Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

Query the memory system for relevant learnings from past sessions

Release preparation workflow - security audit → E2E tests → review → changelog → docs

Create handoff document for transferring work to another session

Check reference SDK implementations using btca ask

Find unused functions and dead code in the codebase

Store a learning, pattern, or decision in the memory system for future recall

Implement technical plans from thoughts/shared/plans with verification

Computational geometry with Shapely - create geometries, boolean operations, measurements, predicates

Environment Triage

Create or update continuity ledger for state preservation across clears

Resume work from handoff document with context analysis and validation

Workflow orchestrator that chains existing skills for feature development

Guide to the math cognitive stack - what tools exist and when to use each

Unit-aware computation with Pint - convert units, dimensional analysis, unit arithmetic

Search Mathlib for lemmas by type signature pattern

Agent Orchestration Rules

Friendly onboarding when users ask about capabilities

Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging

Code refactoring workflow - analyze → plan → implement → review → validate