Results for “dep”

Plans, builds, and deploys a complete Ethereum dApp using a three-phase build system with local fork, testnet, and production stages, plus a secret safety protocol and ERC-8004/x402 commerce flow.

Deploy Llama Guard, NeMo Guardrails, and LLM Guard as runtime input/output scanners to block jailbreaks, prompt injection, and toxic content in production LLM applications.

Deploy and serve LLMs with high throughput using vLLM's PagedAttention and continuous batching. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism for production inference.

Deploys anomaly detection for industrial control environments using machine learning models trained on OT network baselines, physics-based process models, and behavioral analysis of industrial protocol communications.

Train or fine-tune language and vision models using TRL or Unsloth on Hugging Face Jobs cloud infrastructure, with support for SFT, DPO, GRPO, and reward modeling, plus GGUF conversion for local deployment.

Build Unity games with optimized C# scripts, efficient rendering, and proper asset management. Masters Unity 6 LTS, URP/HDRP pipelines, and cross-platform deployment. Handles gameplay systems, UI implementation, and platform optimization. Use PROACTIVELY for Unity performance issues, game mechanics, or cross-platform builds.

Implements a Python function that converts an RGB image to HSV color space and extracts a specified channel (H, S, or V), including handling to convert the image to uint8 type to avoid OpenCV depth errors.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.

Automates the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models, including baseline evaluation, RCA, synthetic defect generation, data mining, retraining, and deployment gating until KPI targets are met.

Reuse a running Chrome session for browser automation via Playwriter CLI + MCP. Use when the task depends on the browser the user already has open — existing logins, cookies, extensions, passkey-friendly flows, or live-tab continuity. Route repeatable fresh-browser or CI-style checks to `browser-harness` instead.

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.

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.

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.

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.

Build type-safe AI agents and graph-based workflows with PydanticAI and PydanticGraph. Agent creation, function tools, capabilities, dependency injection, structured output, streaming, multi-agent patterns, testing, evals, and graph state machines. Use whenever you are building agents, tool-using LLM workflows, or graph-based state machines in Python.

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Design and implement clear, modular, resilient software and create executor-grade implementation plans with explicit scope, drift checks, verification gates, tests, STOP conditions, dependencies, and delegated-work review. Use for development, refactoring, architecture, implementation planning, safe migrations, handoffs to another engineer or agent, or verifying delegated code changes.

Design and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis. Use when a task contains genuinely independent workstreams, specialized roles, parallel research or implementation, reviewer-worker loops, or coordination problems that one agent should not execute sequentially.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

Design and deploy IEC 62443-compliant conduit architecture for secure OT remote access, including jump servers, MFA gateways, session recording, and approval-based workflows for vendor and engineer access to industrial control systems.

DEPRECATED in v5.6.0 — see joint-multi-tf-v560 skill. Documents the v5.2.0 dual-model approach (train separate 15Min/1Hour models, combine via weighted voting). Still relevant for: (1) loading legacy v5.5.0 dual models, (2) understanding the historical aggregation layer, (3) resampling pattern via origin='start'.

Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new skill', 'MCP server', 'custom tool', 'agent design'. NOT for using existing agents (invoke them directly), general coding (use language-specific skills), or infrastructure setup (use deployment-engineer).

Audit, plan, implement, or review Model Context Protocol version and SDK migrations. Use for MCP 2026-07-28, stateless Streamable HTTP, server/discover, removal of initialize or Mcp-Session-Id, MCP Tasks extension changes, full JSON Schema 2020-12 tool schemas, OAuth issuer hardening, deprecated roots/sampling/logging, or cross-version client/server compatibility.

Run 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.

Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.

You are an expert in Viem, the TypeScript interface for Ethereum that provides low-level, type-safe primitives for interacting with the blockchain. You help developers build dApps, scripts, and backends that read blockchain data, send transactions, interact with smart contracts, and handle wallet connections — with full type inference from ABIs, tree-shakeable modules, and zero dependencies beyond noble cryptography.

Codebase-wide Retrieval-Augmented Generation for deep code understanding. Use when: (1) Answering questions about large codebases by searching across all files, (2) Finding related code patterns, implementations, or dependencies across a project, (3) Building context from multiple files before making changes, (4) Understanding how a feature works end-to-end across the codebase, (5) Tracing data flow through multiple modules

Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses Socratic questioning to capture intent before drafting, and validates output against an agent-readiness checklist.