Project
feat(ci): test multi-Skill composition and add model evaluation controls
Source excerpt
Summary The previous CI booted a checked-in reference plugin but did not exercise multi-Skill composition or model outcomes. This change adds explicit planner coverage for every installed Skill and a seven-task Harbor evaluation workflow with separate control and model jobs. It also explicitly prepares snapshot commits for CI, fetching missing pins without
Automatically summarized from source discussions. Sources and the full record are available below.