Use when a set-up project (project/BRIEF.md approved, PROFILE/STATE/backlog present) should continue building autonomously — orchestration of CEO/PO/DEV/REVIEWER cycles with parallel agents, without user input. Also for resuming after an interruption or…
Use when an approved product brief (project/BRIEF.md, status APPROVED) exists and the project should be set up without further user input — research, tech decisions, scaffold, backlog. Do not use while the brief is missing or DRAFT (→ project-onboarding).
Use when the user pitches a new project or product idea, wants to start a new project, or asks for an onboarding interview — including vague ideas ("I have an idea for an app"). The only interactive skill of the suite; everything after it runs autonomously.
Use when the overall state of the repo needs checking (not a diff) — before releases, after major rework, at milestone gates, or periodically: pattern consistency, module boundaries, security posture, rule compliance, doc drift. Not for package reviews (→…
Use when a portfolio decision is due — prioritization, approval, defer, escalation, or gate evaluation — or when autonomous-loop requests a CEO tick. Not for implementation, scope cutting, or diff review.
Use when exactly one approved work package (WORK card) should be implemented — including as a DEV subagent in autonomous-loop. Not for scope decisions, reviews, or when no approved card exists.
Use when a work package needs cutting, acceptance criteria need defining, a new idea needs evaluating (idea triage), or scope creep must be prevented — or when autonomous-loop requests the PO step. Not for implementation or portfolio prioritization.
Use when a completed work package or a bounded diff needs checking — architecture, risks, test quality, truth of DONE/status claims — including as a review subagent in autonomous-loop. Not for whole-repo state audits (→ role-auditor).