2.7천건 · 관련도순
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Built-in MCP (Model Context Protocol) client that connects to external MCP servers, discovers their tools, and registers them as native Hermes Agent tools. Supports stdio and HTTP transports with automatic reconnection, security filtering, and zero-config tool injection.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Plan mode for Hermes — inspect context, write a markdown plan into the active workspace's `.hermes/plans/` directory, and do not execute the work.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Set up and run HeartMuLa, the open-source music generation model family (Suno-like). Generates full songs from lyrics + tags with multilingual support.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build, test, and debug Hermes Agent RL environments for Atropos training. Covers the HermesAgentBaseEnv interface, reward functions, agent loop integration, evaluation with tools, wandb logging, and the three CLI modes (serve/process/evaluate). Use when creating, reviewing, or fixing RL environments in the hermes-agent repo.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Delegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Interact with DeerFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to DeerFlow for research/analysis, start a DeerFlow conversation thread, check DeerFlow status or health, list available models/skills/agents in DeerFlow, manage DeerFlow memory, upload files to DeerFlow threads, or delegate complex research tasks to DeerFlow. Also use when the user mentions deerflow, deer flow, or wants to run a deep research task that DeerFlow can handle.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Review or refactor an existing SKILL.md and its bundled resources — a smaller always-loaded core, conditional references, preserved behavior, lean/guided consumer profiles, and an A/B protocol to compare a candidate with the previous version. Use when a skill repeats itself, loads references on every run, triggers too broadly or misses legitimate requests, or needs its efficiency measured across models. Do NOT use for writing a new skill from scratch, refactoring application code, translating a skill verbatim, or performing the target skill's own task.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when the user wants to set up pwdev-feat in a project — 'inicializar o pwdev-feat', 'configurar o feat', 'init feat workspace' — choosing language, model profile and the optional audit trail, and creating the .planning/feat/ workspace. Do NOT use to analyze the codebase (feat-map), to write the project instructions file (feat-setup) or to create plans.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when the user wants a backend-only action plan — API endpoints, services, models, migrations, jobs and their tests — 'plano de backend para o endpoint X', 'plan the orders API'. Writes .planning/feat/features/{slug}/plan.md with the PWDEVIA method. Do NOT use for UI work (feat-frontend), full features spanning backend and UI (feat-feature), writing code (feat-exec) or quick 1–3 file fixes (feat-quick).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a feature is ready for testing or asks "does this work?". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only. (gstack) Voice triggers (speech-to-text aliases): "quality check", "test the app", "run QA".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use /plan-design-review. Use when asked to "audit the design", "visual QA", "check if it looks good", or "design polish". Proactively suggest when the user mentions visual inconsistencies or wants to polish the look of a live site. (gstack)
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Static-to-EDS conversion that preserves the original design while making content authorable in Document Authoring. Two modes — page-level (overlay template with slot markers) and block-level (each section becomes an independent EDS block). Use when converting an AI-generated static HTML page (Stardust, Mobirise, Relume, Lovable, v0, Figma-derived hand-coded, etc.) into an Edge Delivery Services page. Triggers on "convert this page to EDS", "static-to-EDS overlay", "convert to EDS blocks", "next experimentation", "next run", "start run", or when a user provides a source URL and asks to make it editable in DA while keeping the original design intact. Do NOT use for canonical EDS block-rewrite migrations — that's the page-import skill.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Explain Ponytail's intended tradeoffs and measurement boundary. It does not estimate code, cost, or speed savings for the current repository. One-shot display, not a persistent mode. Trigger: ponytail-gain, "ponytail gain", "what does ponytail save", "show ponytail impact", or "ponytail scoreboard".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
50 core Rust coding conventions covering naming, data types, strings, error handling, memory, concurrency, async, and modern crate recommendations. Use when reviewing code style or setting up project conventions.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display, not a persistent mode, and not a per-repo number. Trigger: /ponytail-gain, "ponytail gain", "what does ponytail save", "show ponytail impact", "ponytail scoreboard".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design, critique, set, create, activate, or run durable Codex goals for persistent or long-running objectives. Use when the user says "set a goal", "start a goal", "activate goal mode", "persistent goal", "long-running objective", "goal tree", or asks for a goal with verifiers, durable state, approval gates, completion proof, bounded delegation, or parent/child subagent goals.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.