Conversation
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
There was a problem hiding this comment.
main, but PRs should target staged.
The main branch is auto-published from staged and should not receive direct PRs.
Please close this PR and re-open it against the staged branch.
You can change the base branch using the Edit button at the top of this PR,
or run: gh pr edit 1346 --base staged
There was a problem hiding this comment.
Pull request overview
Adds a new custom agent focused on reviewing PySpark code for distributed performance bottlenecks, and registers it in the agents catalog so it’s discoverable and installable.
Changes:
- Introduces
spark-performance.agent.md, a PySpark performance & parallelism reviewer agent with a structured review/reporting format. - Adds the new agent entry to
docs/README.agents.md(including VS Code install links).
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 8 comments.
| File | Description |
|---|---|
| docs/README.agents.md | Adds the new “PySpark Expert Agent” row to the agents table with install links. |
| agents/spark-performance.agent.md | Defines the new PySpark performance reviewer agent behavior, output contract, and report template. |
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
🔍 Skill Validator Results2 resource(s) checked | ✅ All checks passed Full output
|
|
@copilot apply changes based on the comments in this thread |
Pull Request Checklist
npm startand verified thatREADME.mdis up to date.stagedbranch for this pull request.Description
A specialized PySpark performance reviewer that analyzes distributed workloads to identify execution bottlenecks, parallelism issues, and inefficient transformations. It recommends Spark‑native optimizations and scalable alternatives to RDD or row‑level Python logic for improved distributed executions.
Type of Contribution
Additional Notes
The agent can work with any code which is attached and creates a file with the findings and categorize them as critical ,high, medium or low severity.
By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.