View original page

Troubleshoot Spark Job

DevOps & Infrastructure

Diagnoses and fixes failed or slow Apache Spark workloads on AWS Glue, EMR on EC2, EMR Serverless, and EMR on EKS with the analyze_spark_workload MCP tool, which provides deeper analysis than the AWS job run APIs alone. Analyzes job failures, performance issues, and error stack traces, and generates code fix recommendations as a follow-up only when the diagnosis identifies a code-level fix. Applies to requests such as: spark job failed, glue job error, emr job failing, emr on eks job failed, spark out of memory, spark job slow, debug spark, spark exception, analyze spark failure, spark job stuck, spark job troubleshoot. Not intended for upgrading Spark versions, creating new Spark jobs, or general cluster management.

Publisher / source

aws/agent-toolkit-for-aws (found on skills.sh)

Upstream record

aws/agent-toolkit-for-aws

Version

Version 1

Published

2026-11-19

Publication review

Approved for publication

Content fingerprint

8bba9a3fbcaf28903aa1cc99f0c304b38e1c0d804ad19ee00bdaa00752f17f42

Review before you use it

Publication approval is a recorded review state, not a guarantee of safe execution. Check the upstream license, required tools and permissions, and test in your intended client.

Sign in to inspect the full instructions and download the SKILL.md file. This public page contains metadata only.

Open skill in your workspace


Source: https://prompeteer.ai/skills-hub/f536e19a-7f2e-4b6f-9ec0-9d7436e21a3f