Every agent loads this skill at the start of every session to consult the long-term knowledge base before rediscovering prior work. The primary agent may delegate global KB writes; subagents have read access and report candidate learnings upward.
Use after completing non-trivial work in a project to assess whether anything learned should be persisted as project-level context. Captures project-specific conventions, workflows, architecture patterns, and tooling quirks to AGENTS.md or project skills — so future sessions don't rediscover them.