/ Directory / Playground / buyer-eval-skill
← All servers ↗ GitHub
● Community salespeak-ai ⚡ Instant

buyer-eval-skill

by 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'.

▶ Watch demo 📦 Install 💡 Use Cases

Why use it

Key features

Live Demo

What it looks like in practice

buyer-eval-skill.replay ▶ ready
0/0

Install

Pick your client

~/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
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.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 uses the same mcpServers schema as Claude Desktop. Project config wins over global.

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
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "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
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.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 uses an array of server objects rather than a map.

~/.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"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

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

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use buyer-eval-skill

How to evaluate three SaaS vendors against your requirements

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

When to use: You've shortlisted 3 vendors and need to pick one defensibly.

Prerequisites
  • Skill cloned — git clone https://github.com/salespeak-ai/buyer-eval-skill ~/.claude/skills/buyer-eval-skill
Flow
  1. Define the rubric
    We're buying a customer support platform. Propose a weighted rubric (feature depth, integrations, price, security, support).✓ Copied
    → 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.✓ Copied
    → Per-criterion evidence snippets with sources
  3. Score and compare
    Score all three and produce a comparison matrix with a recommendation.✓ Copied
    → Matrix + recommendation + named risks

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

Pitfalls
  • 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
Combine with: filesystem

Compare RFP responses against your requirements

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

When to use: You sent an RFP, got 5 responses, and need to rank them.

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

Outcome: A fair, fast RFP review.

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

Combinations

Pair with other MCPs for X10 leverage

buyer-eval-skill + filesystem

Read PDFs/docs from a local folder during evaluation

Read rfp/responses/ and extract answers per requirement.✓ Copied
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.✓ Copied

Tools

What this MCP exposes

ToolInputsWhen to callCost
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

Cost & Limits

What this costs to run

API quota
none beyond LLM
Tokens per call
10–40k per full eval
Monetary
free
Tip
Interview one vendor at a time — keeps context focused and evidence clean

Security

Permissions, secrets, blast radius

Credential storage: none
Data egress: only if the skill calls out to vendor agents you point it at

Troubleshooting

Common errors and fixes

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

Alternatives

buyer-eval-skill vs others

AlternativeWhen to use it insteadTradeoff
creative-director-skillEvaluating creative concepts, not B2B softwareDifferent judgment domain

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills