Token导航 LogoToken导航

Agent Skill · 研究检索

technical-decision-making(技术决策)

technical-decision-making 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。

technical-decision-making 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;许可证为 MIT,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 52,496。

总安装 558周安装 23GitHub Stars 3下载 182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:technical-decision-making(技术决策)
来源仓库:https://github.com/pluginagentmarketplace/custom-plugin-engineering-manager
仓库路径:skills/technical-decision-making
安装命令:
npx skills add https://github.com/pluginagentmarketplace/custom-plugin-engineering-manager --skill technical-decision-making
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 technical-decision-making

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。

用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务场景快速定位候选结果。通过 npx skills add 命令从指定 GitHub 仓库安装使用。安装前需确认权限范围、维护状态,以及是否会触发联网或文件读写操作。

technical-decision-making 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/technical-decision-making

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

technical-decision-making 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。

technical-decision-making 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。

technical-decision-making 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。

technical-decision-making 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。

technical-decision-making 用的人多吗?

公开数据是累计安装 558 次,近一周安装 23 次,下载 182 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。

technical-decision-making 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。
  • 需要处理研究检索类任务、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。

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
technical-decision-making

技术决策 · 本页

5583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

Technical Decision Making Skill

Purpose

Provide engineering managers with structured frameworks for making sound technical decisions, evaluating technologies, managing technical debt, and developing technical roadmaps.

Primary Bond

Agent: technical-strategy-agent Relationship: This skill provides ADR templates, evaluation frameworks, and decision tools that the technical-strategy-agent uses.


Templates

Architecture Decision Record (ADR)

# ADR-{NUMBER}: {TITLE}

## Status
{Proposed | Accepted | Deprecated | Superseded by ADR-XXX}

## Date
{YYYY-MM-DD}

## Context
{What is the issue that we're seeing that is motivating this decision?}

## Decision Drivers
- {driver 1}
- {driver 2}

## Considered Options
1. {Option 1}
2. {Option 2}
3. {Option 3}

## Decision Outcome
Chosen option: "{option X}", because {justification}.

### Positive Consequences
- {consequence 1}

### Negative Consequences
- {consequence 1}

## Pros and Cons of Options

### Option 1: {name}
| Aspect | Assessment |
|--------|------------|
| Effort | {Low/Medium/High} |
| Risk | {Low/Medium/High} |
| Team Fit | {score}/5 |
| Reversibility | {Easy/Hard} |

Good, because {argument}.
Bad, because {argument}.

## Links
- {Link to related ADR}
- {Link to documentation}

Technology Evaluation Matrix

technology_evaluation:
  template:
    candidate: "{Technology name}"
    evaluation_date: "{Date}"
    evaluator: "{Name}"

  criteria:
    technical_fit:
      weight: 25%
      factors:
        - scalability_match: "1-5"
        - performance_requirements: "1-5"
        - security_compliance: "1-5"
      score: null

    team_readiness:
      weight: 20%
      factors:
        - current_expertise: "1-5"
        - learning_curve: "1-5"
        - hiring_market: "1-5"
      score: null

    ecosystem_maturity:
      weight: 20%
      factors:
        - community_size: "1-5"
        - documentation_quality: "1-5"
        - library_availability: "1-5"
      score: null

    operational:
      weight: 20%
      factors:
        - deployment_complexity: "1-5"
        - monitoring_support: "1-5"
        - maintenance_burden: "1-5"
      score: null

    cost:
      weight: 15%
      factors:
        - licensing: "1-5"
        - infrastructure: "1-5"
        - training: "1-5"
      score: null

  interpretation:
    4.5_plus: "Strong candidate - proceed"
    3.5_to_4.4: "Viable - address concerns"
    2.5_to_3.4: "Risky - significant gaps"
    below_2.5: "Not recommended"

Technical Debt Tracker

technical_debt_item:
  id: "TD-{NUMBER}"
  title: "{Short description}"
  category: "{architecture | code | infrastructure | testing | documentation}"
  quadrant: "{deliberate_prudent | deliberate_reckless | inadvertent_prudent | inadvertent_reckless}"

  description: "{Detailed description}"
  created_date: "{Date}"
  owner: "{Team/Person}"

  impact:
    development_velocity: "{-X%}"
    reliability_risk: "{low | medium | high}"
    security_risk: "{low | medium | high}"

  effort:
    estimate: "{T-shirt: S/M/L/XL}"
    sprints: "{Number}"
    dependencies: ["{Other work}"]

  interest_rate: "{stable | increasing | decreasing}"

  recommendation:
    action: "{fix | defer | monitor | accept}"
    timeline: "{Q1 2025}"
    justification: "{Why this recommendation}"

  resolution:
    status: "{open | in_progress | resolved | wont_fix}"
    resolved_date: null
    notes: null

