a5c-ai/babysitter Skills

Use when receiving code review feedback, before implementing suggestions. Requires technical rigor and verification, not blind implementation.

Execute work units through the rigorous 4-phase Metaswarm cycle (Implement -> Validate -> Adversarial Review -> Commit) with independent quality gate enforcement.

Use when creating new skills, editing existing skills, or verifying skills work before deployment.

Validate scripts for POSIX compliance with portability checks, bashism detection, and cross-platform compatibility.

Create, track, and land convoys of related beads as primary work orders in the Gas Town multi-agent orchestration framework.

Automated test validation, coverage checking, and quality metrics with aggressive defaults

Generate plugin dependency resolution logic with topological sorting.

Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.

Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.

NVIDIA NeMo Guardrails configuration for conversational safety and control

OpenTelemetry instrumentation for LLM applications with distributed tracing

Structured prompt template creation with variables, formatting, and version control

Query expansion, HyDE, and multi-query generation for improved retrieval

Cross-encoder reranking and MMR diversity filtering for improved retrieval quality

6-phase iterative specification execution workflow covering implementation, testing, review, improvement, commit, and progress tracking with quality-gated convergence.

Git-backed state management for safe rollback. Create and restore checkpoints with tagged commits and metadata tracking.

PM2 process management, backend/frontend cascade execution, parallel worktree builds, and cross-service integration testing.

LangChain chain composition including SequentialChain, RouterChain, and LCEL patterns

Set up cosmiconfig for hierarchical configuration loading from multiple sources and formats.

Implement computational geometry algorithms

Minimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use Write/Edit tools only.

Perform cross-artifact consistency and coverage analysis across constitution, specification, plan, and task artifacts to detect gaps, conflicts, and misalignments before implementation.

Systematic codebase exploration following the Iron Law - understand the problem before exploring code. Four phases with file-finder and web-researcher agents.

Provide implementations of advanced data structures