Token导航 LogoToken导航

Agent Skill · 研究检索

checklist-discipline(纪律清单)

checklist-discipline 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。

checklist-discipline 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,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 38,503。

总安装 1,551周安装 64GitHub Stars 98下载 507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:checklist-discipline(纪律清单)
来源仓库:https://github.com/erichowens/some_claude_skills
仓库路径:skills/checklist-discipline
安装命令:
npx skills add https://github.com/erichowens/some_claude_skills --skill checklist-discipline
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/erichowens/some_claude_skills --skill checklist-discipline

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。

checklist-discipline 将个体专业知识转化为系统化卓越表现,专门捕获复杂流程中的认知失效,适合在 Codex、Claude、Cursor、Gemini CLI 中协调多学科团队或处理百步以上流程时使用。适用于医疗、航空、金融等领域的高风险操作标准化管理。

核心能力是建立团队间决策整合机制并对抗知识应用惰性。安装命令为 npx skills add https://github.com/erichowens/some_claude_skills --skill checklist-discipline。使用前需明确流程步骤划分与责任边界以避免误用。

来源仓库内路径:skills/checklist-discipline

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/erichowens/some_claude_skills --skill checklis…;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

checklist-discipline 怎么安装?

在终端执行 npx skills add https://github.com/erichowens/some_claude_skills --skill checklist-discipli…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

checklist-discipline 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。

checklist-discipline 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。

checklist-discipline 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。

checklist-discipline 用的人多吗?

公开数据是累计安装 1,551 次,近一周安装 64 次,下载 507 次,GitHub 98 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。

checklist-discipline 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

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。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 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
checklist-discipline

纪律清单 · 本页

1,55198只读未明确通过

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

Checklist Discipline

Transform individual expertise into systematic excellence by catching inevitable cognitive failures and enabling team coordination in extreme complexity.

When to Use

✅ Use for:

  • Complex processes with 100+ steps where memory/attention failures are inevitable
  • High-stakes domains (surgery, aviation, construction, finance) where 1% error rates compound catastrophically
  • Coordinating specialists across disciplines who must integrate decisions
  • Converting strangers into functioning teams under time pressure
  • Combating ineptitude (knowledge exists but isn't applied) vs. ignorance

❌ NOT for:

  • Simple tasks with <10 steps that professionals reliably complete
  • Teaching comprehensive procedures to complete novices (use training instead)
  • Replacing professional judgment or handling true unpredictability
  • Situations requiring detailed instruction manuals
  • Avoiding responsibility through bureaucratic compliance theater

Core Process

Checklist Design Decision Tree

START: Define the complex process
│
├─> Is failure due to IGNORANCE (knowledge doesn't exist)?
│   └─> YES: Checklist cannot help → Research/develop knowledge first
│   └─> NO: Failure is INEPTITUDE (knowledge exists but misapplied) → CONTINUE
│
├─> Identify PAUSE POINTS (when to check)
│   ├─> Before critical commitment? (before anesthesia, takeoff, concrete pour)
│   ├─> Before point of no return? (before incision, before leaving OR)
│   ├─> After high-risk phase? (after landing, after patient leaves OR)
│   └─> Define 1-3 precise moments per process
│
├─> Choose FORMAT per pause point
│   ├─> Are users EXPERTS performing ROUTINE tasks?
│   │   └─> YES: DO-CONFIRM (perform from memory, then pause and verify)
│   └─> Are users NOVICES or tasks UNFAMILIAR?
│       └─> YES: READ-DO (execute each step as read, like recipe)
│
├─> Identify KILLER ITEMS (5-9 per pause point)
│   ├─> What's most dangerous if skipped?
│   ├─> What do experts reliably forget under stress?
│   ├─> What requires team coordination/shared awareness?
│   ├─> What has downstream cascading failures?
│   └─> OMIT: Steps professionals never skip, obvious items, comprehensive how-to
│
├─> Draft checklist
│   ├─> 5-9 items per pause point maximum
│   ├─> 60-90 seconds execution time maximum
│   ├─> One page, sans serif font, upper and lowercase
│   ├─> Precise, simple wording (no vagueness)
│   └─> Include forcing functions (verbal confirmations, sign-offs)
│
├─> TEST in real-world conditions
│   ├─> Use actual users, not designers
│   ├─> Observe in complex/stressful scenarios
│   ├─> Expect first draft to FAIL
│   ├─> Document: What was skipped? What took too long? What was confusing?
│   └─> ITERATE: Refine → Retest → Repeat until works consistently
│
└─> Implementation decision tree
    ├─> Make it TEAM CONVERSATION (not paperwork)
    │   ├─> Require VERBAL confirmation
    │   ├─> All team members state NAME and ROLE (activation phenomenon)
    │   └─> Lowest-authority person initiates checklist
    │
    ├─> Empower STOP authority
    │   ├─> Anyone can halt process if checklist incomplete
    │   └─> Create forcing function (e.g., metal tent until nurse approves)
    │
    └─> When to DEVIATE from checklist?
        ├─> Unique circumstances require professional judgment
        ├─> Time-critical emergency demands prioritization
        └─> BUT: Deviation must be informed choice, not negligence

