memory-protocol
File-based knowledge persistence patterns: when to store discoveries, when to recall past solutions, and how to organize project memory. Activate when starting tasks, encountering errors, making decisions, or when context may be lost between sessions.
ue-serialization-savegames
Use when implementing save/load systems, player progress persistence, or data serialization in Unreal Engine. Triggers on: save game, USaveGame, FArchive, serialization, SaveGameToSlot, config, persist data, save file, load game. See references/save-system-architecture.md for full slot management and multi-user patterns.
postgres-k8s-setup
Deploy PostgreSQL on Kubernetes for LearnFlow student data persistence
Event Store Design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
web-state-pinia
Pinia stores, Vue 3 state patterns. Use when managing client state in Vue applications, choosing between Options/Setup stores, composing stores, or implementing persistence.
event-store-design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
Persistence Knowledge
Comprehensive knowledge base for the Water Framework persistence layer, including the Repository pattern, JPA implementations, the QueryBuilder fluent API, transaction management, and SystemService integration. Use this when designing, implementing, or debugging data access, query construction, pagination, or transaction logic in Water modules.
hugging-face-model-trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
Beads Workflow
Context persistence across AI sessions using Beads CLI. Never lose progress between conversations.
todo-crud
Implement CRUD operations for TODO items with REST API and data persistence
Event Store Design
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
homelab-container-lifecycle
Manage Docker/Podman container lifecycle including creation, starting, stopping, updating, cleanup, and troubleshooting. Handles image management, volume persistence, network configuration, and container health monitoring. Use when working with containers, deploying services, updating images, cleaning up resources, or troubleshooting container issues.
work-access-demo-generator
Generate comprehensive demonstrations showing how to access projects and continue work across different environments (Manus terminals, personal computers, team collaboration). Use when users ask how to access work from another terminal or computer, how to share it with their team, how to get it on a Mac, or when they need clarification on Manus persistence versus GitHub usage.
building-chat-interfaces
Build AI chat interfaces with custom backends, authentication, and context injection. Use when integrating chat UI with AI agents, adding auth to chat, injecting user/page context, or implementing httpOnly cookie proxies. Covers ChatKitServer, useChatKit, and MCP auth patterns. NOT when building simple chatbots without persistence or custom agent integration.