DevOps e Infra

Analyze medical billing and revenue cycle management software including claims processing pipelines, EDI transaction handling (837P/837I/835/270/271/276/277), ICD-10 and CPT code validation with NCCI edit checking, payer rules engine configuration, denial management and appeal workflows, prior authorization tracking, charge capture completeness, AR aging analysis, underpayment detection, and compl

Interact with X/Twitter via the x-cli terminal client using official X API credentials. Use for posting, reading timelines, searching tweets, liking, retweeting, bookmarks, mentions, and user lookups.

Generate a production-grade Industrial IoT protocol bridge — OPC UA ↔ MQTT Sparkplug B, Modbus → MQTT, or direct PLC (Rockwell/Siemens/Beckhoff) → cloud (AWS IoT Core / Azure IoT Hub / GCP IoT / self-hosted HiveMQ). Output is real code with TLS / X.509 mutual auth, Sparkplug B lifecycle (NBIRTH/DBIRTH/DDATA/DDEATH), canonical topic schema, store-and-forward buffering for network drops, and a docke

Skill Overloop CLI: gerencie prospects, campanhas, sourcings e alcance de clientes via Overloop API v2, diretamente do terminal.

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

Map a cloud system against NIST SP 800-53 Rev. 5 + FedRAMP baselines to produce the documentation an authorization needs — System Security Plan (SSP), Control Implementation Summary (CIS), Plan of Action and Milestones (POA&M), Continuous Monitoring (ConMon) Plan. Aware of 2026 FedRAMP CR26 changes (Certification Classes A/B/C/D replacing Pilot/Ready/Low/Li-SaaS/Moderate/High; JAB authorization mo

Planejando mudanças na API e decidindo a abordagem de versionamento.

Set up a complete mobile publishing pipeline — chains CI/CD workflow generation, iOS App Store publishing via Fastlane, Google Play Store publishing, and analytics verification into an end-to-end release automation. Use for Flutter, React Native, or native iOS/Android apps ready for store submission.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Create and review bash scripts specifically for NinjaOne or Action1 RMM deployment to Linux servers. ONLY use when the user explicitly mentions RMM, NinjaOne, Action1, or background agent deployment targeting Linux. Do NOT use for general shell scripting.

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Decentralized AI-to-AI and human chat rooms with E2E encryption. Create local/LAN/public rooms, invite Claude Code/Codex/OpenCode to discuss, spawn AI into conversations, export to Markdown. Relay via Cloudflare Durable Objects for cross-internet chat. Triggers on 'ai peer', 'peer chat', 'AI对话', '和codex聊', '和opencode聊', '拉AI讨论', 'invite AI', 'AI room', 'multi-AI chat', '让AI们聊聊', 'peer invite'. Use