What problem does it solve? Teams running AI-DLC workflows lack a unified way to measure project health across documentation, work tracking, and code. This Skill produces a consolidated confidence, risk, and progress report so stakeholders can see where a project stands and what needs attention. ## Core Features & Use Cases - Two Assessment Modes: Full Assessment covers documentation quality, team readiness, execution evidence, and code health; Execution Assessment focuses on epics and sprints with complexity-vs-coverage analysis of completed work and estimation confidence for pending work. - Multi-Backend Support: Automatically detects and works with GitLab (markdown files), Linear (Initiatives/Projects/Issues), or Confluence (pages with Jira), at any phase from planning through implementation. - Parallel Sub-agent Assessment: Spawns specialized assessors for documentation, work tracking, code health, completed work, and pending work, then consolidates results into weighted Confidence and Risk scores with a visual dashboard and machine-readable JSON. - Use Case: Ask "How are we doing on PROJ-123?" mid-sprint to get an execution assessment showing which completed sprints have unmitigated complexity and which pending sprints carry high estimation risk. ## Quick Start Ask the assistant to check the progress of your project by providing a GitLab branch, Linear initiative URL, Confluence page URL, or Jira key, then choose Full or Execution assessment when prompted.
