ai-sprintlisted

# Sprint ## Purpose Sprint lifecycle management: plan new sprints from backlog, run data-driven retrospectives comparing planned vs shipped, and track sprint-level goals. Bridges the gap between spec-level planning and day-to-day delivery. ## Trigger - Command: `/ai-sprint plan|retro|goals` - Context: sprint boundary (start or end of sprint), goal tracking mid-sprint. ## Pre-conditions (MANDATORY) 1. Read `.ai-engineering/manifest.yml` — `work_items` section. 2. Determine active provider (`github` or `azure_devops`). 3. Read `.ai-engineering/reference/gather-activity-data.md` for the canonical git log, PR query, and work item commands. 4. Use provider-specific config: - **Azure DevOps**: filter by `area_path`, auto-detect current `iteration_path` - **GitHub**: filter by `team_label`, use milestones for sprint boundaries 5. Use all standard and custom fields the platform provides. ## Workflow Four modes follow the sprint lifecycle: 1. `plan` — read backlog, propose sprint goals, scope items, write sprint file. 2. `goals` — mid-sprint progress check vs the planned goals. 3. `retro` — data-driven retrospective comparing planned vs shipped. 4. `review` — generate the sprint review deck (delegates to `/ai-slides`). ## Modes ### plan -- New sprint planning 1. **Review backlog** -- read open specs, GitHub Issues/Projects, and prioritized items from the backlog (GitHub Issues with priority labels or manual ranking). 2. **Assess capacity** -- count working days in sp