# hybrid

> Use this tool when you need to integrate large language model (LLM) judgment with deterministic code in a cyclical process to solve complex problems, such as diagnosing biases or discovering schemas. It takes in LLM outputs and code inputs, and produces calibrated and audited results through a mutually-constraining cycle. Ideal for use cases requiring iterative refinement and validation, such as AI model development and testing.

Canonical page: https://skillsregistry.net/skills/justinstimatze-hybrid  
JSON: https://api.skillsregistry.net/v1/skills/justinstimatze-hybrid

## Description

Design pattern + Claude Code skill for AI engineers. LLM judgment and deterministic code in mutually-generative cycles, not pipelines. Library of named graph-shapes (RAG, ReAct, codegen-with-verification, dev-time critique loops, more).

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** devops-ci
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/justinstimatze/hybrid)

## 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": "justinstimatze-hybrid"
    }
  }
}
```

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