Add AI-assisted contribution and review policy (#1603)

Author: brendancol

CONTRIBUTING.md

@@ -43,6 +43,43 @@ In order to avoid duplication of effort, it's always a good idea to comment on a
 8. We will review your PR as time permits. Reviewers may comment on your contributions, ask you questions regarding the implementation or request changes. If changes are requested, push new commits to the existing branch. Do *NOT* rebase, amend, or cherry-pick published commits. Any of those actions will make us start the review from scratch. If you need updates from `main`, just merge it into your branch.
 
 
+### AI-Assisted Contribution and Review
+
+xarray-spatial welcomes responsible AI-assisted development and review when it helps contributors move faster, improve quality, and reduce maintainer burden. The project has limited dedicated development capacity, so contributors are encouraged to use AI tools for testing, debugging, feature work, documentation, deployment, and release preparation.
+
+Attribution and responsibility belong to human contributors. Do not add AI tools, coding agents, or AI companies as commit authors, co-authors, reviewers, or attribution lines in commits, pull requests, changelogs, or release notes.
+
+Please avoid attribution such as:
+
+    Co-authored-by: Claude <...>
+    Co-authored-by: ChatGPT <...>
+    Generated with Claude Code
+    Generated by Copilot
+    Reviewed-by: <AI tool>
+
+If AI-assisted code introduces a bug, security issue, regression, or incorrect behavior, the responsible party is the human contributor who submitted and reviewed the change. AI tools may assist the work, but they do not own the work.
+
+#### Review Expectations
+
+Before submitting a pull request, contributors should review and use the relevant commands in:
+
+    .claude/commands/
+
+These command markdown files reflect current project expectations for performance, accuracy, security, testing, maintainability, deployment, and release readiness. New contributors should read through them to understand the project's quality standards.
+
+Contributors who do not use Claude Code can adapt the command markdown files into prompts or checklists for their preferred AI tools and review workflows. The important part is the quality review they represent, not the specific tool used to run them.
+
+Where applicable, run the relevant sweep or review commands before requesting maintainer review. If a command flags an issue, either address it or clearly explain why it is acceptable for the current change.
+
+Copilot code review may run on pull requests as automated review assistance. Its feedback is useful, but it does not replace human responsibility or maintainer judgment.
+
+#### Current Priority
+
+The next sprint is focused on stabilizing xarray-spatial for its first major release. Contributors should prioritize bug fixes, reliability, tests, release blockers, and performance, accuracy, or security issues. New features should avoid adding significant release risk unless they are essential.
+
+The preferred contribution style is fast, careful, and human-accountable: use AI aggressively to improve velocity and quality, but keep ownership and attribution with the people contributing to the project.
+
+
 ### Attribution
 
 Portions of text derived from [Bokeh CONTRIBUTING file]: (https://github.com/bokeh/bokeh/blob/branch-3.4/.github/CONTRIBUTING.md)