checklist-runner

To automate release readiness validation, run checklist-runner in yolo mode against your Markdown checklist. It autonomously scores evidence from Git diffs and test results, applying PASS/FAIL/PARTIAL logic to generate an APPROVED or FAIL decision.

Checklist validation is the process of scoring work artifacts against shared Markdown criteria. It evaluates Git diff evidence by loading context, applying PASS/FAIL/PARTIAL/N/A logic per item, and generating a structured section-level decision report.

Yes, you can use checklist-runner for pre-push quality checks in an interactive workflow. It supports section-by-section confirmation, allowing you to validate Git diff changes and test evidence incrementally before finalizing the approval decision.

Yes, checklist validation works with npm test results and story documentation. The evidence-aware context loading mechanism checks these artifacts alongside the current Git diff to verify deliverables against your Markdown checklist.

The best way to resolve checklists by name during autonomous quality gate runs is using the fuzzy checklist resolution feature in yolo mode. It locates the Markdown checklist from configured paths, loads context artifacts, and produces a structured final report.

You should not use autonomous checklist validation in yolo mode when you need strict manual oversight of the quality gate process. Instead, use interactive mode to review evidence, verify test results, and confirm section-level decisions incrementally.