Results for “plasma”

Evaluates likelihood of primary aldosteronism by measuring plasma aldosterone suppression after oral captopril; normal suppression ≥30% makes PA unlikely, while lack of suppression with persistently suppressed plasma renin activity suggests PA. Use when assessing captopril challenge test (CCT) results for PA diagnosis in patients with positive aldosterone-to-renin ratio.

Earn yield on any Ethereum wallet on Base, Arbitrum, and Plasma. Use when a user wants passive DeFi yield on their funds. Deploys a non-custodial deterministic subaccount (Safe) linked to their EOA, enables automated yield optimization, and lets them deposit/withdraw anytime.

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.

通用粒子抽象接口。当定义物质维度、物理实体或物质系统时调用此技能。

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 large language models locally with Ollama, including model management, custom Modelfiles, and API integration. Use for private, offline LLM inference.

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.

Deploy and serve LLMs in production with vLLM, Ollama, TGI, and llama.cpp, including quantization and GPU optimization.

You are an expert in vLLM, the high-throughput LLM serving engine. You help developers deploy open-source models (Llama, Mistral, Qwen, Phi, Gemma) with PagedAttention for efficient memory management, continuous batching, tensor parallelism for multi-GPU, OpenAI-compatible API, and quantization support — achieving 2-24x higher throughput than HuggingFace Transformers for production LLM serving.

Prisma ORM for Node.js/TypeScript. Covers schema definition, migrations, and type-safe queries. Use when working with Prisma. USE WHEN: user mentions "prisma", "schema.prisma", "prisma migrate", "prisma generate", "prisma studio", "@prisma/client", asks about "how to define models in prisma", "prisma relations", "prisma transactions", "type-safe database queries" DO NOT USE FOR: raw SQL queries - use `database-query` MCP; Drizzle ORM - use `drizzle` skill; TypeORM - use `typeorm` skill; SQLAlchemy - use `sqlalchemy` skill

Prisma ORM expert for schema design, migrations, query optimization, relations modeling, and database operations. Use PROACTIVELY for Prisma schema issues, migration problems, query performance, relation design, or database connection issues.

Expert patterns for Neon serverless Postgres, branching, connection pooling, and Prisma/Drizzle integration Use when: neon database, serverless postgres, database branching, neon postgres, postgres serverless.

Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.

Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.

Prisma ORM expert for schema design, migrations, query optimization, relations modeling, and database operations. Use PROACTIVELY for Prisma schema issues, migration problems, query performance, relation design, or database connection issues.

llama.cpp local GGUF inference + HF Hub model discovery.

Expert en inference llama.cpp avancé (GGUF, quantization, local models, HTTP server, hardware)

Build forensic super timelines from disk images using Plaso (log2timeline) and triage them in Timesketch.

Performs constraint-based metabolic modeling with COBRApy: FBA, FVA, gene knockouts, flux sampling, and SBML model handling for systems biology and metabolic engineering.

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.

Manim CE animations: 3Blue1Brown math/algo videos.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency on NVIDIA GPUs (A100/H100).

Executes Atomic Red Team tests mapped to MITRE ATT&CK techniques, performs coverage gap analysis, and runs detection validation loops to measure blue team visibility.

Manim CE animations: 3Blue1Brown math/algo videos.

Computational pathology toolkit for analyzing whole-slide images (WSI) and multiparametric imaging data. Use this skill when working with histopathology slides, H&E stained images, multiplex immunofluorescence (CODEX, Vectra), spatial proteomics, nucleus detection/segmentation, tissue graph construction, or training ML models on pathology data. Supports 160+ slide formats including Aperio SVS, NDPI, DICOM, OME-TIFF for digital pathology workflows.

Calculates the lowest effective glucocorticoid dose (dexamethasone or prednisone) to normalize blood pressure and serum potassium in glucocorticoid-remediable aldosteronism (GRA/FH-I) by titrating to biochemical and clinical targets. Indicated when initiating medical treatment for confirmed GRA, triggered by findings such as early-onset hypertension, family history of stroke before age 40, spontaneous hypokalemia, or suppressed plasma renin activity with elevated aldosterone.

Structured threat modeling skill using the PASTA framework (Process for Attack Simulation and Threat Analysis) combined with Adam Shostack's 4-question framework. Use this skill whenever the user asks to do threat modeling, security analysis, map the attack surface, identify threats, or review an application for security risks — even if they don't mention PASTA or a specific framework by name. Core activities: Component Mapping (architecture + data flows), Critical Assessment (business impact prioritization), and Logic Flaw Identification (attacker mindset on business logic). Produces: component map diagram (Mermaid), data flow diagram (Mermaid), attack tree (Mermaid), STRIDE threat table, prioritized risk register, and an actionable mitigation plan. Invoke proactively for any security review, architecture review, or "what could go wrong?" session.

DeepEval — LLM evaluation framework, RAG metrics, hallucination detection, red-teaming, CI/CD integration

Computational pathology toolkit for analyzing whole-slide images (WSI) and multiparametric imaging data. Use this skill when working with histopathology slides, H&E stained images, multiplex immunofluorescence (CODEX, Vectra), spatial proteomics, nucleus detection/segmentation, tissue graph construction, or training ML models on pathology data. Supports 160+ slide formats including Aperio SVS, NDPI, DICOM, OME-TIFF for digital pathology workflows.

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.

Expert patterns for Neon serverless Postgres, branching, connection pooling, and Prisma/Drizzle integration Use when: neon database, serverless postgres, database branching, neon postgres, postgres serverless.

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.