buyer-eval-skill

A free open-source Claude skill that evaluates B2B software vendors by prompting for buyer context, conducting domain-expert question exchanges, optionally engaging vendor AI agents via the Salespeak Frontdoor API, cross-referencing claims against independent sources, and producing a comparative, evidence-tagged scorecard plus risk analysis and demo-prep questions.

Evaluated Mar 30, 2026 (0d ago)
Repo ↗ Ai Ml ai-agent claude-skill b2b procurement vendor-evaluation evidence-tracking due-diligence
⚙ Agent Friendliness
33
/ 100
Can an agent use this?
🔒 Security
41
/ 100
Is it safe for agents?
⚡ Reliability
29
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
0
Documentation
35
Error Messages
0
Auth Simplicity
85
Rate Limits
10

🔒 Security

TLS Enforcement
60
Auth Strength
30
Scope Granularity
20
Dep. Hygiene
50
Secret Handling
50

End-user flow is described as not requiring an account or API key, but upstream authentication and how secrets are handled are not documented here. The skill performs outbound interactions (vendor AI agents) and cross-references claims; robust logging/privacy controls and data-handling details are not specified in the provided README.

⚡ Reliability

Uptime/SLA
0
Version Stability
55
Breaking Changes
40
Error Recovery
20
AF Security Reliability

Best When

You are evaluating multiple vendors in a B2B software category and want faster, evidence-tagged comparative analysis that distinguishes vendor-verified vs independent claims.

Avoid When

You need a strict, documented machine interface (OpenAPI/SDK) for deep automation, or you require guaranteed availability and well-defined reliability/SLA for automated runs.

Use Cases

  • Assist B2B buyers with vendor selection and due diligence
  • Generate structured, evidence-backed scorecards across common procurement dimensions
  • Surface hidden requirements via domain-expert/adversarial question flows
  • Prepare tailored questions for vendor demos based on identified gaps

Not For

  • Replacing legal/compliance reviews or contract negotiation
  • Automating final procurement decisions without human verification
  • Performing web-scale scraping where direct integrations are required

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
No
SDK
No
Webhooks
No

Authentication

Methods: Salespeak Frontdoor API (used internally by the skill for POST requests when available)
OAuth: No Scopes: No

README states 'No API key needed. No account needed' for end users of the Claude skill, but the skill itself may call the Salespeak Frontdoor API under the hood when company agents are available. Authentication details for that upstream API are not documented in the provided README.

Pricing

Free tier: Yes
Requires CC: No

Repository is described as free and open-source. No pricing for the upstream Salespeak API or any limits are stated in the provided content.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Upstream vendor-agent availability may vary (skill behavior differs when a vendor has a Salespeak Company Agent vs not).
  • End-user auth/controls for upstream calls are not described; agent outputs may depend on upstream response quality and coverage.
  • No documented interface contracts (tool schemas, retries, error codes) are provided in the README, which can complicate robust automation.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for buyer-eval-skill.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6533
Packages Evaluated
19870
Need Evaluation
586
Need Re-evaluation
Community Powered