> ## Documentation Index
> Fetch the complete documentation index at: https://jacobpevans-docs-reusable-workflow-main-pin.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# AI Development

> Multi-model AI coding pipeline. Claude, Gemini, Copilot, and local MLX models each doing what they're best at.

> File an issue, grab coffee, come back to a PR. Not quite there yet — but close enough to be dangerous.

The AI development surface is opinionated, not magical. Each model has a sweet spot. Each tool has a role. Universal configuration lives in one place so every IDE, every agent, every CLI reads the same rules.

## The tools landscape

| Layer                | Repo / tool                                                                                                               | What it owns                                                                      |
| -------------------- | ------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------- |
| **Universal config** | [Assistant rules](/ai-development/ai-assistant-instructions)                                                              | `CLAUDE.md`, `AGENTS.md`, rules, permissions, workflows — read by every AI tool   |
| **Cloud models**     | Claude Code, Gemini CLI, GitHub Copilot                                                                                   | The IDEs and CLIs that do the work                                                |
| **Local inference**  | MLX                                                                                                                       | Apple Silicon-native model inference for typo fixes, quick edits, no cloud tokens |
| **Extensions**       | [Claude Code plugins](/ai-development/claude-code-plugins), `claude-code-routines`, `ai-workflows`, `raycast-smart-issue` | Commands, scheduled agents, Copilot workflows, Raycast UI on top of MLX           |

## Model routing

* **Claude** — multi-file refactors, deep reasoning, agentic loops. Default for non-trivial work.
* **Gemini** — second opinions, code review, broad context.
* **GitHub Copilot** — line-level completions inside the editor. Cheap for high-volume routine work.
* **Local MLX** — typo fixes, quick edits, anything where burning cloud tokens makes no sense.

Routing rules live in `~/CLAUDE.md` and `AGENTS.md`, sourced from [ai-assistant-instructions](https://github.com/JacobPEvans/ai-assistant-instructions). See [Repo boundaries](/ai-development/repo-boundaries) for how rules, plugins, and docs are split across three repositories.

## Repos in this section

<CardGroup cols={2}>
  <Card title="Repo boundaries" icon="border-all" href="/ai-development/repo-boundaries">
    How rules, plugins, and docs are split across three repositories.
  </Card>

  <Card title="ai-assistant-instructions" icon="book" href="/ai-development/ai-assistant-instructions">
    Universal AI configuration layer. Rules, permissions, workflows, agents. Loaded by every AI tool.
  </Card>

  <Card title="claude-code-plugins" icon="plug" href="/ai-development/claude-code-plugins">
    Commands, skills, hooks, agents for Claude Code. Project-specific automation.
  </Card>

  <Card title="claude-code-routines" icon="clock" href="https://github.com/JacobPEvans/claude-code-routines">
    Scheduled remote-agent routines on Claude.ai. Cron-driven Claude tasks for GitHub ops.
  </Card>

  <Card title="ai-workflows" icon="github" href="https://github.com/JacobPEvans/ai-workflows">
    Reusable GitHub Copilot agentic workflows. Repo-level agent recipes.
  </Card>

  <Card title="raycast-smart-issue" icon="bolt" href="https://github.com/JacobPEvans/raycast-smart-issue">
    Raycast extension. AI-drafted GitHub issues via a local MLX model.
  </Card>

  <Card title="nix-ai" icon="snowflake" href="/nix/nix-ai">
    The Nix package layer that ships every AI CLI to your shell.
  </Card>
</CardGroup>

See [AI development pipeline](/architecture/ai-pipeline) for how these fit into the issue → PR → ship flow.