Token导航 LogoToken导航

Agent Skill · 研究检索

adhd-task-management-skill(多动症任务管理技能)

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。

adhd-task-management-skill 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 43,584。

总安装 974周安装 41GitHub Stars 5下载 341核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

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。

来源仓库内路径:skills/adhd-task-management-skill

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/breverdbidder/life-os --skill adhd-task-manage…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

adhd-task-management-skill 怎么安装?

在终端执行 npx skills add https://github.com/breverdbidder/life-os --skill adhd-task-management-skill。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

adhd-task-management-skill 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

adhd-task-management-skill 需要什么权限?

权限级别是只读。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。

adhd-task-management-skill 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

adhd-task-management-skill 用的人多吗?

公开数据是累计安装 974 次,近一周安装 41 次,下载 341 次,GitHub 5 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

adhd-task-management-skill 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
adhd-task-management-skill

多动症任务管理技能 · 本页

9745只读未明确有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

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

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills