Development with LLMs

Chalk provides specialized prompts to help Large Language Models (LLMs) write effective Chalk code. These prompts are designed to guide AI assistants in understanding Chalk’s patterns, best practices, and API conventions.

---

​

Getting started

1. Add the prompt to your local repository. If you use Claude Code or Codex, chalk init offers to add it, along with the Chalk MCP server and the agent skills. For other assistants, or to add only the prompt, run the chalk init agent-prompt command.
2. Provide specific context about your feature requirements.
3. Review generated code for adherence to your team’s conventions.
4. Test the generated features in your development environment.

These prompts encode Chalk’s conventions, so an assistant working from them produces more idiomatic Chalk code.

---

​

Agent prompts repository

The Chalk team maintains the public repository chalk-ai/agent-prompts with prompts specifically designed for LLM-assisted Chalk development:

This repository contains prompts that are tested against LLM providers to help them understand:

• Chalk’s feature definition patterns
• Built-in LLM integration capabilities
• Resolver implementation best practices
• Data source integration patterns
• Template interpolation syntax
• Model selection and configuration

---

​

Agent skills

Chalk publishes seven agent skills for specific tasks, alongside the general-purpose prompt above.

Install one with chalk install agent-skill, followed by a skill name from the table below:

chalk install agent-skill

In a terminal, run the command without a skill name to choose skills and coding agents from a list.

For example, this installs the chalk-notebooks skill for Claude Code:

chalk install agent-skill chalk-notebooks --claude

That writes the skill to .claude/skills/ in the current directory. Pass --global to install it at the user level instead, so it applies in every project. The same command serves other agents with --codex or --cursor, and --delete removes a skill you no longer want. chalk init installs every skill in the project for the coding agents you choose.

Skill	Use it for
writing-online-resolvers	Writing, refactoring, and debugging @online Python resolvers, including input and output signatures.
writing-static-chalkdf	Writing @online(static=True) resolvers with chalkdf, and porting pandas or numpy logic to static acceleration.
chalk-resolver-acceleration	Reducing feature-pipeline latency, and deciding whether to accelerate a Python resolver or migrate it to inline expressions.
chalk-streaming	Writing, testing, and tuning stream resolvers against Kafka, Kinesis, or PubSub.
migrating-features-to-chalk	Porting existing features into Chalk from dbt models, Airflow or Prefect pipelines, and Spark jobs.
chalk-sandboxes	Creating and operating sandboxes for one-off commands or long-running agent work, including host pool placement, lifetimes, network access, and failure diagnosis.
chalk-notebooks	Creating, running, and debugging Chalk Notebooks, including the CLI and installed dependencies.

Skills live alongside the prompts in that repository, under skills/.