AI Engineering

Memorix Mini-Skills turns durable project knowledge into reusable agent guidance. Use it to promote repeated fixes, gotchas, and workflows instead of keeping them as ordinary memory.

Memorix Orchestrate coordinates explicit subagent work with tasks, handoffs, messages, file locks, and the orchestrate CLI. Use it when a main agent needs managed multi-agent execution.

Memorix Reasoning stores why a technical decision was made and retrieves prior rationale later. Use it for trade-offs, rejected alternatives, architecture choices, and design risks.

Memorix Sessions helps agents start, resume, and end work sessions when handoff context or project binding is needed. Use it for recent session summaries, HTTP control-plane binding, or explicit coordination identity.

Memorix Troubleshooting helps diagnose missing MCP tools, stale bindings, hook failures, and setup issues for Memorix. Use it to check project status, restart integrations, or fall back to CLI commands and control-plane checks.

Agent Judge adds judge-level skill installation for agent-based evaluation runs. Use it when the evaluator needs reusable rubrics or domain guidance separate from the skill under test.

Agent Judge Support adds judge-side Skills to agent_judge evaluations so the reviewer agent can install and use separate rubric Skills. It is used when you need reusable, isolated review rules and audit data for scoring.

Business Brainstorm pressure-tests a new business, product, or side project against a structured founder filter. It scores the idea, checks naming and research signals, and returns a build, sleep on it, or pass verdict.

Company Brain structures team knowledge about people, companies, meetings, SOPs, decisions, and customer language so Claude can answer questions and compile a wiki. Use it to capture, query, review, lint, connect, or search shared context.

Custom Engine is a minimal end-to-end fixture for testing local and HTTP custom agent transports. Use it to verify SessionInput and SessionResult flow through the pipeline.

Decide guides a structured decision-making workflow that picks the most relevant questions, reaches a call or a wait, and archives the rationale for later review. It is used when you need to choose between options, handle go/no-go calls, or log the reasoning with a revisit date.

Deep Research plans and runs multi-source research on a topic, then writes a cited brief with contradictions, gaps, and next steps. Use it for competitor research, due diligence, market validation, or other questions that need verification across several sources.