Results for “support”

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.

Design and ship production-ready MCP servers from OpenAPI contracts instead of hand-written tool wrappers. Supports Python and TypeScript, schema validation, and safe evolution.

Train or fine-tune sentence-transformers models for retrieval, similarity, clustering, classification, and reranking, with support for bi-encoders, cross-encoders, and sparse encoders.

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

Implement and debug network requests, API calls, and data fetching in Expo apps using fetch, React Query, SWR, and Expo Router loaders.

Generate music from text prompts using ElevenLabs Music API, supporting instrumental tracks, songs with lyrics, composition plans, video-to-music, and inpainting.

Build, test, lint, version, and publish production-grade Python libraries to PyPI with support for multiple build backends, versioning strategies, and CI/CD.

Generates customizable prompts for scanning codebases to identify and document high-quality code exemplars, supporting multiple programming languages and configurable analysis depth.

Swap ERC20 tokens across supported chains via OpenSea's cross-chain DEX aggregator. Get quotes with optimal routing, check token balances, and execute swaps.

Creates and manages Twitter/X agents with distinct personalities, storylines, and post-image libraries, including automated posting and multi-agent support.

Downloads YouTube video transcripts/subtitles and cover images by URL or video ID, with support for multiple languages, translation, chapters, and speaker identification.

Perform differential gene expression analysis for bulk RNA-seq data using PyDESeq2, supporting formulaic designs, Wald tests, FDR correction, LFC shrinkage, and result visualization.

Analyzes encryption algorithms, key management, and file encryption routines used by ransomware families to assess decryption feasibility, identify implementation weaknesses, and support recovery efforts.

Generate images using FLUX models via the inference.sh CLI, supporting text-to-image, image-to-image, and LoRA fine-tuning.

Transcribe and translate speech across 99 languages using OpenAI's Whisper model, with support for multiple model sizes, batch processing, and subtitle generation.

Process large-scale ML datasets with distributed streaming execution across CPU/GPU, supporting Parquet, CSV, JSON, images, and integration with PyTorch, TensorFlow, and Ray Train.

Provides expert guidance for fine-tuning LLMs with LLaMA-Factory, covering WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, and multimodal support.

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag) using standardized prompts and metrics. Supports HuggingFace, vLLM, and API backends.

Build and review high-quality technical documentation, including agent instruction files and contributor-governance files, with support for audits, multilingual parity, and sub-agent orchestration.

Converts syllabi, past papers, or notes into a ranked study roadmap ordered by difficulty, with support for theory, numericals, MCQs, coding, and lab prep.

Guides authorized hardware and embedded interface security research including UART/JTAG discovery, debug pad triage, secure boot assessment, and offline firmware extraction support.

Enables AI agents to autonomously pay for APIs and services via HTTP requests to CrowPay, supporting x402 USDC payments and credit card transactions with configurable spending rules.

Swaps or trades tokens on the Base network using the CDP Swap API, supporting USDC, ETH, WETH, and custom contract addresses with configurable slippage.

Track elapsed time from a set epoch with tamper-evident locking, supporting count-up, count-down, and count-between modes, milestones, and email notifications.

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.

Provides chat-based Azure infrastructure assistance using the Azure CLI, supporting read-only queries, auditing, and monitoring of resources, with safe change proposals requiring explicit confirmation.

Orchestrates a strict four-stage shipping pipeline: session critique, validation, commit, and pull request, halting on failure. Supports a critique-only mode for mid-session quality checks.

Batch-converts UI design screenshots into Vue 3 Composition API components, with support for Vant, Element Plus, and Ant Design Vue.

Deploy static websites to IPFS with a single command using PinMe CLI, supporting Vite, React, Vue, Next.js, Angular, and static sites. Returns a preview URL after upload.

Manages SST applications by discovering project config, checking stack status, and inspecting bound resources. Supports deployment, live Lambda debugging, secret management, and multi-stage environments.

Appends a row or multiple rows to a Google Sheets spreadsheet using the gws CLI, with support for simple values or JSON arrays and optional target range.

Generates images, videos, and audio transcripts using fal.ai's API, supporting models like FLUX, Stable Diffusion, and Whisper.

Three-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces a structured verification report with source links for human review.

Use this skill for motion tokens, durations, easing, choreographed transitions, reduced-motion support. Trigger when the task involves ui/ux work related to Motion Design System, production implementation, audits, debugging, strategy, or validation.

Generate changelog entries and GitHub releases from git history. Categorizes commits into features, fixes, breaking changes, and docs. Supports conventional commits, PR-based grouping, and semantic versioning. Creates formatted CHANGELOG.md entries and GitHub releases.

Use when you need to remove adapter sequences from high-throughput sequencing reads, trim low-quality bases, or filter reads by length. Supports single-end and paired-end FASTQ/FASTA input with error-tolerant adapter matching.