Construction Coordination Decision Tree

START: Complex building project with 16+ specialized trades
│
├─> Create construction SCHEDULE
│   ├─> Line-by-line, day-by-day required tasks
│   ├─> Color-code CRITICAL PATH (tasks that delay everything if missed)
│   └─> Submit to all subcontractors for verification
│
├─> Create SUBMITTAL SCHEDULE (communication requirements)
│   ├─> Who must communicate with whom?
│   ├─> By which date?
│   ├─> About what decisions/specifications?
│   └─> What meetings required at which decision points?
│
├─> Run CLASH DETECTION software
│   ├─> Identify specification conflicts (ductwork vs. beam placement)
│   ├─> Resolve through group discussion (not individual autonomy)
│   └─> Update specifications before construction begins
│
├─> Daily execution
│   ├─> Supervisors report completed tasks → Project executive
│   ├─> Update schedule weekly minimum
│   └─> Post new work phases visibly
│
└─> HALT construction if:
    ├─> Required communication checkpoint not completed
    ├─> Unresolved clash detected between trades
    └─> Critical specification unclear or contradictory

Surgical Checklist Example (WHO Model)

PAUSE POINT 1: BEFORE ANESTHESIA (7 items, 60 seconds)
├─> Patient identity verified? (verbal confirmation with patient)
├─> Surgical site marked? (visual inspection)
├─> Consent signed and informed? (document verified)
├─> Pulse oximeter functioning? (signal confirmed)
├─> Medication allergies known? (team awareness)
├─> Airway risk assessed? (difficult intubation anticipated?)
└─> Blood available if needed? (type and cross-match confirmed)

PAUSE POINT 2: BEFORE INCISION (7 items, 60 seconds)
├─> TEAM INTRODUCTIONS: Each person states name and role
├─> Correct patient, site, procedure? (verbal confirmation)
├─> Prophylactic antibiotic given <60 min ago? (time-critical)
├─> Radiology images displayed? (visual reference available)
├─> Expected duration? (team temporal awareness)
├─> Anticipated blood loss? (preparation for emergency)
└─> Equipment/concerns? (surface any worries NOW)

PAUSE POINT 3: BEFORE LEAVING OR (5 items, 60 seconds)
├─> Procedure name verified? (correct documentation)
├─> Needle/sponge/instrument count correct? (nothing left inside)
├─> Specimens labeled? (with patient name, verbal confirmation)
├─> Equipment problems to address? (flag for repair)
└─> Recovery concerns? (handoff to recovery team complete)

Anti-Patterns

Master Builder Syndrome

Novice approach: "I'm the expert—I can hold all the knowledge and coordinate everything myself. Systematic coordination constrains my professional judgment."

