Create, run, and review Databricks skill tests via a YAML-first GRP pipeline.
npx skills add https://github.com/databricks-solutions/ai-dev-kit --skill skill-test
Please help me install this Agent Skill. Skill: skill-test Source: https://github.com/databricks-solutions/ai-dev-kit/tree/main/.test Command: npx skills add https://github.com/databricks-solutions/ai-dev-kit --skill skill-test
The Skill Testing Framework centralizes Databricks skill evaluation by providing a reproducible, YAML-first workflow for generating test scaffolding, executing tests (including optional Databricks MCP), and promoting results to ground truth for reliable regression testing.
/skill-test <skill-name> init, then run evaluations with /skill-test <skill-name> run.ground_truth.yaml and baseline.yaml to manage regression tests and track improvements over time.High-intent search queries and answers about installing and using this skill.
Run regression tests for Databricks skills by defining test cases in YAML files and executing the Generate-Review-Promote pipeline to validate behavior and promote results to ground truth baselines.
MLflow integration tracks evaluation metrics and trace analysis during skill testing, allowing you to monitor regressions across skill versions and environments using baseline comparisons.
Yes, the skill testing framework supports routing and trace evaluation to validate skill activation and verify Claude Code behavior through MLflow-backed metrics and interactive CLI reviews.
The Generate-Review-Promote pipeline is a YAML-first workflow that generates test scaffolding, executes skill tests, and promotes reviewed candidates to ground truth for reliable regression testing.
Yes, the framework requires python-dotenv, PyYAML, mlflow, and databricks-sdk dependencies to execute tests, manage YAML configurations, and integrate with Databricks environments.
Initialize test scaffolding with `/skill-test <skill-name> init`, then execute evaluations using `/skill-test <skill-name> run` to generate prompts and review candidates against baselines.
thbehGenerate Python step definitions for Behave tests using the Databricks SDK.
itsadijmbtEvaluate and optimize Databricks agent skills against ground truth YAML test cases.
juanlamadrid20Automate production deployment and monitoring of AI agents on Databricks.
leary-pokenEvaluate Databricks skills by comparing WITH-skill and WITHOUT-skill results.