Mike Schwarz

Set up an OpenRig team for ongoing repository work, with clear ownership, implementation, independent review, and handoffs. Choose direct coordination, a task queue, or an explicit workflow, then expand the team as authorized work requires.

• Starting a builder and reviewer team for a repository
• Keeping ownership visible across task handoffs
• Choosing direct work, a queue, or a workflow

Review feature plans before development from business strategy, user experience, and engineering perspectives. Receive scored assessments, specific gaps tied to requirements, and prioritized actions that clarify what must change before the team starts building.

• Checking a feature specification before development
• Reviewing screen states and accessibility requirements
• Assessing scope against business priorities

Verify development results before reporting success or preparing commits and pull requests. Run checks that support each claim, inspect their actual output, and report remaining gaps instead of relying on assumptions or another agent’s success message.

• Checking evidence before reporting a bug as fixed
• Confirming test and build results before a commit
• Verifying that a regression test detects the bug

Create reusable starting configurations that combine an agent’s role, startup context, and source history. The skill guides registry entries, checks whether their sources are current, and manages their progression from initial capture to recommendation or retirement.

• Create reusable startup context for an agent role
• Refresh an agent workspace from an existing starter
• Check a starter’s source history and freshness

Guides the design and review of agent startup context, including role files and links to authoritative records. It helps identify stale guidance, missing updates, overloaded startup files, and instructions that lose the purpose of the work.

• Designing startup files for a new agent
• Reviewing stale guidance used by running agents
• Separating role information from reusable procedures

Classify agent work as ready to continue, needing human judgment, or intentionally paused. Structure decision requests with evidence, a recommended choice, and clear outcomes, then connect the recorded decision to the next responsible agent.

• Deciding whether agent work needs human review
• Preparing decision requests with evidence and recommended choices
• Designing a dashboard for pending human decisions

Change a running OpenRig setup by adding or removing agent seats, connecting existing sessions, or attaching terminals. Guides checks for roles, startup context, permissions, and session identity so the setup reflects each change correctly.

• Add agent seats to a running rig
• Remove seats and clean up remaining references
• Connect an existing session to an OpenRig node