a5c-ai/babysitter Skills

Manage agent sessions including initialization, handoffs, revival (seance), and persistent identity for Polecats and Crew agents.

Context window monitoring and budget management. Keeps orchestrator at 15-30% context usage while subagents get full 200k tokens. Provides warnings at thresholds, context-aware summarization triggers, and wave-level budget planning.

Parallel design review by 6 specialist agents (PM, Architect, Designer, Security Design, UX, CTO) with mandatory unanimous approval.

Decompose implementation plans into discrete work units with enumerated DoD items, file scope declarations, dependency mapping, and human checkpoint flags.

Convention discovery and rule generation from codebase analysis. Scans project structure, builds search indexes, identifies patterns, and generates enforceable rules.

Specification creation and management for the Pilot Shell methodology. Covers semantic search, clarifying questions, structured spec generation, and iterative refinement.

# Completion Verification Verify all phases are complete with weighted quality scoring before allowing session exit. ## Agent Completion Verifier - `pwf-completion-verifier` ## Workflow 1. Read all three planning files in parallel 2. Parse checkbox completion state from task_plan.md 3. Cross-refe

Structured code quality assessment with Conventional Comments format, scaled review depth, and soft-gating verdicts preserving user autonomy.

Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle.

Validate implementation quality through custom checklists, scoring against constitution standards, specification coverage, and producing remediation recommendations.

Configure PyInstaller for Python binary builds with spec files and bundling options.

Use when you have a spec or requirements for a multi-step task, before touching code. Creates bite-sized TDD implementation plans with dependency tracking.

Chroma local vector database setup and operations for development and production

Integrate dotenv for environment variable loading with validation and type coercion.

Conversation summarization for memory compression and context management

Conditional edge routing and state-based transitions for LangGraph workflows

Subgraph composition and modular workflow design for LangGraph

Generate dynamic plugin loading system with discovery, validation, and lifecycle management.

Define plugin manifest schema with versioning and dependency declarations.

Prompt injection detection and prevention for secure LLM applications

Generate Scoop manifest for Windows CLI distribution.

Redis backend for conversation state persistence and caching

Assist in designing optimal DP states and transitions

Configure plugin sandboxing with vm2 or isolated-vm for secure plugin execution.