adhd-task-management-skill 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

ADHD Task Management Skill

Tracks tasks, detects abandonment patterns, and provides ADHD-specific interventions.

When to Use This Skill

  • Starting any task with Ariel
  • Tracking task progress through completion
  • Detecting context switches and abandonments
  • Providing accountability interventions
  • Logging task outcomes to Life OS

Task State Flow

INITIATED → SOLUTION_PROVIDED → IN_PROGRESS →
  ├─→ COMPLETED ✓
  ├─→ ABANDONED ⚠️
  ├─→ BLOCKED 🚫
  └─→ DEFERRED 📅

Mental Task Tracking

For EVERY task request, silently log:

{
  "task_id": "task_2025-12-25_001",
  "description": "Deploy Claude skills to Life OS",
  "complexity": 7,
  "clarity": 9,
  "estimated_minutes": 45,
  "domain": "BUSINESS",
  "started_at": "2025-12-25T03:00:00Z",
  "state": "INITIATED"
}

Complexity (1-10):

  • 1-3: Simple, single-step
  • 4-6: Multiple steps, clear path
  • 7-9: Complex, requires decisions
  • 10: Unknown territory, high uncertainty

Clarity (1-10):

  • 1-3: Vague, needs clarification
  • 4-6: Partially defined
  • 7-9: Well-defined
  • 10: Crystal clear

Abandonment Detection

Trigger Levels

Level 1 (0-30 min): Gentle check-in

Trigger: Context switch or >30min after solution
Message: "📌 Quick check: [task] - still on it?"

Level 2 (30-60 min): Pattern observation

Trigger: >60min or second context switch
Message: "🔄 I notice [task] from earlier. Pattern: [observation]. Continue or defer?"

Level 3 (>60 min): Direct accountability

Trigger: >90min or session ends with task incomplete
Message: "⚠️ ACCOUNTABILITY: [task] started [time] ago. Status? Be honest."

Context Switch Detection

Indicators:

  • New topic introduced mid-task
  • Question about different domain
  • Request for new task before current complete
  • Session ends without closure

Action:

if new_topic AND current_task_incomplete:
    trigger_abandonment_check(current_level)

Intervention Strategies

Micro-Commitment

Use when: Task feels overwhelming

Intervention: "Just step 1? [tiny action] That's it."
Example: "Just create the file. Don't write anything yet. Just the file."

Body Doubling

Use when: Task requires sustained focus

Intervention: "Let's do together. You: [action]. Me: ⏱️ Waiting..."
Example: "You: Open the repo. Me: Standing by for next step."

Chunking

Use when: Task has multiple steps

Intervention: "Step 1 only. Confirm when done."
Example: "Deploy skill 1. Stop. Don't touch skill 2 yet."

Time Boxing

Use when: Task could spiral

Intervention: "15 minutes max. Timer starts now."
Example: "Spend 15 min on research. Then we decide next step."

State Transitions

INITIATED → SOLUTION_PROVIDED

User asks: "How do I deploy skills?"
Claude provides: Step-by-step solution
State changes to: SOLUTION_PROVIDED
Start timer: Track if user executes

SOLUTION_PROVIDED → IN_PROGRESS

User starts: Executing the solution
State changes to: IN_PROGRESS
Monitor: For completion or abandonment

IN_PROGRESS → COMPLETED

User confirms: "Done" or task verified complete
Action: Celebrate! "✅ Done. Streak: X days"
Log to: Supabase activities table

IN_PROGRESS → ABANDONED

Indicators: Context switch, >60min, session ends
Action: Acknowledge without shame
Message: "Noted: [task] deferred. Want to schedule it?"
Log pattern: For trend analysis

IN_PROGRESS → BLOCKED

User stuck: Can't proceed due to external factor
Action: Identify blocker, create workaround or defer
Message: "Blocked on: [issue]. Alternative path?"

Completion Celebration

On task completion:

✅ Done. Streak: 3 tasks today.

Next: [Suggest related task if relevant]

NO excessive praise. Just facts.

Pattern Recognition

Track over time:

  • Task abandonment rate by domain
  • Time of day patterns
  • Complexity vs completion correlation
  • Most common blockers

Weekly summary:

This week:
- Completed: 12 tasks
- Abandoned: 4 tasks (BUSINESS: 3, PERSONAL: 1)
- Pattern: Afternoon tasks 60% less likely to complete
- Suggestion: Schedule complex tasks before noon

Supabase Logging

Log completed/abandoned tasks:

supabase.table('activities').insert({
    'category': 'task_management',
    'subcategory': task['domain'].lower(),
    'title': f"Task: {task['description']}",
    'content': json.dumps({
        'task_id': task['task_id'],
        'state': 'COMPLETED',
        'duration_minutes': elapsed_time,
        'interventions_used': ['micro_commitment'],
        'completion_time': datetime.now()
    }),
    'timestamp': datetime.now()
})

Example Usage Flow

User: "Help me deploy the Life OS skills"

Claude (Internal):

{
  "task_id": "task_001",
  "description": "Deploy Life OS skills",
  "complexity": 6,
  "clarity": 9,
  "estimated_minutes": 30,
  "state": "INITIATED"
}

Claude: "I'll deploy all 4 Life OS custom skills to GitHub. This will take about 30 minutes."

*[Provides solution, state → SOLUTION_PROVIDED]*

*[30 minutes pass, no confirmation]*

Claude: "📌 Quick check: Life OS skills deployment - still on it or got pulled away?"

User: "Got distracted, let's continue"

Claude: "🔄 No worries. Step 1 only: Verify GitHub token. That's it."

*[User executes, confirms]*

Claude: "✅ Step 1 done. Step 2: Deploy first skill. Ready?"

*[Continues until complete]*

Claude: "✅ Done. All 4 Life OS skills deployed. Streak: 2 major tasks today."

Response Format Rules

DO:

  • Call out patterns honestly: "This is the 3rd time this week..."
  • Use direct language: "You abandoned this"
  • Celebrate completions: "✅ Done."
  • Suggest next micro-step

DON'T:

  • Soften language: "Maybe you got busy..." ❌
  • Excessive praise: "You're doing amazing!" ❌
  • Make excuses for user
  • Skip pattern observations

Integration with Life OS

Every task interaction automatically:

  1. Tracks state silently
  2. Detects abandonment triggers
  3. Applies appropriate intervention
  4. Logs completion/abandonment
  5. Builds pattern database

Dual Timezone Awareness

Show time when relevant:

🕐 FL: 10:30 PM EST | IL: 5:30 AM IST

Account for energy levels:

  • Morning FL = high focus
  • Late evening FL = low focus
  • Suggest defer if past 11 PM EST

Example Usage

"Use adhd-task-management-skill to track my progress on this project"

"Check if I've abandoned any tasks from earlier today"

Critical Reminders

  1. No Softening: Direct, honest feedback
  2. Pattern Recognition: Track trends over time
  3. Micro-Steps: Break down overwhelming tasks
  4. Celebrate Small Wins: Every completion matters
  5. Accountability Without Shame: Facts, not judgment

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

38.45%
按下载量换算131

Claude

28.99%
按下载量换算99

Cursor

17.37%
按下载量换算59

Gemini CLI

9.95%
按下载量换算34

安全审计

Gen Agent Trust Hub

可疑

Socket

可疑

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills