Token导航 LogoToken导航

Agent Skill · 研究检索

consultancy-practices(咨询实践)

consultancy-practices 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。

consultancy-practices 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 38,093。

总安装 1,616周安装 68GitHub Stars 329下载 566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:consultancy-practices(咨询实践)
来源仓库:https://github.com/proffesor-for-testing/agentic-qe
仓库路径:skills/consultancy-practices
安装命令:
npx skills add https://github.com/proffesor-for-testing/agentic-qe --skill consultancy-practices
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/proffesor-for-testing/agentic-qe --skill consultancy-practices

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。

提供质量咨询的标准流程,包括倾听优先、影响/努力矩阵和知识转移。覆盖评估、转型和顾问三种合作模式的时间规划与成功度量。适用于危机干预、战略对齐和执行失败诊断等复杂场景。强调定义明确的成功指标和周度跟踪机制。consultancy-practices 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/consultancy-practices

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/proffesor-for-testing/agentic-qe --skill consu…;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

consultancy-practices 怎么安装?

在终端执行 npx skills add https://github.com/proffesor-for-testing/agentic-qe --skill consultancy-pra…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

consultancy-practices 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。

consultancy-practices 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。

consultancy-practices 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。

consultancy-practices 用的人多吗?

公开数据是累计安装 1,616 次,近一周安装 68 次,下载 566 次,GitHub 329 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。

consultancy-practices 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
consultancy-practices

咨询实践 · 本页

1,616329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

Consultancy Practices

<default_to_action> When consulting on quality:

  1. LISTEN FIRST: Understand their context before prescribing solutions
  2. DISCOVER: What's the pain? What have they tried? What are constraints?
  3. PRIORITIZE: Impact/effort matrix - high impact, low effort first
  4. TRANSFER KNOWLEDGE: Leave them better, not dependent on you
  5. MEASURE: Define success metrics upfront, track weekly

Engagement Types:

  • Assessment (1-4 weeks): Discover, analyze, recommend
  • Transformation (3-12 months): Implement new practices
  • Advisory (ongoing): Strategic guidance, course-correct
  • Crisis (1-4 weeks): Fix critical issues blocking production

Key Questions:

  • "Walk me through your last deployment"
  • "Tell me about a recent bug that escaped to production"
  • "If you could fix one thing, what would it be?" </default_to_action>

Quick Reference Card


Common Patterns (What Clients Say vs. What They Mean)

"We Need Test Automation"

What they say: "We need test automation" What they mean: "Manual testing is too slow/expensive"

Discovery: How long is regression? What's deployment frequency?

Typical Finding: They need faster feedback, not "automation"

Recommendation:

  1. Unit tests for new code (TDD)
  2. Smoke tests for critical paths
  3. Keep exploratory for discovery
  4. Build automation incrementally

"Fix Our Quality Problem"

What they say: "We have too many bugs" What they mean: "Something is broken but we don't know what"

Discovery: Where found? What types? When introduced?

Typical Finding: No test strategy, testing too late, poor feedback loops

Recommendation:

  1. Shift testing left
  2. Improve coverage on critical paths
  3. Speed up CI/CD feedback
  4. Better requirements/acceptance criteria

"We Want to Scale Quality"

What they say: "Growing fast, quality can't keep up" What they mean: "Can't hire enough QA fast enough"

Discovery: Current QA:Dev ratio? Where's QA spending time?

Typical Finding: QA is bottleneck - manual regression, gatekeeping

Recommendation:

  1. Make QA strategic, not tactical
  2. Developers own test automation
  3. QA focuses on exploratory, risk analysis
  4. Use agentic approaches for scale

Difficult Situations

"We already tried that" → "Tell me what you tried and what didn't work" (learn from their experience)

"Our context is special" → "Help me understand what makes yours special" (they might be right, or making excuses)

"We don't have budget/time" → "What's the cost of not fixing this? Let's start small" (show ROI)

"That won't work here" → "What specific constraints? Let's adapt" (find what WILL work)


Agent Integration

// Automated codebase assessment
const assessment = await Task("Assess Codebase", {
  scope: 'client-project/',
  depth: 'comprehensive',
  reportFormat: 'executive-summary'
}, "qe-quality-analyzer");

// Returns: { qualityScore, testCoverage, technicalDebt, recommendations }

// ROI analysis for quality initiatives
const roi = await Task("Calculate ROI", {
  currentState: { defectEscapeRate: 0.15, mttr: 48 },
  proposedImprovements: ['test-automation', 'ci-cd-pipeline'],
  timeframe: '6-months'
}, "qe-quality-analyzer");

// Returns: { estimatedCost, estimatedSavings, paybackPeriod }

Agent Coordination Hints

Memory Namespace

aqe/consultancy/
├── assessments/*      - Client assessments
├── recommendations/*  - Prioritized recommendations
├── roi-analysis/*     - ROI calculations
└── progress/*         - Implementation tracking

Fleet Coordination

const consultingFleet = await FleetManager.coordinate({
  strategy: 'client-engagement',
  agents: [
    'qe-quality-analyzer',          // Assess current state
    'qe-regression-risk-analyzer',  // Risk assessment
    'qe-quality-gate',              // Define quality gates
    'qe-deployment-readiness'       // Deployment maturity
  ],
  topology: 'hierarchical'
});

Related Skills


Remember

Good consulting is about empowering teams, not creating dependency. Your success is measured by them not needing you anymore - while still wanting to work with you again.

Best compliment: "We've got this now, but when we tackle X next year, we're calling you."

Be honest. Be helpful. Be context-driven. Leave them better.

平台分布

Claude Code

26.81%
按下载量换算152

Antigravity

24.06%
按下载量换算136

windsurf

17.9%
按下载量换算101

github-copilot

13.28%
按下载量换算75

Codex

8.61%
按下载量换算49

trae

3.56%
按下载量换算20

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