Open Data Hub avatar

Open Data Hub

Official

@opendatahub-io

0Followers
|
219Public Repos
|
19Published Skills

Organization for Open Data Hub community

Skills Distribution
DomainDeveloper To...CI/CD Pipeline Dia.. (40%)Package Metadata A.. (30%)Model Evaluation F.. (30%)

Agent Skills by Open Data Hub

Showing 19 vetted skills indexed across 4 GitHub repositories.

opendatahub-ioopendatahub-io

pipeline-rca

Analyze trace logs, source code, and build artifacts to diagnose CI/CD pipeline failures.

Official
Advanced
opendatahub-ioopendatahub-io

pipeline-grouping

Group and deduplicate CI/CD pipeline failures using error files and Jira tickets.

Official
Intermediate
opendatahub-ioopendatahub-io
36

eval-analyze

Analyze a target skill to generate eval.yaml configuration for /eval-run.

Official
Advanced
opendatahub-ioopendatahub-io
36

eval-review

Analyze evaluation results to identify alignment gaps between automated checks and human assessment.

Official
Advanced
opendatahub-ioopendatahub-io
36

eval-setup

Configure and validate the agent-eval-harness environment with MLflow tracking and API key checks.

Official
Intermediate
opendatahub-ioopendatahub-io
36

eval-run

Execute skills against test cases, score outputs with judges, and generate run summaries.

Official
Advanced
opendatahub-ioopendatahub-io
36

eval-mlflow

Logs MLflow evaluation runs and syncs datasets bidirectionally with feedback.

Official
Advanced
opendatahub-ioopendatahub-io
36

eval-optimize

Analyze eval results and edit SKILL.md to fix judge failures.

Official
Advanced
opendatahub-ioopendatahub-io
36

eval-dataset

Generates evaluation test cases from eval.md and eval.yaml for /eval-run workflows.

Official
Advanced
opendatahub-ioopendatahub-io
2

lint-check

Create structured lint checks for the kubectl odh lint command.

Official
Intermediate
opendatahub-ioopendatahub-io
36

vLLM Slack Summary

Export vLLM CI Slack messages and convert them into markdown transcripts.

Official
Intermediate
opendatahub-ioopendatahub-io
36

license-finder

Identify Python package licenses from PyPI metadata and repository LICENSE files.

Official
Intermediate
opendatahub-ioopendatahub-io
36

upload-chat-log

Upload chat logs as Markdown files to JIRA tickets.

Official
Intermediate
opendatahub-ioopendatahub-io
36

pipeline-debugger

Fetch GitLab CI/CD pipeline and job statuses via the GitLab API.

Official
Intermediate
opendatahub-ioopendatahub-io
36

complexity

Analyze PyPI metadata to assess Python package build complexity and wheel strategies.

Official
Basic
opendatahub-ioopendatahub-io
36

env-finder

Analyze build configuration files to extract environment variables affecting Python wheel builds.

Official
Basic
opendatahub-ioopendatahub-io
36

source-finder

Locate Python package source repositories by analyzing PyPI metadata and project URLs.

Official
Basic
opendatahub-ioopendatahub-io
36

license-checker

Assess Python package license compatibility using SPDX data.

Official
Basic
opendatahub-ioopendatahub-io
36

shallow-clone

Creates a depth-1 clone of a Git repository in a temporary location.

Official
Intermediate

Frequently Asked Questions About Open Data Hub

FAQPage Schema
What specific tasks can I perform using Open Data Hub's diagnostic capabilities?

You can perform deep-dive root cause analysis on CI/CD pipeline failures, audit PyPI package metadata for build complexity, and validate license compliance using SPDX data. Additionally, the suite enables the generation of structured lint checks for Kubernetes-based environments and the systematic tracking of evaluation metrics via MLflow.

Which technical personas benefit most from these evaluation and diagnostic utilities?

These utilities are designed for DevOps engineers, release managers, and machine learning practitioners. They specifically assist those responsible for maintaining stable build environments, ensuring open-source license adherence in software supply chains, and managing the rigorous testing and validation of model performance within enterprise development cycles.

What are the primary prerequisites for running the evaluation and linting components?

Execution requires a configured environment capable of interfacing with GitLab for pipeline data, JIRA for issue tracking, and MLflow for experiment logging. Users must ensure valid credentials for these services are present, alongside the necessary configuration files like eval.yaml and eval.md to define test parameters and validation logic.