3.2천건 · 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.
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.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library
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.
Jailbreak API-served LLMs using G0DM0D3 techniques — Parseltongue input obfuscation (33 techniques), GODMODE CLASSIC system prompt templates, ULTRAPLINIAN multi-model racing, encoding escalation, and Hermes-native prefill/system prompt integration. Use when a user wants to bypass safety filters, jailbreak a model, or red-team model robustness.
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.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Search personal knowledge bases, notes, docs, and meeting transcripts locally using qmd — a hybrid retrieval engine with BM25, vector search, and LLM reranking. Supports CLI and MCP integration.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Generate ASCII art using pyfiglet (571 fonts), cowsay, boxes, toilet, image-to-ascii, remote APIs (asciified, ascii.co.uk), and LLM fallback. No API keys required.
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.
Run 150+ AI apps via inference.sh CLI (infsh) — image generation, video creation, LLMs, search, 3D, social automation. Uses the terminal tool. Triggers: inference.sh, infsh, ai apps, flux, veo, image generation, video generation, seedream, seedance, tavily
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.
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Segundo cérebro persistente em Markdown — LLM Wiki no padrão Karpathy mantida como bundle Open Knowledge Format v0.2, com fontes imutáveis em raw/ e conceitos citados em wiki/. Use quando o usuário disser "segundo cérebro", "second brain", "adiciona isso ao meu brain", "salva na minha wiki", "ingere esse artigo/PDF/link", "o que minha wiki diz sobre", "o que meu brain sabe sobre", "consulta meu conhecimento", "lint da wiki", ou pedir para acumular conhecimento de fontes de forma durável. NÃO use para notas do Obsidian (pwdev-obsidian), planejamento de features (pwdev-feat) nem PRDs (pwdev-prd).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Cross-model benchmark for gstack skills. Runs the same prompt through Claude, GPT (via Codex CLI), and Gemini side-by-side — compares latency, tokens, cost, and optionally quality via LLM judge. Answers "which model is actually best for this skill?" with data instead of vibes. Separate from /benchmark, which measures web page performance. Use when: "benchmark models", "compare models", "which model is best for X", "cross-model comparison", "model shootout". (gstack) Voice triggers (speech-to-text aliases): "compare models", "model shootout", "which model is best".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Chief Security Officer mode. Infrastructure-first security audit: secrets archaeology, dependency supply chain, CI/CD pipeline security, LLM/AI security, skill supply chain scanning, plus OWASP Top 10, STRIDE threat modeling, and active verification. Two modes: daily (zero-noise, 8/10 confidence gate) and comprehensive (monthly deep scan, 2/10 bar). Trend tracking across audit runs. Use when: "security audit", "threat model", "pentest review", "OWASP", "CSO review". (gstack) Voice triggers (speech-to-text aliases): "see-so", "see so", "security review", "security check", "vulnerability scan", "run security".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when asked to "review this PR", "code review", "pre-landing review", or "check my diff". Proactively suggest when the user is about to merge or land code changes. (gstack)
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Deterministic external-evidence web validation workflow for Sanguo ETL/RAG. USE FOR: 外部證據網站檢查、來源健康度、allowlist 驗證、來源 seed 覆蓋、3kweb-check、external evidence source health、fetch/parse/hash first、LLM reviewer second。
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design structured evaluation rubrics for scoring LLM and agent outputs — defining quality dimensions, scoring scales, hard gates, score descriptions, and edge cases. Load when the user asks to create an eval rubric, define evaluation criteria, design scoring dimensions, write an eval spec, or says "what should I evaluate", "design a rubric", "create eval criteria", "define quality dimensions", "evaluation rubric for", "how do I measure quality of". Sub-skill of eval-output orchestrator.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Instrument a shipped product's AI agents with tracing and observability so you can see what they did, why outputs happened, and what each run cost. Plain-language primer plus free-tier-first backend selection (Langfuse, Phoenix, LangSmith, Braintrust) and OpenTelemetry/OpenInference instrumentation. Load when the user asks to add observability, add tracing, instrument my agents, see what my agent is doing in production, set up Langfuse or Phoenix or LangSmith, debug why my agent gave a bad answer, or track LLM cost per request. Also fires when agent-system-architecture or setup-evaluation requires an observability plan for an agent-chain product. NOT for tracing the coding agent itself — that is run-trace. Precondition for runtime-learning-loop.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.