Token导航 LogoToken导航

Agent Skill · AI 工具

culture-engagement(文化参与)

culture-engagement 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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。

culture-engagement 是AI 工具类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证为 MIT,第三方扫描已通过,按安装量在AI 工具类的 2,536 个 Skill 里排第 1,792。

总安装 466周安装 20GitHub Stars 3下载 163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
MIT

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:culture-engagement(文化参与)
来源仓库:https://github.com/pluginagentmarketplace/custom-plugin-engineering-manager
仓库路径:skills/culture-engagement
安装命令:
npx skills add https://github.com/pluginagentmarketplace/custom-plugin-engineering-manager --skill culture-engagement
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/pluginagentmarketplace/custom-plugin-engineering-manager --skill culture-engagement

这个 Skill 是做什么的

AI 工具类 Skill 用来扩展助手本身的能力,例如接模型、接检索、接外部服务。

culture-engagement 为工程管理者提供心理安全与包容性环境构建工具包。适用于团队健康度调研、仪式设计与 engagement 提升活动策划。包含心理安全脉冲调查模板、庆祝机制与冲突解决流程建议。输出聚焦可操作步骤,避免理论堆砌而无实际落地路径。应定期重复测量,跟踪干预措施的有效性并及时调整策略。

来源仓库内路径:skills/culture-engagement

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/pluginagentmarketplace/custom-plugin-engineeri…;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

culture-engagement 怎么安装?

在终端执行 npx skills add https://github.com/pluginagentmarketplace/custom-plugin-engineering-manager…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

culture-engagement 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。

culture-engagement 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。

culture-engagement 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

culture-engagement 用的人多吗?

公开数据是累计安装 466 次,近一周安装 20 次,下载 163 次,GitHub 3 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。

culture-engagement 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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 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AI 工具类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

AI 工具类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
executing-plans

执行计划 · Codex、Claude

1,515,336173,110只读MIT通过
verification-before-completion

完成前的验证 · Codex、Claude

1,319,472173,121权限未标注MIT通过
subagent-driven-development

子 Agent 驱动开发 · Codex、Claude

1,312,416173,138只读MIT通过
copy-editing

复制编辑 · Codex、Claude

1,209,57625,632只读MIT通过
paywall-upgrade-cro

付费专区升级 cro · Codex、Claude

1,030,17625,617只读MIT通过
culture-engagement

文化参与 · 本页

4663只读MIT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

Culture & Engagement Skill

Purpose

Provide engineering managers with frameworks for building healthy team cultures, fostering psychological safety, driving engagement, and creating inclusive environments.

Primary Bond

Agent: culture-engagement-agent Relationship: This skill provides survey templates, ritual frameworks, and engagement tools that the agent uses.


Templates

Psychological Safety Pulse

psychological_safety_pulse:
  metadata:
    team: "{Team name}"
    date: "{Date}"
    participants: "{X/Y responded}"
    response_rate: "{X}%"

  dimensions:
    inclusion_safety:
      questions:
        - "I feel like I belong on this team"
        - "My unique perspective is valued"
        - "I can be myself at work"
      average_score: null
      trend: null

    learner_safety:
      questions:
        - "It's safe to ask questions, even obvious ones"
        - "Mistakes are treated as learning opportunities"
        - "I can admit when I don't know something"
      average_score: null
      trend: null

    contributor_safety:
      questions:
        - "My contributions make a real difference"
        - "I can use my skills effectively"
        - "My work is valued by the team"
      average_score: null
      trend: null

    challenger_safety:
      questions:
        - "I can challenge ideas without negative consequences"
        - "Speaking up is encouraged, even with bad news"
        - "Disagreement is handled constructively"
      average_score: null
      trend: null

  interpretation:
    4.5_plus: "Excellent - maintain and reinforce"
    4.0_to_4.4: "Good - minor improvements needed"
    3.5_to_3.9: "Concerning - targeted intervention"
    below_3.5: "Critical - immediate action needed"

  action_planning:
    top_strength: ""
    top_concern: ""
    committed_actions: []
    follow_up_date: ""

