# Claude Code Agent: Llm Architect

> Use when designing LLM systems for production, implementing fine-tuning or RAG architectures, optimizing inference serving infrastructure, or managing multi-model deployments. Spec

## Install

Save the content below to `.claude/skills/` or append to your `CLAUDE.md`:

# Claude Code Agent: Llm Architect

## Quick Use

```bash
npx claude-code-templates@latest --agent ai-specialists/llm-architect --yes
```

This installs the upstream agent definition into Claude Code. For Codex or another agent runtime, use the sections below as the activation brief and keep the upstream source URL attached for review.

## What This Agent Is For

Use when designing LLM systems for production, implementing fine-tuning or RAG architectures, optimizing inference serving infrastructure, or managing multi-model deployments. Specifically:\\n\\n\\nContext: A startup needs to deploy a custom LLM application with sub-200ms latency, fine-tuned on domain-specific data\\nuser: \"Design a production LLM architecture that supports our use case with sub-200ms P95 latency, includes fine-tuning capability, and optimizes for cost\"\\nassistant: \"I'll start by gathering your

Category: AI Specialists. Expected tool surface: Read, Write, Edit, Bash, WebSearch.

## Agent Activation Brief

Use this asset when a task needs a focused specialist for ai specialists work. Hand the agent a narrow objective, the relevant repository paths or inputs, and a concrete output contract. Ask it to cite changed files or evidence, avoid unrelated rewrites, and stop if required credentials, production access, or destructive actions are needed.

## Operating Boundaries

- Treat this as a specialist agent, not a general chat prompt.
- Keep write scope explicit before using it in a coding session.
- Run normal project tests or verification after accepting its output.
- Do not pass secrets into the agent instructions; configure credentials through the host runtime instead.

## Clean Source

- Source repository: https://github.com/davila7/claude-code-templates
- Source file: https://github.com/davila7/claude-code-templates/blob/main/cli-tool/components/agents/ai-specialists/llm-architect.md
- Source file SHA: `4ca678e5d42e5de47a42668d15014c085e5cce2d`
- Upstream body hash: `8a1595d870ff8dc6fe6eed910436e8587702df8f08698a91cae3d865bd9c4090`
- License: MIT
- Repository stars at publication check: 27403

## Source & Thanks

Created by the Claude Code Templates community and maintained in `davila7/claude-code-templates`. This TokRepo asset is a concise install and activation wrapper around the upstream MIT-licensed agent definition.

---
Source: https://tokrepo.com/en/workflows/claude-code-agent-llm-architect-019c1564
Author: TokRepo精选