/ 目录 / 演练场 / buyer-eval-skill
← 全部服务器 ↗ GitHub
● 社区 salespeak-ai ⚡ 即开即用

buyer-eval-skill

作者 salespeak-ai · salespeak-ai/buyer-eval-skill

B2B vendor evaluation skill — domain-expert questions, evidence-based scoring, and structured vendor interviews.

buyer-eval-skill makes Claude your B2B procurement lead: it asks domain-expert questions of the vendor (or their AI agent), records evidence against your evaluation rubric, scores each criterion, and produces a comparison matrix when you're evaluating multiple vendors. Reduces the time from 'let's look at vendors' to 'here's my recommendation with receipts'.

▶ 观看演示 📦 安装 💡 使用场景

为什么要用

核心特性

实时演示

实际使用效果

buyer-eval-skill.replay ▶ 就绪
0/0

安装

选择你的客户端

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "buyer-eval-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/salespeak-ai/buyer-eval-skill",
        "~/.claude/skills/buyer-eval-skill"
      ],
      "_inferred": true
    }
  }
}

打开 Claude Desktop → Settings → Developer → Edit Config。保存后重启应用。

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "buyer-eval-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/salespeak-ai/buyer-eval-skill",
        "~/.claude/skills/buyer-eval-skill"
      ],
      "_inferred": true
    }
  }
}

Cursor 使用与 Claude Desktop 相同的 mcpServers 格式。项目级配置优先于全局。

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "buyer-eval-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/salespeak-ai/buyer-eval-skill",
        "~/.claude/skills/buyer-eval-skill"
      ],
      "_inferred": true
    }
  }
}

点击 Cline 侧栏中的 MCP Servers 图标，然后选 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "buyer-eval-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/salespeak-ai/buyer-eval-skill",
        "~/.claude/skills/buyer-eval-skill"
      ],
      "_inferred": true
    }
  }
}

格式与 Claude Desktop 相同。重启 Windsurf 生效。

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "buyer-eval-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/salespeak-ai/buyer-eval-skill",
        "~/.claude/skills/buyer-eval-skill"
      ]
    }
  ]
}

Continue 使用服务器对象数组，而非映射。

~/.config/zed/settings.json
{
  "context_servers": {
    "buyer-eval-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/salespeak-ai/buyer-eval-skill",
          "~/.claude/skills/buyer-eval-skill"
        ]
      }
    }
  }
}

加入 context_servers。Zed 保存后热重载。

claude mcp add buyer-eval-skill -- git clone https://github.com/salespeak-ai/buyer-eval-skill ~/.claude/skills/buyer-eval-skill

一行命令搞定。用 claude mcp list 验证，claude mcp remove 卸载。

使用场景

实战用法： buyer-eval-skill

How to evaluate three SaaS vendors against your requirements

👤 Buyers, RevOps, procurement leads ⏱ ~120 min intermediate

何时使用： You've shortlisted 3 vendors and need to pick one defensibly.

前置条件
  • Skill cloned — git clone https://github.com/salespeak-ai/buyer-eval-skill ~/.claude/skills/buyer-eval-skill
步骤
  1. Define the rubric
    We're buying a customer support platform. Propose a weighted rubric (feature depth, integrations, price, security, support).✓ 已复制
    → Weighted criteria with rationale
  2. Interview each vendor
    Use the skill's question bank to interview vendor A. Their docs / AI agent is at <url>. Record evidence per criterion.✓ 已复制
    → Per-criterion evidence snippets with sources
  3. Score and compare
    Score all three and produce a comparison matrix with a recommendation.✓ 已复制
    → Matrix + recommendation + named risks

结果： A defensible vendor pick with evidence, not vibes.

注意事项
  • Rubric favors the vendor you already like — Lock the rubric before seeing demos
  • Evidence is just vendor marketing claims — Weight third-party sources (docs, G2, case studies) over marketing
搭配使用： filesystem

Compare RFP responses against your requirements

👤 Procurement teams drowning in RFP responses ⏱ ~90 min intermediate

何时使用： You sent an RFP, got 5 responses, and need to rank them.

步骤
  1. Load the responses
    Here are 5 RFP response PDFs in rfp/. Extract answers per requirement.✓ 已复制
    → Per-requirement matrix
  2. Flag gaps and fluff
    Where did a vendor answer the wrong question or punt? Flag fluff.✓ 已复制
    → Honest read of each response
  3. Rank
    Rank the responses and write a short memo for the evaluation committee.✓ 已复制
    → Ranked memo

结果： A fair, fast RFP review.

注意事项
  • Rewarding the best-written response over the best fit — Score on substance; penalize fluff

组合

与其他 MCP 搭配，撬动十倍杠杆

buyer-eval-skill + filesystem

Read PDFs/docs from a local folder during evaluation

Read rfp/responses/ and extract answers per requirement.✓ 已复制
buyer-eval-skill + google-ai-mode-skill

Cross-check vendor claims against public info

For each vendor claim that isn't in their docs, run a quick web check.✓ 已复制

工具

此 MCP 暴露的能力

工具输入参数何时调用成本
rubric-design domain + must-haves Start of any evaluation 0
vendor-interview vendor source (docs/AI agent) Per vendor 0
scoring-and-matrix evidence per vendor + rubric After interviews 0
recommendation-memo matrix Final step 0

成本与限制

运行它的成本

API 配额
none beyond LLM
每次调用 Token 数
10–40k per full eval
费用
free
提示
Interview one vendor at a time — keeps context focused and evidence clean

安全

权限、密钥、影响范围

凭据存储： none
数据出站： only if the skill calls out to vendor agents you point it at

故障排查

常见错误与修复

Evidence is shallow

Point Claude at primary docs; fallback to published case studies

Scores feel gamed

Re-lock the rubric and re-run scoring blind to vendor identity if possible

替代方案

buyer-eval-skill 对比其他方案

替代方案何时用它替代权衡
creative-director-skillEvaluating creative concepts, not B2B softwareDifferent judgment domain

更多

资源

📖 阅读 GitHub 上的官方 README

🐙 查看未解决的 issue

🔍 浏览全部 400+ MCP 服务器和 Skills