Glue Diagnostics

What it does

When your agent uses it

• Investigate and troubleshoot AWS Glue problems by analyzing ETL jobs
• DPU utilization
• Spark execution
• Job bookmarks following structured runbooks

Example prompts

• “/glue-diagnostics”

Requirements

• Python 3
• Compatibility (from SKILL.md): Requires AWS CLI or SDK access with Glue, S3, CloudWatch Logs, IAM, EC2 (for VPC/connections), and optionally KMS permissions.

Workflow steps

2 steps, taken from the step headings in SKILL.md.

1. 1Collect and triage
2. 2Domain deep dive

What it can do on your machine

Read from SKILL.md and the folder at commit ff51758. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • aws

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use aws, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Requires AWS CLI or SDK access with Glue, S3, CloudWatch Logs, IAM, EC2 (for VPC/connections), and optionally KMS permissions.

  From compatibility in the SKILL.md frontmatter.

Context cost

Glue Diagnostics loads about 2k tokens when it runs, and up to ~38k if it reads all its reference files. Until then it costs about 200 tokens; SKILL.md has 753 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~200

When it runs · the whole SKILL.md, loaded when a task matches

~2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~38k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Kilo-Org/kilo-marketplace at commit ff51758, republished under its MIT licence (© Kilo-Org). 753 words, ~1,985 tokens.

name

glue-diagnostics

description

Use this skill to investigate and troubleshoot AWS Glue problems by analyzing ETL jobs, crawlers, connections, Data Catalog, DPU utilization, Spark execution, and job bookmarks following structured runbooks. Activate when: job failures, job timeouts, OOM errors, Spark executor or driver crashes, crawler failures, schema detection issues, partition problems, JDBC connection failures, VPC/subnet connectivity, S3 endpoint access, Data Catalog sync issues, schema evolution conflicts, DPU sizing problems, shuffle bottlenecks, data skew, transformation errors, bookmark issues, data quality failures, IAM permission errors, encryption problems, Glue Studio visual editor errors, job generation failures, or the user says something is wrong with Glue without naming specific symptoms.

compatibility

Requires AWS CLI or SDK access with Glue, S3, CloudWatch Logs, IAM, EC2 (for VPC/connections), and optionally KMS permissions.

metadata.category

data

aws glue get-job --name <job-name>
aws glue get-job-run --job-name <job-name> --run-id <run-id>
aws glue batch-get-jobs --job-names <job1> <job2>
aws glue get-crawler --name <crawler-name>
aws glue get-connection --name <connection-name>
aws logs filter-log-events --log-group-name /aws-glue/jobs/logs-v2 --log-stream-name-prefix <run-id>

aws glue get-job-runs --job-name <job-name> --max-results 10
aws glue get-crawler-metrics --crawler-name-list <crawler-name>
aws glue get-databases
aws glue get-tables --database-name <db-name>
aws glue get-partitions --database-name <db-name> --table-name <table-name>
aws glue get-job-bookmark --job-name <job-name>
aws cloudwatch get-metric-statistics --namespace Glue --metric-name glue.driver.aggregate.bytesRead --dimensions Name=JobName,Value=<job-name> --start-time <iso> --end-time <iso> --period 300 --statistics Sum

© Kilo-Org, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 27 other files (references) in skills/glue-diagnostics of Kilo-Org/kilo-marketplace.

• SKILL.md
• LICENSE
• README.md
• references/A1-job-failures.md
• references/A2-job-timeout.md
• references/A3-oom-errors.md
• references/A4-spark-errors.md
• references/B1-crawler-failures.md
• references/B2-schema-detection.md
• references/B3-partition-issues.md
• references/C1-jdbc-connection-failures.md
• references/C2-vpc-subnet-issues.md
• references/C3-s3-endpoint-access.md
• references/D1-catalog-sync-issues.md
• references/D2-schema-evolution.md
• references/E1-dpu-sizing.md
• references/E2-shuffle-issues.md
• references/E3-data-skew.md
• references/F1-transformation-errors.md
• references/F2-bookmark-issues.md
• … and 8 more

Open the folder on GitHubat commit ff51758