aaaav

Use when creating, editing, or auditing agent skills and instructions, applying friction notes, or bootstrapping or overhauling a project's agent system.

Use when changing source code or its tests, such as fixing a bug, adding or changing behavior, refactoring, improving performance, or prototyping a design…

Use when resolving user-owned decisions or ambiguous architectural tradeoffs, when a decision artifact has open rows, or when the user asks to be grilled on…

Use when auditing or reviewing a specific target, diff, commit, or spec, or running final QA or a release-readiness check.

Use when writing text another agent reads rather than the user, such as a subagent brief or follow-up, a subagent's final report, an intercom, tower…

Use when project terminology or domain boundaries need refinement.

Use when evaluating human feedback or conducting interactive UI verification.

Use when writing or revising documentation, a README, an article, a PR description, or prose in general, tightening existing text, or cleaning up code comments.

Use when explaining a concept or how something works, comparing technical alternatives, summarizing results or a change for the user, or when the user says…

Use when researching questions, diagnosing root causes without fixing them, or gathering evidence.