Engagement Survey

engagement_survey:
  metadata:
    team: "{Team name}"
    quarter: "{Q1 2025}"
    response_rate: "{X}%"

  categories:
    basic_needs:
      - "I know what's expected of me"
      - "I have the tools and resources to do my work"

    individual:
      - "I can do what I do best every day"
      - "I receive recognition for good work"
      - "Someone at work cares about me as a person"
      - "Someone encourages my development"

    team:
      - "My opinions seem to count"
      - "The mission makes my work feel important"
      - "My co-workers are committed to quality"
      - "I have a best friend at work"

    growth:
      - "I've had conversations about my progress"
      - "I have opportunities to learn and grow"

  eNPS:
    question: "How likely are you to recommend this team as a place to work?"
    scale: "0-10"
    calculation: "Promoters (9-10) - Detractors (0-6)"
    target: ">40"

  interpretation:
    engagement_score:
      excellent: ">4.5"
      good: "4.0-4.4"
      needs_attention: "3.5-3.9"
      critical: "<3.5"

    eNPS:
      excellent: ">50"
      good: "30-50"
      needs_attention: "0-30"
      critical: "<0"

Team Culture Canvas

team_culture_canvas:
  values:
    - name: "{Value 1 - e.g., Ownership}"
      definition: "{What it means to us}"
      behaviors:
        do:
          - "{Observable behavior we encourage}"
          - "{Another behavior}"
        dont:
          - "{Behavior that violates this value}"

    - name: "{Value 2 - e.g., Transparency}"
      definition: ""
      behaviors:
        do: []
        dont: []

  norms:
    communication:
      - "Default to async, sync when needed"
      - "Respond within 4 hours during work hours"
      - "Use public channels unless confidential"

    meetings:
      - "Agenda required for all meetings"
      - "Start and end on time"
      - "Notes shared within 24 hours"
      - "Camera on for video calls (optional for listeners)"

    feedback:
      - "Direct and kind"
      - "Timely (within 48 hours)"
      - "In private for constructive"
      - "In public for praise"

    work_life:
      - "No messages after 6pm local time"
      - "Vacation is vacation"
      - "Core hours: 10am-4pm local"

  rituals:
    daily:
      - name: "Standup"
        time: "{Time}"
        format: "{Async/Sync}"
        purpose: "Alignment and blockers"

    weekly:
      - name: "Team sync"
        time: "{Day/Time}"
        duration: "30 min"
        purpose: "Strategic alignment"

      - name: "Social time"
        time: "{Day/Time}"
        duration: "30 min"
        purpose: "Connection"

    monthly:
      - name: "All-hands"
        purpose: "Company updates"

      - name: "Recognition"
        purpose: "Celebrate wins"

    quarterly:
      - name: "Retrospective"
        purpose: "Continuous improvement"

      - name: "Planning"
        purpose: "Align on goals"

Stay Interview Guide

stay_interview:
  purpose: "Understand what keeps people engaged and identify retention risks"
  frequency: "Quarterly for all, monthly for high-risk"

  questions:
    engagement:
      - "What keeps you here?"
      - "What do you look forward to when you come to work?"
      - "When was the last time you thought about leaving?"

    concerns:
      - "What might tempt you to leave?"
      - "What frustrates you most about working here?"
      - "What would you change if you could?"

    value:
      - "Do you feel valued? Why or why not?"
      - "Is your work recognized appropriately?"
      - "Do you feel you're paid fairly?"

    growth:
      - "Do you see a future for yourself here?"
      - "What skills would you like to develop?"
      - "Is your career progressing as you'd like?"

    manager:
      - "How can I better support you?"
      - "Is there feedback you haven't shared?"
      - "What do you need from me?"

  action_planning:
    immediate_actions: []
    longer_term_changes: []
    follow_up_date: ""
    commitment_made: ""

Decision Trees

Psychological Safety Intervention

Safety score below 4.0
|
+-- Which dimension is lowest?
|   |
|   +-- Inclusion Safety
|   |   +-- New team members struggling?
|   |   +-- Cliques forming?
|   |   +-- Action: Intentional inclusion activities
|   |
|   +-- Learner Safety
|   |   +-- Questions being mocked?
|   |   +-- Mistakes punished?
|   |   +-- Action: Leader vulnerability modeling
|   |
|   +-- Contributor Safety
|   |   +-- Ideas ignored?
|   |   +-- Credit not given?
|   |   +-- Action: Recognition program
|   |
|   +-- Challenger Safety
|       +-- Bad news hidden?
|       +-- Dissent suppressed?
|       +-- Action: Explicitly invite challenge
|
+-- Is there a specific incident?
|   +-- Yes -> Address directly with individuals
|   +-- No -> Continue
|
+-- Team-wide issue or specific individuals?
    +-- Team-wide -> Team retrospective, new norms
    +-- Specific -> 1-on-1 coaching, potential consequences

