GPT Sherpa

Claude Code setup guides, CLAUDE.md templates, Quarto authoring patterns, and reusable LLM workflow skills for data scientists and engineers.

Production-tested LLM workflow patterns

GPT Sherpa is a field notebook for data scientists and software engineers using LLMs on real projects: Claude Code setup, CLAUDE.md control files, Quarto authoring workflows, and copyable skills that make AI-assisted work more reliable.

Not prompt hacks. Not vendor docs. These are practical patterns that survived real work, then got cleaned up so you can reuse them.

Latest advice

New — The rubric is the new prompt (June 2026)

The biggest change in the AI tooling landscape this year is not a model. It is a shift in what the tools accept as input: not just a task, but a definition of done — and a harness that iterates against it without you. Claude’s Outcomes and /goal, Grok Build’s plan approval, and Fable 5’s spec-up-front design all reward the same skill: writing success criteria a grader can actually check.

Read the full post → · Browse all advice →

Choose your starting point

I am setting up Claude Code

Install the CLI, configure permissions, and add your first custom skill without guessing which defaults matter.

Use the setup guide →

I already use Claude Code

Give the model durable project memory with a CLAUDE.md file. Start from a template, then refine the instructions as the project grows.

Copy the CLAUDE.md template →

I write with Quarto

Use LLMs to author Quarto documents while keeping execution control, cross-references, citations, and reproducible outputs intact.

Open the Quarto authoring skill →

I use Grok Build with agents & pipelines

Pair Claude’s agents with Grok Build subagents, todos, and provenance-first DAG patterns — cross-vendor review under the same CLAUDE.md rules, with explicit data-design registries and validation gates.

Explore Grok Build subagents & provenance →

What you can copy

Claude Code workflows

Quarto and publishing patterns

Data and review skills

  • Data profiling — inspect data before asking an LLM to explain or model it.
  • AskSage review — package multi-model review into a repeatable workflow.
  • Tidymodels — capture modeling conventions in a reusable skill.
  • Rhino + Shiny — guide LLM-assisted work in a structured Shiny application.

Regulated and knowledge-work patterns

  • PHI scanning — make sensitive-data review an explicit step instead of an afterthought.
  • Knowledge vault pattern — organize reusable project context so models can retrieve the right background.
  • Knowledge vault skill — the drop-in skill version of the pattern.
  • txtarchive — work with archived text in a way that stays inspectable.

Grok Build workflows (xAI)

  • Grok Build subagents & provenance — cross-vendor review of agentic work on real targets DAGs using explicit data-design registries, validation gates, and provenance tracking.
  • Use Grok Build’s typed subagents (spawn_subagent, worktree-isolated) + todo_write for parallel verification when Claude Code does the hands-on work.
  • Grok Build reads the same CLAUDE.md / .claude/ rules with zero configuration, so all existing patterns (knowledge vault, PHI scanning, etc.) transfer directly.

Advice — opinionated, dated, one idea each

Why this exists

LLM-assisted work breaks down when the model has no project context, no operating rules, and no way to tell exploratory notes from production constraints. GPT Sherpa treats those pieces as part of the workflow: write the control document, name the assumptions, keep reusable patterns close, and make the next run better than the last one.

The result is not a magic prompt. It is a small operating system for using LLMs with code, data, and technical writing.

Useful first files


Source: llmcheatsheets on GitHub. Licensed for reuse under the repository terms.