a5c-ai/babysitter Skills

WASM-based instant code transforms for simple tasks, achieving 352x speedup over LLM inference with zero cost.

SONA self-optimizing neural architecture with ReasoningBank trajectory learning, EWC++ anti-forgetting, and reinforcement learning feedback loops.

Complexity-based task routing with Q-Learning optimization, Agent Booster WASM fast-path, and Mixture-of-Experts model selection.

Use when you have a written implementation plan to execute in a separate session with review checkpoints between batches.

Execute development tasks to build features, producing code, tests, and configuration artifacts that satisfy specification requirements and comply with constitution standards.

Track progress through CSES Problem Set with structured learning

Write feature specifications as requirements and user stories with acceptance criteria, focusing on business value and testable conditions.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans.

Generate blessed widgets for Node.js terminal UIs with boxes, lists, forms, and dashboard layouts.

Chain-of-thought and step-by-step reasoning prompts for complex problem solving

Constitutional AI and safety guardrail prompts for aligned LLM behavior

Generate Bubble Tea (Go) TUI application structure with models, commands, and views using the Elm architecture.

CrewAI multi-agent orchestration setup for collaborative AI systems

Generate customized segment tree implementations

Few-shot example generation and optimization for improved LLM performance

Guardrails AI validation framework setup for LLM applications. Implement input/output validation, safety checks, and structured output enforcement.

Generate Click-based Python CLI applications with decorators, groups, context, and modern Python patterns. Creates complete scaffolded CLI with proper project structure.

Generate Cobra/Viper-based Go CLI applications with persistent flags, subcommands, and configuration management. Creates production-ready Go CLI with modern patterns.

Generate bash script templates with best practices including error handling, argument parsing, logging, and portability considerations.

LangChain retriever implementation with various retrieval strategies for RAG applications

Interface with Codeforces API for contest data, problem sets, and submissions

LangGraph StateGraph builder with state schema design. Create stateful agent workflows with cycles, conditionals, and persistence.

Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.

Provide implementations of advanced data structures