Expert approach: "Modern complexity exceeds individual cognitive capacity. I need systematic tools to coordinate specialists and catch my inevitable memory lapses. Checklists buttress expertise, not replace it."

Timeline to expertise:

  • 0-2 years: Resist checklists as threats to developing autonomy
  • 3-5 years: Begin noticing personal memory failures, reluctantly try checklists
  • 5-10 years: Experience prevented error through checklist, embrace as cognitive net
  • 10+ years: Advocate for systematic approaches, design checklists for others

Recognition shibboleth: "Checklists handle the dumb stuff so I can focus cognitive capacity on the hard stuff" vs. "I don't need reminders—I'm experienced enough to remember everything."


Checklist Hypertrophy

Novice approach: Create comprehensive 40-item checklist spelling out every step because "thoroughness equals safety." Takes 8 minutes to complete.

Expert approach: Ruthlessly limit to 5-9 killer items per pause point. 60-90 seconds maximum. Omit what professionals reliably do. Make it "swift, usable, and resolutely modest."

Timeline to expertise:

  • First draft: 30+ items because "everything seems important"
  • After first test: Observe people shortcutting, skipping items due to length
  • Iteration 3-5: Cut ruthlessly to only what's MOST dangerous if skipped
  • Final version: 5-9 items that people actually use consistently

Recognition shibboleth: "What can we remove?" vs. "What else should we add?"


Paperwork Compliance Theater

Novice approach: Nurse silently checks boxes on clipboard alone, files form in chart. No verbal confirmation, no team discussion.

Expert approach: Checklist is team CONVERSATION with verbal confirmations. Lowest-authority person (nurse) initiates. Everyone speaks names. Team consensus required before proceeding.

Timeline to expertise:

  • Month 1: Treat as bureaucratic requirement, check boxes silently
  • Month 2-3: Hospital mandates verbal confirmation, feels awkward/wasteful
  • Month 4-6: Experience moment when verbal check surfaces critical forgotten item
  • Month 6+: Recognize activation phenomenon—team coordination visibly improves

Recognition shibboleth: "Did everyone hear that?" vs. silently checking boxes


Individual Heroism Paradigm

Novice approach: "Great professionals improvise brilliantly under pressure. Checklists are for less skilled people. I have 'the right stuff.'"

Expert approach: "Modern heroism is calm procedure-following and effective teamwork. Sullenberger saved 155 lives through disciplined checklist use, not exceptional flying. Discipline is the fourth element of professionalism."

Timeline to expertise:

  • Years 1-5: View checklists as embarrassing crutch, beneath expertise
  • Major failure: Personal error causes harm despite knowledge/skill
  • Crisis moment: Realize even exceptional individuals make predictable errors
  • Years 5-10: Embrace discipline alongside selflessness, skill, trustworthiness
  • Years 10+: Model systematic approaches, mentor others toward discipline

Recognition shibboleth: "Man is fallible, but maybe men are less so" vs. "I've never had a problem."


Command-and-Control Centralization

Novice approach: Complex crisis requires centralized expert directing all decisions. Frontline workers await instructions. (FEMA Hurricane Katrina model)

Expert approach: "Push power to periphery. Set clear goals, maintain communication, measure progress—but frontline makes decisions with local knowledge." (Walmart Katrina model: "Do what's right above your level.")

Timeline to expertise:

  • Initial crisis: Attempt centralized control, become information-overwhelmed
  • Day 2-3: Realize cannot process information volume or respond fast enough
  • Breakthrough: Empower frontline decision-making within clear goals
  • Post-crisis: Institutionalize distributed authority with communication requirements

Recognition shibboleth: "What decision authority do you need?" vs. "Wait for my approval."


Technology Solutionism

Novice approach: "Electronic medical records / surgical robots / AI will eliminate errors. We don't need procedural changes—just better technology."

Expert approach: "Technology cannot handle unpredictability or complex judgment. Optimizing individual components creates 'expensive junk' without systematic coordination. Technology enables human judgment but doesn't replace it."

