a5c-ai/babysitter Skills

Observation capture and retrieval across sessions. Stores decisions, discoveries, and bugfix patterns. Searchable via tags and relevance scoring.

Generate configuration file migration utilities for version upgrades.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Requires root cause investigation first.

Adversarial plan review by 3 independent reviewers (Feasibility, Completeness, Scope & Alignment) before presenting to user.

Transform research findings into actionable implementation plans with stakes-based rigor, test-first strategy, and granular task decomposition.

Convert requirements into structured technical specifications with architecture decisions

# Plan Creation Create a structured task_plan.md with phases, goals, and checkbox tracking for persistent planning. ## Agent Plan Architect - `pwf-plan-architect` ## Workflow 1. Analyze task description to identify logical phases 2. Decompose phases into specific, achievable goals 3. Define phase

Multi-agent swarm formation and coordinated execution with topology-aware agent deployment, consensus protocols, and anti-drift enforcement.

# Story Development Implement user stories with test-driven development methodology. ## Agent Amelia (Developer) - `bmad-dev-amelia` ## Workflow 1. Read entire story and acceptance criteria 2. Write failing tests for each criterion 3. Implement minimum code to pass tests 4. Refactor while keeping

Create Architecture Decision Records (ADRs) documenting significant technical choices with context, options, consequences, and sequential numbering.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements.

PreToolUse protection blocking sensitive file access across 195+ patterns in 12 categories with bash pipeline analysis and multi-tool ignore support.

# Agent Dispatch Build dependency-aware, batched dispatch queues for parallel agent execution. ## Agent Feature Planner - `automaker-feature-planner` ## Workflow 1. Analyze inter-feature dependencies 2. Build directed acyclic graph (DAG) 3. Generate topologically sorted execution order 4. Group f

Build structured knowledge frameworks from scattered vault notes with source attribution

Git worktree management for safe, isolated feature development. Creates, manages, and cleans up worktrees with branch naming and dependency setup.

Apply language-specific micro-optimizations

Manage and generate competitive programming templates

Simulate realistic coding interview experience

Break technical specifications into small, implementable stories with dependency ordering

Cross-domain pattern analysis with personal, professional, and project domain synthesis

Generate formatted help text with examples, descriptions, sections, and consistent styling for CLI applications.

AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.

Interface with AtCoder for Japanese competitive programming contests

LlamaIndex agent and query engine setup for RAG-powered agents