a5c-ai/babysitter Skills

Generate argparse-based Python CLI applications with subparsers, type converters, and standard library patterns. Creates lightweight Python CLIs without external dependencies.

Convert problem descriptions into graph representations

LangSmith tracing and debugging setup for LLM applications. Configure observability, capture traces, and enable debugging for LangChain/LangGraph agents.

Generate BATS test structure and fixtures for shell script testing with setup/teardown, assertions, and mocking.

SetFit few-shot learning for efficient intent classification with minimal data

Human-in-the-loop integration for LangGraph workflows with approval and intervention points

Process meeting recordings and transcripts into decisions, action items, and team dynamics

Generate OpenAPI specifications from code or legacy APIs with schema inference and documentation

Compare database schemas between source and target environments for migration planning

Multi-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Router Contract generation.

Assist in containerizing applications with Dockerfile generation and optimization

# Audit Trail Full traceability from PRD to code commit through the CCPM spec-driven pipeline. ## Traceability Chain PRD -> Epic -> Task -> GitHub Issue -> Code Commit ## Capabilities - PRD user story to task mapping - Task to GitHub issue linking - Commit to issue cross-referencing - Coverage ma

Parallel research agent orchestration dispatching 5-10 concurrent agents for comprehensive multi-source research with synthesis and validation.

Track beads as git-backed issues with persistent attribution, supporting Gas Town's bead lifecycle and convoy progress monitoring.

Pinecone vector database setup, configuration, and operations for RAG applications

Compare multiple solutions for correctness and performance

Translate SQL queries between different database dialects with function mapping and optimization

Generate clear explanations of algorithm solutions

Assist in constructing algorithm correctness proofs

Convert technical plans into actionable development tasks with dependency graphs, effort estimates, and parallelization opportunities.

# Epic Generation Transform PRD into a technical implementation plan with architecture decisions and dependency mapping. ## Agent Architect - `architect` ## Workflow 1. Parse PRD and extract structured requirements 2. Define architecture decisions with ADR format 3. Specify technology approach an

Build and query suffix arrays and related structures

Generate shell completion scripts for bash, zsh, and fish from CLI command definitions. Creates intelligent completions with argument suggestions, file completions, and dynamic values.

Validate data integrity during and after migration with comprehensive verification checks