a5c-ai/babysitter Skills

Analyze test coverage and identify gaps before migration to ensure adequate safety nets

Generate contract tests for API migrations with consumer-driven contracts and provider verification

Assess application readiness for cloud migration with 6Rs classification and cloud-native compliance checking

Discover and document existing API endpoints from code, logs, and traffic analysis

Generate hook-based plugin extension system with event emitter patterns.

Entity and fact extraction for user profiling and personalization

Arize Phoenix observability platform setup for LLM debugging and evaluation

Capture, validate, query, and sync architectural patterns and design decisions in the knowledge graph

Continuous monitoring using Deacon/Witness patterns for agent health checks, stuck detection, and automated recovery.

Evaluation harness for testing agent and skill quality through structured benchmarks, regression tests, and quality scoring.

Set up Viper for Go configuration management with file, env, and flag binding.

Extract domain models from monolithic codebases using DDD principles for microservices decomposition

Rasa NLU pipeline configuration and training for intent and entity extraction

Urgent issue classification, root cause analysis, and fast-path routing for production hotfixes

LLM-based zero-shot and few-shot classification for flexible intent detection

Generate cross-platform path handling utilities for Windows, macOS, and Linux compatibility in CLI applications.

Pattern extraction, confidence-scored evaluation, skill creation, organization, versioning, and cross-project export pipeline.

Batch embedding generation with caching, rate limiting, and multiple provider support

LangChain tool creation and integration utilities for agent systems

Generate documentation for migrated systems including API docs, architecture docs, and runbooks

# Findings Capture Capture and persist research findings, discoveries, and decision rationale to findings.md. ## Agent Findings Curator - `pwf-findings-curator` ## Workflow 1. Initialize findings.md with structured section headers 2. Capture findings during execution with timestamps 3. Apply 2-Ac

Select optimal data structure based on operation requirements

Generate trap handlers for cleanup, signal handling, and graceful shutdown in shell scripts.

Orchestrate strangler fig pattern implementation for gradual migration with traffic routing and cutover management