What problem does it solve?
Contributors to the AnalyticsPlatformAgents repository frequently waste time waiting for CI results and fixing avoidable issues (structural lint errors, broken skill references, failing evals) that could have been caught locally before pushing a PR.
Core Features & Use Cases
- Local CI Parity: Runs the exact three checks CI executes (quality structural lint, Vally eval for changed skills, filtered full-eval for multi-step changes) to ensure PRs pass on first push.
- Guided Workflow: Walks users through prerequisites (ephemeral tenant login, workspace provisioning, capacity selection) and step-by-step execution for each check, including error handling and cleanup.
- Use Case: A contributor modifying a Fabric skill can run this skill to validate their changes locally, catch issues in minutes instead of waiting 10+ minutes for CI, and avoid review rounds for failed checks.
Quick Start
Use the pre-pr-check skill to run all required local verification steps for your PR that touches skills, agents, common, or tests before you push your changes.