📋
Megatron Memory Estimator
Estimate GPU memory usage for Megatron-based MoE (Mixture of Experts) and dense models. Use when users need to (1) estimate memory from HuggingFace model configs (DeepSeek-V3, Qwen, etc.), (2) plan GPU resource allocation for training, (3) compare different parallelism strategies (TP/PP/EP/CP), (4)
yzlnewworkflow
📋
Messaging Rabbitmq Architect
This skill designs robust RabbitMQ topologies, optimizing exchanges, queues, DLX, clustering, and reliability for durable, scalable messaging.
backenddevopsperformancecloud
📋
Microsoft Teams Send As Workflow
Send messages and Adaptive Cards to Microsoft Teams via Incoming Webhook. Use when user requests to send notifications, alerts, or formatted cards to Teams channels. Triggers include requests to post to Teams, Teams webhook, Teams notification, Teams card, or any request to send messages to Microsof
nocooworkflow
📋
Migrate Postgres Tables To Hypertables
This skill guides migrating PostgreSQL tables to TimescaleDB hypertables with configuration, planning, and validation to maximize performance.
databasemigrationsqlperformance
📋
Model
Algorithm/model development and fine-tuning skill. Use for tasks like dataset design/cleaning, supervised fine-tuning (SFT), preference optimization (DPO/RLHF concepts), LoRA/QLoRA, training configs, evaluation (offline/online), safety checks, deployment packaging, and cost/performance trade-offs.
muzhicaomingwangworkflow
📋
Moldable
Complete guide for building Moldable apps. Use this skill when creating new apps with scaffoldApp, modifying existing apps, implementing workspace-aware storage, integrating with the Moldable desktop via postMessage APIs (moldable:show-in-folder, moldable:set-chat-input, moldable:set-chat-instructio
moldable-aiworkflow
📋
Monitoring Observability
This skill guides designing metrics, logs, and traces for robust monitoring, improving incident response and system reliability.
observabilitymonitoringdevopscloud
📋
Multi Cloud Architecture
Design multi-cloud architectures using a decision framework to select and integrate services across AWS, Azure, and GCP. Use when building multi-cloud systems, avoiding vendor lock-in, or leveraging best-of-breed services from multiple providers.
questfortech-investmentsworkflow
📋
My
Personal development toolkit - AI integration, session management, parallel development. Use when: multi-model AI, session handoff, git worktree operations. Triggers: "gemini", "codex", "handoff", "resume", "worktree"
sungjunleeworkflow