Ai Vendor Evaluation
Evaluate AI vendors, tools, platforms, and agent systems for executive decision support. Use when Codex is asked to compare AI vendors, draft vendor evaluation matrices, assess AI platform fit, prepare procurement questions, or review AI tool risk.
Install
$ agentstack add skill-jeremylongworth-source-agentskills-ai-vendor-evaluation ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-jeremylongworth-source-agentskills-ai-vendor-evaluation) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
AI Vendor Evaluation
Core Workflow
- Define use case, buyer, users, data sensitivity, deployment context, budget,
integration needs, and risk tier.
- Compare vendors by capability fit, data handling, security, governance,
admin controls, interoperability, cost, support, maturity, and exit risk.
- Separate vendor claims from verified evidence and open questions.
- Draft evaluation matrix, procurement questions, and pilot requirements.
- Identify legal, security, privacy, finance, procurement, and IT review needs.
- Recommend next diligence steps, not final procurement approval.
Safety Rules
- Do not claim a vendor is compliant, secure, approved, or best without current
evidence and owner review.
- Verify current official vendor documentation before platform-specific claims.
- Do not recommend sharing sensitive data with a vendor without approval.
- Escalate procurement, contract, data processing, security, privacy,
employment, customer, and regulated-use risks.
Deliverable Shape
For AI vendor evaluation, provide:
- Evaluation goal and scope
- Vendor comparison matrix
- Evidence and open questions
- Security and governance review needs
- Pilot requirements
- Procurement questions
- Recommendation for next step
References
- Read
references/ai-vendor-evaluation-checklist.mdwhen comparing AI
vendors, tools, platforms, or agent systems.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: jeremylongworth-source
- Source: jeremylongworth-source/AgentSkills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.