Link the Data Contract Skills for coding agents

README.md

@@ -24,7 +24,7 @@ It can be used as a standalone CLI tool, in a CI/CD pipeline, or directly as a P
 >
 > Quick links: [Quickstart](https://docs.datacontract.com/quickstart) · [Commands](https://docs.datacontract.com/commands) · [Best Practices](https://docs.datacontract.com/best-practices) · [Custom Export and Import](https://docs.datacontract.com/extending) · [Release Notes](https://docs.datacontract.com/release-notes) · [Development Setup](#development-setup)
 >
-> For LLMs: [docs.datacontract.com/llms.txt](https://docs.datacontract.com/llms.txt) · [docs.datacontract.com/llms-full.txt](https://docs.datacontract.com/llms-full.txt)
+> For LLMs: [docs.datacontract.com/llms.txt](https://docs.datacontract.com/llms.txt) · [docs.datacontract.com/llms-full.txt](https://docs.datacontract.com/llms-full.txt) · [Data Contract Skills](https://github.com/datacontract/datacontract-skills) for coding agents
 
 ## Getting started
 
@@ -185,6 +185,7 @@ if not run.has_passed():
 ## How to
 
 - [How to integrate Data Contract CLI in your CI/CD pipeline as a GitHub Action](https://github.com/datacontract/datacontract-action/)
+- [How to let your coding agent (Claude Code, Codex, GitHub Copilot) create and test data contracts with the Data Contract Skills](https://github.com/datacontract/datacontract-skills)
 - [How to run the Data Contract CLI API to test data contracts with POST requests](https://docs.datacontract.com/api)
 - [How to run Data Contract CLI in a Databricks pipeline](https://www.datamesh-architecture.com/howto/build-a-dataproduct-with-databricks#test-the-data-product)
 

docs/docs/ai-agents.md

@@ -0,0 +1,59 @@
+---
+sidebar_position: 14
+title: "Use with AI Coding Agents"
+description: "Let Claude Code, Codex, GitHub Copilot, and other coding agents create, test, and evolve data contracts with the Data Contract Skills."
+---
+
+# Use with AI Coding Agents
+
+The [Data Contract Skills](https://github.com/datacontract/datacontract-skills) teach coding agents such as Claude Code, OpenAI Codex, and GitHub Copilot CLI to work with data contracts. The agent uses the Data Contract CLI and the [Data Contract Editor](./editor.md) under the hood: it imports schemas, writes descriptions and quality rules, lints until the contract is valid, runs the tests, and explains failing checks.
+
+| Skill | What the agent does |
+|---|---|
+| Create a Data Contract | Imports a contract from a table, DDL, dbt, Avro, JSON Schema, or Excel, or writes it from requirements, then enriches and lints it. |
+| Test a Data Contract | Sets up the connection, runs `datacontract test`, and finds the cause of every failing check. |
+| Quality Rules | Adds quality rules and service levels per quality dimension, with thresholds grounded in the data. |
+| Breaking Change Check | Runs `changelog` and `breaking` on a changed contract, adds semantic changes, and proposes the version bump. |
+| Export a Data Contract | Generates SQL DDL, dbt models and tests, schemas, and model classes, and integrates them into the project. |
+| Data Contracts in CI/CD | Sets up lint and breaking-change checks on pull requests and scheduled data tests. |
+| Data Contract Editor | Opens the contract in the visual editor while the agent edits the YAML. |
+
+## Install
+
+Claude Code:
+
+```bash
+claude plugin marketplace add https://github.com/datacontract/datacontract-skills
+claude plugin install datacontract-skills@datacontract-skills
+```
+
+OpenAI Codex:
+
+```bash
+codex plugin marketplace add https://github.com/datacontract/datacontract-skills
+codex plugin add datacontract-skills@datacontract-skills
+```
+
+GitHub Copilot CLI:
+
+```bash
+copilot plugin marketplace add https://github.com/datacontract/datacontract-skills
+copilot plugin install datacontract-skills@datacontract-skills
+```
+
+Other agents that support [Agent Skills](https://agentskills.io) can use the `skills/` folder of the repository directly, or reference its `AGENTS.md`.
+
+## Usage
+
+Ask in plain language:
+
+- "Create a data contract for the `orders` table in Snowflake."
+- "Test the orders contract against production and tell me why it fails."
+- "Is my change to the orders contract breaking?"
+- "Generate the dbt models and tests from the contract."
+
+The skills ask before connecting to a data source and never ask for credentials in the chat: set them as [environment variables](./configuration.md) or in a `.env` file.
+
+## Documentation for LLMs
+
+Agents without the skills can still read this documentation in a compact form: [llms.txt](https://docs.datacontract.com/llms.txt) (a link index) and [llms-full.txt](https://docs.datacontract.com/llms-full.txt) (every page in one file).

