Results for “rhel”

Train LLMs with reinforcement learning using verl (Volcano Engine RL), supporting RLHF, GRPO, PPO, and other algorithms for scalable post-training with flexible infrastructure backends.

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

Provides storage and environment conventions for NeMo-RL agents on Brev instances, ensuring large experiment outputs go to /ephemeral and secrets are loaded from .env.

Launch, monitor, stop, and debug NeMo-RL recipes on a Kubernetes cluster using the nrl-k8s CLI, supporting ephemeral and long-lived RayCluster modes.

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning) with support for SFT, DPO, GRPO, KTO, RLOO, and reward model training via CLI commands.

Optimize React and Next.js applications with 70 performance rules across 8 categories, prioritized by impact for automated refactoring and code generation.

Guides agents through the full lifecycle of NeMo-RL experiments: understanding recipes, launching reproducible runs, analyzing results, and preserving human oversight with git and TSV logs.

Debug local web or Electron apps interactively using a persistent Playwright session with js_repl, enabling fast iterative UI debugging and visual QA.

Evaluates RAG pipelines using a filesystem-based benchmark with corpus/ and train.json, running evaluate_rag.py to tune retrieval and generation flags and interpret RAGAS metrics.

Expert guidance for implementing GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

Optimizes React and Next.js performance with 69 prioritized rules covering waterfalls, bundle size, server-side rendering, and re-rendering patterns.

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

Resolves legacy references to the vercel-react-expert capability by routing to the current runtime agent, plugin, or narrower skill.

Fine-tune and align language models using reinforcement learning with TRL, including SFT, DPO, PPO, GRPO, and reward model training.

Crl reference tool. Use when working with crl in security contexts.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Imported skill metadata from vercel

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Identify, assess, and mitigate project risks across technical, scope, dependency, and timeline categories using a structured register and escalation rules.

Query, search, and download public datasets from the City of Raleigh Open Data portal. Use this whenever someone wants to explore city data — crime reports, food inspections, building permits, bike lanes, parks, zoning, traffic, budgets, or any of 200+ public datasets.

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

Regex/parser/DSL design specialist for grammar authoring and ReDoS-safe regex. Not for REST APIs (Gateway) or DB schemas (Schema).

Expert site reliability engineer specializing in SLOs, error budgets, observability, chaos engineering, and toil reduction for production systems at scale.

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

Imported skill agents from vercel

Train reinforcement learning models using torchforge, Meta's PyTorch-native RL library for scalable, algorithm-focused experimentation with GRPO, DAPO, and custom loss functions.

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

Safety guardrails for autonomous agents. Intercepts destructive actions and vets skills, requires structured approval before irreversible operations, with CLI-backed cryptographic audit trails and policy enforcement.

Queue processing with fresh context per phase. Processes N tasks from the queue, spawning isolated subagents to prevent context contamination. Supports serial, parallel, batch filter, and dry run modes. Triggers on "/ralph", "/ralph N", "process queue", "run pipeline tasks".

RAG with Vllm. building RAG systems.

React and Next.js performance optimization guidelines from Vercel Engineering. Use this skill when writing, reviewing, or refactoring React/Next.js code. Apply it proactively whenever working on React components, Next.js pages, API routes, data fetching (server or client), bundle size, rendering performance, re-renders, server actions, hydration, animations, or JavaScript optimizations. If the code involves React or Next.js, use this skill — even if performance isn't the stated goal, these patterns prevent issues before they arise.

rustls — modern, safe TLS implementation in pure Rust. Drop-in replacement for OpenSSL/native-tls in Rust apps. No C dependencies — perfect for mobile cross- compile and embedded targets. Covers ClientConfig + ServerConfig, certificate verification with webpki-roots, mTLS, custom verifier (cert pinning), ALPN negotiation (HTTP/2, HTTP/3), session resumption, integration with hyper + reqwest + tokio. USE WHEN: user mentions "rustls", "ClientConfig", "ServerConfig", "webpki-roots", "rustls-pemfile", "rustls cert pinning", "rustls mTLS", "rustls Tokio", "rustls hyper" DO NOT USE FOR: OpenSSL specifics - use OpenSSL skill (or platform TLS) DO NOT USE FOR: Apple/Windows native TLS - use platform-specific skills DO NOT USE FOR: Tor anonymous transport - use `network/arti` DO NOT USE FOR: TLS protocol theory - use OWASP / RFC docs