AI Skills

Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when adding, creating, or implementing a new cuTile operator/kernel in TileGym, or when asking how to register a new cuTile op.

Expert-level algorithmic trading, market systems, quantitative analysis, and trading platforms

Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.

Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.

>

When the user wants to plan email marketing, EDM, newsletter strategy, or email deliverability. Also use when the user mentions "email marketing," "EDM," "newsletter," "SPF," "DKIM," "DMARC," "email deliverability," "email content strategy," "email campaigns," "newsletter strategy," "email automation," or "cold email." For signup UI, use newsletter-signup-generator.

React Three Fiber fundamentals - Canvas, hooks (useFrame, useThree), JSX elements, events, refs. Use when setting up R3F scenes, creating components, handling the render loop, or working with Three.js objects in React.

Scrapes content based on a preset URL list, filters high-quality technical information, and generates daily Markdown reports.

Curate Claude Code's auto-memory into durable project knowledge. Analyze MEMORY.md for patterns, promote proven learnings to CLAUDE.md and .claude/rules/, extract recurring solutions into reusable skills. Use when: (1) reviewing what Claude has learned about your project, (2) graduating a pattern from notes to enforced rules, (3) turning a debugging solution into a skill, (4) checking memory health and capacity.

Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for generic word boosting (use /finetune-asr).

Recommend and customize Megatron Bridge recipes for a user's model, GPU count, and training goal. Indexes library recipes (pretrain/SFT/PEFT) and performance recipes.

Agent skill for topology-optimizer - invoke with $agent-topology-optimizer

Guide for migrating Apache Airflow 2.x projects to Airflow 3.x. Use when the user mentions Airflow 3 migration, upgrade, compatibility issues, breaking changes, or wants to modernize their Airflow codebase. If you detect Airflow 2.x code that needs migration, prompt the user and ask if they want you to help upgrade. Always load this skill as the first step for any migration-related request.

Agent skill for goal-planner - invoke with $agent-goal-planner

Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.

Agent skill for code-review-swarm - invoke with $agent-code-review-swarm

>

Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3, Qwen3, Qwen3-Next, and VLM bring-up work.

Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex dispatcher backends such as DeepEP and HybridEP.

Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows

Deploy to Cloudflare (Workers, R2, D1), Docker, GCP (Cloud Run, GKE), Kubernetes (kubectl, Helm). Use for serverless, containers, CI/CD, GitOps, security audit.

>

Foundational plotting library. Create line plots, scatter, bar, histograms, heatmaps, 3D, subplots, export PNG/PDF/SVG, for scientific visualization and publication figures.

Tauri development guidelines for building cross-platform desktop applications with TypeScript, Rust, and modern web technologies

Systematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper. Covers the Three Walls framework, parallel folding, recompute strategy, dispatcher choice, and CUDA-graph bring-up.

>

Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine.

Agent skill for consensus-coordinator - invoke with $agent-consensus-coordinator

Routes NVIDIA Nemotron Speech (Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted.