babysitter

Use when adding a new agent harness (CLI-based coding agent) adapter to adapters. Covers capability audit, adapter scaffold, session parsing, auth detection, hooks/plugins wiring, tests, and docs.

Reference for querying the Atlas knowledge graph through its MCP tools — the SECONDARY enrichment/comparison layer that adds best-practice context to systems you have ALREADY scanned from your real sources (`az`, repos, dirs). Use when you need to look up nodes, edges, kinds, clusters, stats, or wiki pages in Atlas to compare against your real inventory. (atlas graph, query atlas, atlas mcp, search the graph, graph neighbors, atlas record, atlas kinds, enrichment layer)

Atlas turns your STATED NEED into a real systems atlas by SCANNING your actual sources (Azure via `az`, git repos, local dirs) and process/data mining them, THEN enriching against the Atlas knowledge graph. Use this skill when asked to inventory/map your real systems, scan your cloud + repos + directories, mine the real processes or data they contain, or collect their real constraints/gotchas. (atlas, scan my systems, inventory our azure account, map my repos, real systems atlas, process mining, data mining, collect nuances, system discovery)

Execute via @babysitter. Use this skill when asked to babysit a task, do anything that is structured process-driven (even a loop) or whenever it is called explicitly. (babysit, babysitter, with a process, orchestrate, orchestrate a run, workflow, loop until, etc.)

Build dependency-aware, batched dispatch queues for parallel agent execution.

Perform code review with quality scoring and configurable threshold enforcement.

Parse and normalize features from text descriptions, images, and screenshots into structured requirements.

Initialize and manage Kanban board state for feature workflow tracking.

Emit real-time progress events for streaming UI consumption.

Execute Vitest and Playwright test suites with result collection and failure analysis.

Manage git worktree lifecycle for safe, isolated parallel development.

Design comprehensive system architecture with technology selection and ADRs.

Multi-dimensional code review across correctness, security, performance, maintainability, and test coverage.

Create Product Requirements Documents through structured discovery using Jobs-to-be-Done framework.

Create comprehensive product briefs from market, domain, and technical research.

Generate comprehensive project documentation with source tree analysis and Mermaid diagrams.

Generate and execute API and E2E tests with quality gate assessment.

Lean solo-developer workflow for rapid spec-to-implementation with minimal overhead.

Plan implementation sprints with story selection, goal definition, and execution ordering.

Implement user stories with test-driven development methodology.

Create comprehensive UX design with user flows, wireframes, and design systems.

System and API design guidance covering component boundaries, data flow, integration patterns, and scalability considerations.

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

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

Root cause analysis frameworks including log-first investigation, git bisect correlation, and pattern-based diagnosis with confidence scoring.

Structured planning methodology with research, brainstorming, phased plan creation, risk assessment, and plan-to-build continuity.

Mandatory memory persistence system across session resets using three markdown surfaces in .claude/cc10x/. Iron law - every workflow must load at start and update at end.

Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.

Evidence requirement enforcement ensuring all claims are backed by logs, test results, or exit codes. Zero = success, non-zero = failure. No guessing allowed.

Full traceability from PRD to code commit through the CCPM spec-driven pipeline.

Project context loading, isolation, and persistent state management across CCPM sessions.

Transform PRD into a technical implementation plan with architecture decisions and dependency mapping.

Bidirectional synchronization of epics and tasks with GitHub issues, labels, and relationships.

Coordinate multiple specialized agents across parallel work streams with quality gates and conflict resolution.

Interactive PRD brainstorming and drafting with quality-gated refinement.

Status dashboards, standup reports, and blocked task management with GitHub synchronization.

Break epics into parallelizable tasks with acceptance criteria, effort estimates, and dependency graphs.

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

6-agent parallel code review orchestration covering architecture, security, performance, testing, quality, and documentation dimensions with weighted scoring.

Automatic codebase indexing for invisible context injection. Catalogs project structure, file types, entry points, dependencies, and test layout.