Systematically explore unfamiliar codebases to build working mental models. Use when onboarding to new project, "what does this do", or understanding legacy code.
Produce reusable technical architecture documents from codebase exploration. Use when onboarding, "write up what this does", architecture docs, or handoff.
Remove telltale signs of AI-generated "slop" writing from documentation. Use when polishing README files, API docs, or any public-facing text to sound authentically human.
Generate and operationalize improvement ideas for projects. Use when brainstorming features, planning improvements, creating beads from ideas, or "what should we build next".
Run Lean-Rust proof feedback loops to find runtime bugs. Use when proving theorems, triaging hard proof blockers, checking conformance, or closing formal assurance gaps.
Use when the user wants a hard question, proposal, design, review, tradeoff analysis, or difficult debugging problem answered by a council of Claude, Codex, and Gemini through this repo's local multi-ai CLI. Trigger for requests like "ask multiple AIs", "use the council", "get another model's take", "high-confidence review", "difficult question", or "compare top models on this".