3.2천건 · 관련도순
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.
Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Focused Signals scout for PostHog projects running Replay Vision scanners — the standing LLM probes that watch session recordings and write `$recording_observed` events. Watches two promises: that enabled scanners are actually observing (throughput / success-rate cliffs, exhausted quota — a silent watch gap), and that what the scanners see in aggregate gets surfaced (a monitor's `yes`-rate or a scorer's score stepping away from its own baseline, a classifier tag or a recurring summarizer theme concentrating across many sessions). It is the agentic pull complement to the per-session push path: scanners with `emits_signals` already emit one signal per session into this same inbox, so this scout never repeats them — it adds the cross-session shape the per-session probe can't see. Emits findings only when they clear the confidence bar; otherwise writes durable memory and closes out empty. Self-contained peer in the signals-scout-* fleet.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Required reading before writing any HogQL/SQL or calling execute-sql against PostHog. Use whenever the user wants to search, find, or do complex aggregations PostHog entities (insights, dashboards, cohorts, feature flags, experiments, surveys, hog flows, data warehouse, persons, etc.) and query analytics data (trends, funnels, retention, lifecycle, paths, stickiness, web analytics, error tracking, logs, sessions, LLM traces). Covers HogQL syntax differences from ClickHouse SQL, system table schemas (system.*), available functions, query examples, and the schema-discovery workflow.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Focused Signals scout for PostHog projects using AI observability. Rotates through a set of lenses — cost, latency, errors, volume, eval performance, eval/enrichment config, clusters, and tool usage — watching each for trends and spikes sliced by the dimensions it discovers over time. Leans on the sandbox's bundled `exploring-llm-*` deep-dive skills for the actual queries. Emits findings only when they clear the confidence bar; otherwise writes durable memory and closes out empty. Self-contained peer in the signals-scout-* fleet — no dependencies on other scouts.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Write effective prompts for LLMs — structure, few-shot examples, chain-of-thought, system prompts, and output parsing.
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.
Create a recurring AI-generated PostHog report — schedule a free-text prompt to run on a cron, with the LLM-synthesized markdown delivered to email or Slack on each tick. Use when the user wants a recurring AI summary of X on any cadence (daily, weekly, monthly, yearly) rather than a one-off report. (To attach an AI summary to an existing insight/dashboard subscription instead of a free-text prompt, see `managing-subscriptions` and its `summary_enabled` option.)
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Strategic clinical trial design feasibility assessment. Analyzes 6 dimensions (endpoint, population, comparator, effect size, duration, regulatory pathway) using precedent trials and FDA guidance. Produces enrollment projections, endpoint recommendations, and approval-pathway analysis. Use for trial-protocol design, power/sample-size estimation, comparator selection, and FDA submission strategy. Driven by precedent-based reasoning rather than first-principles math.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build training datasets for LLM specialization from production data, frontier model distillation, and synthetic bootstrapping. Use when formatting production logs into SFT data, distilling from frontier APIs, or preparing data for fine-tuning. Covers JSONL formatting, data quality validation, deduplication, and train/eval splitting.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Cost modeling and ROI analysis for specialized LLM development. Use when deciding whether to train a custom model, estimating total cost, or calculating break-even vs frontier APIs. Covers training costs, inference costs, and time-to-ROI projections.
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.
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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.
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.
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.
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.
Generate the success criteria for a task or question, then review work against them. Given a task, goal, or open-ended question, decompose it into scenarios, evaluation perspectives, and fine-grained weighted YES/NO criteria using the Recursive Expansion Tree (RET) method; if work is supplied, score it criterion-by-criterion and surface what is missing or could be better. Use when asked to self-review or check your own work, judge whether a task is done well or completely, build a definition-of-done or completeness checklist, create an evaluation rubric or grading criteria, score or grade answers to a question, set up an LLM-as-judge rubric, or when the user mentions self-review, completeness check, success criteria, evaluation criteria, scoring rubric, Qworld, or the RET algorithm.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.