Retention Risk Response

Retention risk identified
|
+-- Risk level?
|   +-- High (actively interviewing) -> Immediate action
|   +-- Medium (frustrated but not leaving) -> Prioritize
|   +-- Low (minor concerns) -> Address in normal cadence
|
+-- Root cause?
|   +-- Compensation -> Market review, adjustment if warranted
|   +-- Growth -> IDP, stretch assignments, promotion path
|   +-- Manager -> Coaching, potentially reassign
|   +-- Culture -> Team intervention, behavior changes
|   +-- Work itself -> Role adjustment, project changes
|
+-- Is this person critical to retain?
|   +-- Yes -> Escalate, consider exceptions
|   +-- No -> Standard support, don't over-invest
|
+-- Can we address the root cause?
    +-- Yes -> Create action plan, timeline
    +-- No -> Be honest, help them succeed elsewhere

Anti-Patterns

anti_patterns:
  culture_theater:
    symptom: "Values on the wall but not in actions"
    remedy:
      - "Define observable behaviors for each value"
      - "Call out violations (kindly but firmly)"
      - "Celebrate values in action"

  survey_fatigue:
    symptom: "Low response rates, cynicism about surveys"
    remedy:
      - "Reduce frequency, increase impact"
      - "Share results and actions publicly"
      - "Close the loop on previous feedback"

  brilliant_jerk:
    symptom: "High performer with toxic behavior tolerated"
    remedy:
      - "Behavior is a performance dimension"
      - "Address immediately, no exceptions"
      - "Impact on team is measurable"

  forced_fun:
    symptom: "Mandatory team building that people dread"
    remedy:
      - "Make social activities optional"
      - "Offer variety (not everyone likes happy hours)"
      - "Focus on genuine connection"

Quick Reference Cards

Recognition Best Practices

recognition:
  public:
    format: "I want to recognize {name} for {specific action}.
             This demonstrated our value of {value}
             and resulted in {impact}."
    when: "Weekly in team channel or meeting"

  private:
    format: "I noticed you {specific action}.
             This showed great {skill/value}
             and made a real difference in {outcome}."
    when: "As it happens, within 48 hours"

  peer:
    format: "Shoutout to {name} for helping me with {task}.
             Really appreciated your {specific contribution}."
    when: "Encourage regularly, model it yourself"

  guidelines:
    - "Be specific (not just 'great job')"
    - "Be timely (within 48 hours)"
    - "Tie to values when possible"
    - "Balance public and private"
    - "Recognize effort, not just outcomes"

Meeting Inclusion Checklist

meeting_inclusion:
  before:
    - "Is everyone who should be there invited?"
    - "Is the time zone fair for all participants?"
    - "Is the agenda shared in advance?"

  during:
    - "Are all voices heard (not just the loudest)?"
    - "Are there multiple ways to participate (verbal, chat)?"
    - "Are we avoiding side conversations?"
    - "Are we crediting ideas to originators?"

  after:
    - "Are notes shared with all stakeholders?"
    - "Are action items clear and assigned?"
    - "Is there a way to give feedback on the meeting?"

Remote/Hybrid Best Practices

remote_practices:
  connection:
    - "Camera on as default (but respect opt-out)"
    - "Virtual coffee chats scheduled"
    - "Team rituals adapted for remote"

  communication:
    - "Over-communicate (2x what feels necessary)"
    - "Write things down (tribal knowledge shared)"
    - "Async-first, sync when needed"

  inclusion:
    - "Same experience for remote and in-office"
    - "No hallway decisions (document everything)"
    - "Time zone rotation for recurring meetings"

Troubleshooting

ProblemRoot CauseSolution
Silent meetingsLow psychological safetyInvite input explicitly, wait for answers
Survey scores lowReal problems or survey fatigueAct on feedback, show progress
High turnoverMultiple possible causesExit interviews, stay conversations
Cliques formingNatural but needs managementMix up teams, cross-functional projects

Validation Rules

input_validation:
  situation:
    type: string
    min_length: 10
    required: true

  team_size:
    type: integer
    min: 1
    max: 100
    required: false

  remote_percentage:
    type: integer
    min: 0
    max: 100
    required: false

Resources

Books:

  • The Fearless Organization - Amy Edmondson
  • Culture Code - Daniel Coyle
  • Radical Candor - Kim Scott
  • No Rules Rules - Reed Hastings

Research:

  • Google's Project Aristotle
  • Gallup Q12 engagement research
  • Amy Edmondson's psychological safety research

平台分布

Claude Code

30.1%
按下载量换算49

windsurf

21.43%
按下载量换算35

Codex

17.56%
按下载量换算29

OpenCode

12.18%
按下载量换算20

Cursor

6.68%
按下载量换算11

Antigravity

3.32%
按下载量换算5

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。

继续浏览同类 Skills