a5c-ai/babysitter Skills

Final completion discipline including summary generation, plan document updates, and confirmation that all success criteria from the original plan are satisfied.

Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.

Content moderation API integration using OpenAI Moderation, Perspective API, and others

Microsoft Semantic Kernel planner and plugin setup for orchestrated AI

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.

Generate .shellcheckrc configuration with appropriate rules, exclusions, and severity settings for shell script linting.

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

# Architecture Design Design comprehensive system architecture with technology selection and ADRs. ## Agent Winston (Architect) - `bmad-architect-winston` ## Workflow 1. Define high-level system architecture with components 2. Select technology stack with justification 3. Design data model and da

Technical debt management including branch cleanup, doc verification, TODO scanning, and dependency auditing

Hierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization enforcement, and short task cycles.

Multi-protocol consensus for agent swarms supporting Raft leader election, Byzantine fault tolerance, Gossip state propagation, and CRDT conflict-free merging.

# UX Design Create comprehensive UX design with user flows, wireframes, and design systems. ## Agent Sally (UX Designer) - `bmad-ux-sally` ## Workflow 1. Synthesize user research from PRD personas 2. Create user journey maps for primary flows 3. Design information architecture and navigation 4. C

Design technical architecture, select technology stack, and define implementation strategy from specifications and constitution constraints.

Create mock stdin utilities for interactive CLI testing.

Establish project governing principles including dev guidelines, code quality standards, testing policies, UX requirements, performance benchmarks, and security constraints.

Fresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh reviewer spawning.

# QA Testing Generate and execute API and E2E tests with quality gate assessment. ## Agent Quinn (QA Engineer) - `bmad-qa-quinn` ## Workflow 1. Generate API tests for new endpoints 2. Create E2E tests for critical user flows 3. Test edge cases from code review findings 4. Run regression tests 5.

Normalize line endings for cross-platform file handling with CRLF/LF conversion and git configuration.

Use when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent per task.

# Product Brief Creation Create comprehensive product briefs from market, domain, and technical research. ## Agent Mary (Analyst) - `bmad-analyst-mary` ## Workflow 1. Conduct market research (competitors, trends, opportunities) 2. Perform domain research (problem space, stakeholders, pain points)

Security vulnerability assessment identifying OWASP risks, injection vectors, authentication issues, and data exposure with severity classification.

Qdrant vector database with filtering, payloads, and quantization support

# Streaming Progress Emit real-time progress events for streaming UI consumption. ## Agent Progress Streamer - `automaker-progress-streamer` ## Workflow 1. Receive progress event from execution stage 2. Format event with timestamp and stage information 3. Calculate completion percentage 4. Genera

Provide implementations of advanced data structures