Timeline to expertise:

  • Implementation phase: Excited by technological solution promise
  • Months 1-6: Discover technology creates new failure modes
  • Year 1: Realize technology doesn't prevent communication failures
  • Year 2+: Combine technology with systematic human processes (checklists)

Recognition shibboleth: "Anyone who understands systems will know immediately that optimizing parts is not a good route to system excellence."


Desk-Based Checklist Design

Novice approach: Create perfect checklist at desk based on procedure manual. Assume first draft will work. Distribute for immediate use.

Expert approach: Test with actual users in real conditions. Expect first draft to fail. Iterate 5-10 times based on observed failures. Involve frontline professionals in design.

Timeline to expertise:

  • First implementation: Desk-designed checklist falls apart in real use
  • Tests 1-3: Observe length issues, confusing wording, missed workflows
  • Tests 4-7: Refine based on user feedback, real-world constraints
  • Tests 8-10: Fine-tune until works consistently under stress
  • Final: "Checklists must be tested in the real world, which is inevitably more complicated than expected."

Recognition shibboleth: Spending more time testing/observing than writing.

Mental Models & Shibboleths

"Too much airplane for one man to fly"

  • Maps to: Complexity exceeding individual cognitive capacity
  • Expert usage: Recognizing when systematic support becomes necessary, not optional
  • Novice trap: Believing sufficient skill/intelligence eliminates need for procedures

"Cognitive net"

  • Maps to: Checklists as external memory catching inevitable mental flaws
  • Expert usage: "Even I make predictable errors—checklists catch them"
  • Novice trap: "I don't make those errors" or "That's for less skilled people"

"DO-CONFIRM vs. READ-DO"

  • Shibboleth revealing understanding of context-dependent checklist design
  • Expert: Chooses format based on user expertise and task familiarity
  • Novice: Uses one format for everything or doesn't know distinction exists

"Killer items"

  • Identifies practitioner who designs effective checklists
  • Expert: "What's most dangerous if skipped AND most likely overlooked?"
  • Novice: "What are all the steps?" or "Everything's important"

"Activation phenomenon"

  • Deep understanding of checklist mechanism beyond task verification
  • Expert: Designs checklists to force speaking/introductions for teamwork
  • Novice: Views speaking names as time-wasting formality

"Swift, usable, and resolutely modest"

  • Design philosophy separating effective from hypertrophied checklists
  • Expert mantra when tempted to add "just one more item"
  • Novice never feels checklist is complete enough

"First drafts always fail"

  • Reveals testing-based vs. desk-based design philosophy
  • Expert: Allocates 80% of effort to testing/iteration
  • Novice: Spends 90% on writing, 10% on "rollout"

Asking "What can we remove?" vs. "What should we add?"

  • Fundamental orientation difference
  • Expert constantly prunes to essential killer items
  • Novice accumulates comprehensive coverage

"Man is fallible, but maybe men are less so"

  • Core insight about distributed teamwork vs. individual heroism
  • Expert: Embraces team coordination as force multiplier
  • Novice: Views coordination as constraint on individual performance

"That's not my problem"

  • Recognized as "possibly the worst thing people can think"
  • Expert: Takes systemic responsibility beyond narrow specialty
  • Novice: Maintains specialty silos without coordination

References

  • Source: *The Checklist Manifesto: How to Get Things Right* by Atul Gawande (2009)
  • Historical examples: Boeing Model 299 (1935), WHO Safe Surgery Checklist (2008), Peter Pronovost central line infections (2001)
  • Temporal shift: Ignorance-dominated era (pre-1950s) → Ineptitude-dominated era (modern)

平台分布

Codex

36.7%
按下载量换算186

Claude

28.58%
按下载量换算145

Cursor

18.65%
按下载量换算95

Gemini CLI

8.24%
按下载量换算42

安全审计

Gen Agent Trust Hub

通过

Socket

通过

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。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