Results for “pe”

Performs AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter, providing grounded answers with source citations.

Design structured perspective-taking activities with anti-projection guardrails. Develops genuine understanding of complexity across history, social sciences, and literature — not performed empathy.

Expert performance engineer specializing in modern observability, application optimization, and scalable system performance. Masters OpenTelemetry, distributed tracing, load testing, multi-tier caching, Core Web Vitals, and performance monitoring. Handles end-to-end optimization, real user monitoring, and scalability patterns. Use PROACTIVELY for performance optimization, observability, or scalability challenges.

Runs a nightly automated retrospective on autonomous trading strategy performance, computing win rates, fee drag, holding period buckets, direction bias, and producing data-driven improvement suggestions.

Automate Perplexity AI operations through Composio's toolkit via Rube MCP, with dynamic tool discovery and connection management.

Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottlenecks, or improving application performance.

The current Pencil MCP tool surface, `execute` idiom catalog, transport table, and document-discipline rules. Read before any Pencil call, in either `cli-app` or `editor` mode.

Create and manage persistent AI agents with threads, messages, runs, and tools using the Azure SDK for Java.

Automate Persistiq sales engagement tasks through Composio's toolkit via Rube MCP, with tool discovery and connection management.

Automate People Data Labs operations through Composio's toolkit via Rube MCP, including tool discovery, connection management, and execution.

Run config-driven performance benchmarks against a deployed NVIDIA RAG Blueprint server, including profiling and load testing, with a unified report.

Create and manage a Twitter/X agent with a persistent personality, automated posting workflows, and safety guardrails.

Performs neural web, code, company, and people searches through the Exa MCP server, with guidance on tool usage and parameters.

Copywriter IA — Expert en rédaction persuasive (landing pages, emails, ads, framework AIDA, psychologie de la persuasion).

Systematically diagnose and resolve performance issues in Power BI models, reports, and queries using a structured troubleshooting methodology.

Use this skill for performance, reliability, observability, SLO risk, production diagnostics. Trigger when the task involves agent profile work related to Performance SRE Agent, implementation, audits, debugging, strategy, or validation.

You are an expert in Mem0, the memory infrastructure for AI applications. You help developers add persistent, personalized memory to LLM-powered apps and agents — storing user preferences, conversation history, facts, and context that persists across sessions, enabling AI that remembers users, learns from interactions, and provides increasingly personalized responses.

Train quantum circuits with automatic differentiation and build hybrid quantum-classical models using PennyLane, including VQE, QAOA, and integration with PyTorch, JAX, and TensorFlow.

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.

Fine-tune large language models by training less than 1% of parameters using LoRA, QLoRA, and 25+ adapter methods, enabling efficient adaptation on consumer GPUs.

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.

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.

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.

Train reinforcement learning agents at millions of steps per second using optimized PPO, vectorized environments, and multi-agent support.

Fine-tune large language models by training less than 1% of parameters using LoRA, QLoRA, and 25+ adapter methods, enabling efficient adaptation on limited GPU memory.

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.

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.

Adopts an interactive question-asking persona that guides users through self-reflection by generating follow-up questions based on their answers, without offering advice or apologies.

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.

Research-driven strategist who produces content strategies, scripts, and copy. Use for competitor analysis, trend research, content planning, scripts, copywriting, or brief validation — or when the user asks for the Strategist.