# trinity-local

> Use this tool when you need to synthesize answers from multiple AI models, such as Claude, GPT, and Gemini, to get personalized responses based on your unique preferences. It solves the problem of relying on individual AI models or requiring API keys for access, allowing for local and private AI council execution. This tool takes in user input and AI model outputs, generating a unified response tailored to the user's taste lens.

Canonical page: https://skillsregistry.net/skills/keepwhatworks-trinity  
JSON: https://api.skillsregistry.net/v1/skills/keepwhatworks-trinity

## Description

Enables running AI councils across Claude, GPT, and Gemini, synthesizing answers based on your personal taste lens, all locally without an API key.

## Trust

- **Trust score (0–1):** 0.60
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** api-integration
- **Updated:** 2026-06-12

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/mf82mut344)
- **Repository:** <https://github.com/keepwhatworks/trinity>

## Use it

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": "keepwhatworks-trinity"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/keepwhatworks-trinity` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/keepwhatworks-trinity/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