Token导航 LogoToken导航

Agent Skill · 研究检索

commercial-discovery(商业发现)

commercial-discovery 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。

commercial-discovery 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 65,351。

总安装 282周安装 12GitHub Stars 1下载 99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:commercial-discovery(商业发现)
来源仓库:https://github.com/piperubio/ai-agents
仓库路径:skills/commercial-discovery
安装命令:
npx skills add https://github.com/piperubio/ai-agents --skill commercial-discovery
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/piperubio/ai-agents --skill commercial-discovery

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。

commercial-discovery 专为 B2B 咨询销售设计,用于深度理解客户现状与未来目标,构建定制化解决方案的基础。适用于技术咨询项目前期调研,重点评估组织准备度、技术栈与团队能力,而非产品演示。通过结构化提问与笔记捕获,帮助销售团队准备谈判并输出可信的业务洞察,区别于 SaaS 式发现流程。

安装前应检查仓库权限与数据来源,确认是否触发联网或敏感信息处理,避免误用导致数据泄露。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/commercial-discovery

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/piperubio/ai-agents --skill commercial-discove…;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

commercial-discovery 怎么安装?

在终端执行 npx skills add https://github.com/piperubio/ai-agents --skill commercial-discovery。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

commercial-discovery 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。

commercial-discovery 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。

commercial-discovery 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。

commercial-discovery 用的人多吗?

公开数据是累计安装 282 次,近一周安装 12 次,下载 99 次,GitHub 1 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。

commercial-discovery 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
commercial-discovery

商业发现 · 本页

2821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

Commercial Discovery (B2B Consulting Sales)

Purpose

  • Enable thorough, structured discovery for B2B consulting sales.
  • Unlike SaaS discovery (which demos a product), consulting discovery must deeply understand the client's current state, desired future state, organizational dynamics, and constraints to later design a custom solution.
  • Prepare the seller and capture structured notes.

Key Differentiation from SaaS Discovery

  • No product to demo — discovery IS the product sample.
  • Must assess organizational readiness, not just feature fit.
  • Need to understand current tech stack, team capabilities, and culture.
  • Must map multiple stakeholders (not just a single buyer).
  • Consulting discovery often spans 2-3 meetings, not one.

Scope

  • This skill WILL:

- Generate pre-meeting research briefs with tailored SPIN questions - Map buying committees and stakeholder dynamics - Produce structured post-meeting discovery notes - Run mini tech-maturity assessments during discovery - Update pipeline state with discovery insights

  • This skill WILL NOT:

- Propose solutions (defer to solution-design phase) - Generate proposals or SOWs - Conduct qualification scoring (see commercial-qualification)

Inputs

  • prospect-profile.md — from commercial-prospecting
  • commercial-state.md — pipeline context
  • user_input — meeting details, known contacts, specific areas to explore

Outputs (contract)

Output 1: Pre-Meeting Brief (discovery-prep.md)

  • Company research summary — key facts, recent news, strategic context
  • Known pain points and hypotheses — from prospecting or prior interactions
  • Stakeholder map — known contacts, roles, likely agenda
  • SPIN question guide — 15-20 questions tailored to this prospect, organized by S/P/I/N (see references/discovery-frameworks.md)
  • Meeting agenda suggestion — 45-60 min structure
  • Red flags to watch for — signals this opportunity may not be real
  • Success criteria for the meeting — what "good" looks like

Output 2: Post-Meeting Discovery Notes (discovery-notes.md)

  • Meeting metadata — date, attendees, duration
  • Current State summary — tech stack, processes, team, pain points
  • Desired Future State — what success looks like for them
  • Gap Analysis — current → desired, organized by Software / Data / AI
  • Buying Committee Map — Champion, Economic Buyer, Technical Buyer, Coach, Blocker — with names
  • Budget signals — explicit mentions, inferred range
  • Timeline signals — urgency drivers, deadlines, fiscal year
  • Competition signals — other vendors mentioned, internal alternatives
  • Next steps agreed
  • Open questions requiring follow-up

Output 3: Updated commercial-state.md

Update the opportunity with discovery insights: stage, champion, key pain points, next action.


SPIN Framework Adapted for Tech Consulting

  • Situation: Current tech landscape, team structure, processes, recent initiatives
  • Problem: Pain points, inefficiencies, failed past initiatives, technical debt
  • Implication: Business impact of not solving (revenue loss, competitive risk, team attrition, compliance risk)
  • Need-payoff: Value of solving (ROI, speed, capability unlock, market advantage)

For the full SPIN question bank organized by service line (Software, Data, AI) with 10 questions per category, see references/discovery-frameworks.md.

Mini Tech Maturity Assessment (during discovery)

  • Run a quick 5-question assessment per axis (Software / Data / AI) to validate or update prospecting scores.
  • Compare self-reported maturity vs. observed indicators.
  • Full questionnaire available in references/discovery-frameworks.md.

Guardrails (must follow)

  1. Discovery is about listening, not pitching — question-to-statement ratio should be 3:1 minimum.
  2. Never propose a solution during discovery — note the urge, defer to solution-design phase.
  3. Always map at least Champion + Economic Buyer — if you cannot identify both, flag as risk.
  4. Capture exact quotes when possible — client's own words are gold for proposals.
  5. Never assume budget — probe with indirect questions.
  6. If discovery reveals the prospect is not a fit, say so honestly rather than forcing it.
  7. Flag when a single discovery meeting is insufficient and recommend follow-up.

Example

Context: Logistics company (Acme Logistics) exploring data platform modernization. Legacy SQL Server data warehouse, 15-person IT team, $40M revenue.

Sample SPIN Questions:

Situation:

  • "Walk me through how data currently flows from your TMS and WMS into the SQL Server warehouse."
  • "How many people on the team write queries or reports against the warehouse today?"

Problem:

  • "What happens when leadership asks for a report that crosses multiple source systems?"
  • "How long does it take to onboard a new data source into the warehouse?"

Implication:

  • "When route optimization decisions are delayed because data isn't ready, what's the cost per day in fuel and driver hours?"
  • "If the warehouse goes down during peak shipping season, what's the operational impact?"

Need-payoff:

  • "If your operations team had real-time visibility into shipment status across all carriers, how would that change your customer SLA performance?"
  • "What would it mean for the business if you could add a new data source in days instead of months?"

平台分布

Codex

35.09%
按下载量换算35

Claude

30.99%
按下载量换算31

Cursor

20.31%
按下载量换算20

Gemini CLI

9.87%
按下载量换算10

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