# ComputeSage StackBench

> ComputeSage StackBench — com-computesage-stackbench. Use this tool when you need to evaluate and optimize the performance of GPU and Large Language Model (LLM) inference workloads. It provides benchmarks, hardware evidence, and deployment recommendations to inform launch configurations and improve overall efficiency. Ideal for use cases requiring data-driven decisions on hardware and software configurations for AI model deployment.

Canonical page: https://skillsregistry.net/skills/com-computesage-stackbench  
JSON: https://api.skillsregistry.net/v1/skills/com-computesage-stackbench

## Description

Evidence-led private AI deployment intelligence with public evidence and accountless planning.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 0.2.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Updated:** 2026-09-01

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/com.computesage%2Fstackbench)

## Use it

MCP endpoint published by the skill: `https://mcp.computesage.com/mcp`

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "com-computesage-stackbench"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/com-computesage-stackbench` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/com-computesage-stackbench/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt