Results for “leverly”

This skill should be used when building perpetual trading bots, implementing leverage functionality, or adding position management. Covers Avantis integration, long/short positions, and risk controls.

Automate recruiting workflows in Lever ATS -- manage opportunities, job postings, requisitions, pipeline stages, and candidate tags through the Composio Lever integration.

LEMON v2.0 — The Degen Fader. Identifies historically reckless traders (DEGEN activity + CHOPPY consistency) on Hyperliquid, monitors their live positions, and counter-trades them when they're bleeding at high leverage. If a cluster of degens goes max-leverage long on a coin and starts losing, LEMON shorts it — betting on their inevitable liquidation cascade. DSL exit managed by plugin runtime via runtime.yaml.

Hyperliquid L1 reference for Dwellir endpoints: HyperEVM JSON-RPC, Info API proxy, gRPC L1 streaming, order book WebSocket, dedicated nodes, and trading patterns. Covers HyperCore trading layer, HyperEVM smart contracts (chain ID 999), market data queries, perpetuals metadata, spot markets, and best practices. Use when working with Hyperliquid, HYPE, HyperEVM, HyperCore, perpetual futures, order books, funding rates, or Hyperliquid trading through Dwellir. Triggers on mentions of hyperliquid, HYPE, HyperEVM, HyperCore, order book, perpetuals, funding rate, l2Book, l4Book, gRPC streaming, nanoreth, or hyperliquid trading.

Performs web search, content extraction, site crawling, URL discovery, and deep research via the Tavily CLI, returning JSON for LLM consumption.

Extracts clean markdown or text from one or more URLs using the Tavily CLI, with support for JavaScript-rendered pages and query-focused chunking.

Search the web with LLM-optimized results via the Tavily CLI, returning relevant snippets, relevance scores, and metadata. Supports domain filtering, time ranges, and multiple search depths.

Serve LLMs and VLMs on NVIDIA Jetson devices using vLLM or SGLang with optimized Docker containers and quantization presets.

Deploy applications and websites to Vercel as preview or production deployments.

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.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

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.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

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.

Merlin Chain: largest Bitcoin L2 by TVL (2026), ZK rollup with EVM, 150+ dApps. Federation peg with planned trust-minimization. USE WHEN: evaluating Merlin for deployment, BTC DeFi.

Manages and analyzes Ably real-time messaging resources, covering channels, presence, connections, usage analytics, and account health via REST and Control APIs.

Runs the open-source LLaVA vision-language model for image understanding, captioning, visual question answering, and multi-turn image conversations, including setup, inference, and training guidance.

AI-optimized web search using the Tavily API for current events, domain-filtered research, answer summaries, and raw content extraction. Use when live web research needs cleaner LLM-ready results than generic search.

Manages automated dynamic/trailing stop losses (DSL only) for leveraged perpetual positions on Hyperliquid. Default mode: High Water (pct_of_high_water) — the trailing floor is a percentage of the peak ROE, recalculated every tick, no ceiling. Also supports fixed ROE tiers for legacy positions. Monitors price via cron, ratchets profit floors through configurable tiers, syncs the stop loss to Hyperliquid via edit_position, and auto-closes positions on breach via mcporter. Supports LONG and SHORT, strategy-scoped state isolation, and automatic cleanup.

WOLF v6.3 — Fully autonomous multi-strategy trading for Hyperliquid perps via Senpi MCP. Manages multiple strategies simultaneously, each with independent wallets, budgets, slots, and DSL configs. 5+N cron architecture: 5 shared wolf crons (Emerging Movers 3min, SM Flip 5min, Watchdog 5min, Risk Guardian 5min, Health Check 10min) plus one DSL v5.2 cron per strategy (native Hyperliquid SL sync via dsl-dynamic-stop-loss skill v5.3.1). Same asset can be traded in different strategies simultaneously. Enter early on first jumps, not at confirmed peaks. Dynamic risk-based leverage per strategy. Requires Senpi MCP connection, python3, mcporter CLI, OpenClaw cron system, and dsl-dynamic-stop-loss skill (provides dsl-cli.py + dsl-v5.py).

Agent validation overhaul: reward weight overrides, fitness decline gate, pinned data, staged experiments

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

贺炜（体育解说）认知与表达框架（压缩蒸馏）：文学比喻嵌入赛况、克制激情、终场金句… 触发：足球诗人解说 等。非煽动球迷对立

Enforces an algorithm-first discipline: state Big-O, data structure, and algorithm family before writing loops, queries, or recursion to catch O(n²), N+1, and brute-force defaults.

AI-optimized web search using Tavily Search API. Use when you need comprehensive web research, current events lookup, domain-specific search, or AI-generated answer summaries. Tavily is optimized for LLM consumption with clean structured results, answer generation, and raw content extraction. Best for research tasks, news queries, fact-checking, and gathering authoritative sources.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

AI-optimized web search using Tavily Search API. Use when you need comprehensive web research, current events lookup, domain-specific search, or AI-generated answer summaries. Tavily is optimized for LLM consumption with clean structured results, answer generation, and raw content extraction. Best for research tasks, news queries, fact-checking, and gathering authoritative sources.

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

Enables visual instruction tuning and image-based conversations using open-source vision-language models. Supports multi-turn image chat, visual question answering, and image understanding tasks.

Design a wise systems intervention from an existing analysis. Maps proposed actions against Meadows' leverage points, checks for unintended consequences, and generates alternatives.

Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.

Implements real-time pub/sub messaging with Ably's edge infrastructure, covering presence, message history, and token authentication.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

KV cache compression for LLM inference — 4.4x compression, 2x context capacity, near-lossless quality. ICLR 2026 paper implementation with vLLM integration.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.