docs/docs/editor.md

@@ -74,3 +74,5 @@ datacontract edit datacontract.yaml
 ```
 
 See the [`edit` command reference](./commands/edit.md) for the full signature.
+
+To let a coding agent edit the YAML while you review it in the editor, see [Use with AI Coding Agents](./ai-agents.md).

docs/docs/intro.md

@@ -67,6 +67,7 @@ When you run `datacontract test`, the CLI connects to a data source and runs sch
 - Test your own warehouse in 5 minutes: **[Snowflake](./testing/snowflake.md)**, **[BigQuery](./testing/bigquery.md)**, **[Databricks](./testing/databricks.md)**, **[Amazon Redshift](./testing/redshift.md)**, or **[any other source](./testing/index.md)**.
 - Learn the underlying format in **[Open Data Contract Standard](./open-data-contract-standard.md)**.
 - Author contracts visually with the **[Data Contract Editor](./editor.md)**.
+- Let your coding agent (Claude Code, Codex, GitHub Copilot) create and test contracts with the **[Data Contract Skills](./ai-agents.md)**.
 - Run checks against real data with **[Test your Data](./testing/index.md)**, then keep them running with **[Scheduling](./scheduling/index.md)**.
 - Roll it out across a team with **[Adopting Data Contracts](./best-practices.md)**.
 - See every command in the **[Commands reference](./commands/index.md)**.
@@ -104,3 +105,4 @@ More answers — credentials, check selection, type failures, CI behaviour — a
 - Source code: [github.com/datacontract/datacontract-cli](https://github.com/datacontract/datacontract-cli)
 - Community Slack: [datacontract.com/slack](https://datacontract.com/slack)
 - GitHub Action: [datacontract/datacontract-action](https://github.com/datacontract/datacontract-action/)
+- Agent skills: [datacontract/datacontract-skills](https://github.com/datacontract/datacontract-skills)

docs/docusaurus.config.ts

@@ -169,6 +169,7 @@ const config: Config = {
           'scheduling/*.md',
           'dbt.md',
           'editor.md',
+          'ai-agents.md',
           'imports/index.md',
           'imports/*.md',
           'exports/index.md',
@@ -287,6 +288,7 @@ const config: Config = {
           items: [
             { label: 'datacontract.com', href: 'https://datacontract.com' },
             { label: 'Data Contract Editor', href: 'https://editor.datacontract.com' },
+            { label: 'Data Contract Skills', href: 'https://github.com/datacontract/datacontract-skills' },
             { label: 'PyPI', href: 'https://pypi.org/project/datacontract-cli/' },
           ],
         },

llms.txt

@@ -30,6 +30,7 @@ This page is the entry point for the project's GitHub repository and README. The
 - [PyPI package](https://pypi.org/project/datacontract-cli/): released versions and install instructions.
 - [Docker image](https://hub.docker.com/r/datacontract/cli): `datacontract/cli`.
 - [GitHub Action](https://github.com/datacontract/datacontract-action/): running the CLI in a GitHub workflow.
+- [Data Contract Skills](https://github.com/datacontract/datacontract-skills): agent skills for Claude Code, Codex, and GitHub Copilot to create, test, and evolve data contracts with the CLI.
 - [Community Slack](https://datacontract.com/slack): questions and discussion.
 
 ## Optional