Technical Roadmap

technical_roadmap:
  year: 2025

  q1:
    theme: "Foundation"
    initiatives:
      - name: "Infrastructure modernization"
        priority: "P0"
        owner: "Platform team"
        dependencies: []
      - name: "Observability stack"
        priority: "P1"
        owner: "SRE"
        dependencies: ["Infrastructure modernization"]

  q2:
    theme: "Scale"
    initiatives:
      - name: "Database sharding"
        priority: "P0"
        owner: "Data team"
        dependencies: ["Infrastructure modernization"]

  q3:
    theme: "Velocity"
    initiatives:
      - name: "CI/CD improvements"
        priority: "P1"
        owner: "DevEx team"

  q4:
    theme: "Innovation"
    initiatives:
      - name: "Event-driven architecture"
        priority: "P2"
        owner: "Architecture team"

Decision Trees

Build vs Buy

Need identified
|
+-- Is this core to our business?
|   +-- Yes -> Lean toward Build
|   +-- No -> Continue
|
+-- Does a good solution exist?
|   +-- No -> Must Build
|   +-- Yes -> Continue
|
+-- Can we afford the buy option?
|   +-- No -> Must Build
|   +-- Yes -> Continue
|
+-- Is time-to-market critical?
|   +-- Yes -> Lean toward Buy
|   +-- No -> Continue
|
+-- Do we have the expertise to build?
    +-- Yes -> Evaluate total cost of ownership
    +-- No -> Buy (or hire first)

Architecture Pattern Selection

Team size and domain complexity
|
+-- Small team (<5), Simple domain
|   +-- Monolith
|
+-- Small team, Complex domain
|   +-- Modular Monolith
|
+-- Large team (10+), Complex domain
|   +-- Microservices (with caution)
|
+-- Variable load, Event-driven
|   +-- Serverless / Event-driven
|
+-- Strong audit requirements
    +-- Event Sourcing + CQRS

Anti-Patterns

anti_patterns:
  resume_driven_development:
    symptoms:
      - "Let's use X because it's cool"
      - "This will look great on our blog"
    remedy:
      - "Require business case for any new tech"
      - "Evaluate with scoring matrix"

  golden_hammer:
    symptoms:
      - "We use X for everything"
      - "X worked before, it'll work now"
    remedy:
      - "Match tool to problem domain"
      - "Regular tech radar reviews"

  not_invented_here:
    symptoms:
      - "We'll build our own database"
      - "Open source isn't good enough"
    remedy:
      - "Build vs Buy analysis required"
      - "TCO comparison mandatory"

  analysis_paralysis:
    symptoms:
      - "We've been evaluating for 6 months"
      - "Let's add one more option"
    remedy:
      - "Time-box decisions"
      - "Use decision framework"
      - "Accept 'good enough'"

Quick Reference Cards

Decision Time-Boxing

Decision TypeTime BoxReversibility
Tool selection1 weekHigh
Framework choice2 weeksMedium
Architecture pattern1 monthLow
Platform migration1 quarterVery Low

Tech Debt Quadrant

                    Reckless                Prudent
            +---------------------+---------------------+
Deliberate  | "We don't have time | "We must ship now   |
            |  for design"        |  and deal with      |
            |  -> Fix ASAP        |  consequences"      |
            |                     |  -> Plan paydown    |
            +---------------------+---------------------+
Inadvertent | "What's layering?"  | "Now we know how    |
            |  -> Training needed |  we should have     |
            |                     |  done it"           |
            |                     |  -> Refactor next   |
            +---------------------+---------------------+

DORA Metrics

MetricEliteHighMediumLow
Deployment FrequencyOn-demandDaily-WeeklyWeekly-MonthlyMonthly+
Lead Time<1 hour<1 day<1 week1 month+
Change Failure Rate<5%5-10%10-15%15%+
Recovery Time<1 hour<1 day<1 week1 month+

Troubleshooting

ProblemRoot CauseSolution
Decisions get reversedPoor documentationUse ADR template
Tech debt grows uncheckedNo visibilityTrack with debt template
Wrong tech choicesNo evaluation processUse scoring matrix
Roadmap not followedUnclear prioritiesP0/P1/P2 classification

Validation Rules

input_validation:
  decision_context:
    type: string
    min_length: 20
    required: true

  constraints:
    type: object
    properties:
      budget: { type: string }
      timeline: { type: string }
      team_expertise: { type: array }
    required: false

  current_stack:
    type: array
    items: { type: string }
    required: false

Resources

Books:

  • Designing Data-Intensive Applications - Martin Kleppmann
  • Building Evolutionary Architectures - Ford, Parsons, Kua
  • Fundamentals of Software Architecture - Richards, Ford
  • The Staff Engineer's Path - Tanya Reilly

Standards:

  • Architecture Decision Records (ADR) - Michael Nygard
  • DORA Metrics - Accelerate research

平台分布

Claude Code

30.6%
按下载量换算56

windsurf

22.09%
按下载量换算40

Codex

19.3%
按下载量换算35

OpenCode

14.61%
按下载量换算27

Cursor

7.6%
按下载量换算14

Antigravity

3.59%
按下载量换算7

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