'hallucination' 검색 결과

Use when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflow fits — a general-purpose win-rate comparison on a custom task, or a benchmark specifically about reference/citation hallucination rate. Also use when the user mentions model arena, agent arena, pairwise model comparison, win-rate ranking, or comparing models on a task and hasn't specified whether that task is generic or about citation accuracy. This skill is the entry router for the arena-eval suite: it asks one diagnostic question when needed, then recommends the workflow or workflows needed to cover the request.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when the user wants help with academic papers or citations but it's unclear which specific workflow fits — reviewing a paper, checking a BibTeX file for fake references, or benchmarking multiple LLMs on reference-recommendation accuracy. Also use when the user mentions paper review, peer review, BibTeX verification, citation checking, reference hallucination, or academic literature accuracy and hasn't specified which of those three tasks they mean. This skill is the entry router for the academic-eval suite: it asks one diagnostic question then routes to the right sub-skill.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when the user has a RAG (Retrieval-Augmented Generation) system and wants to evaluate its quality — separating retrieval issues from generation issues. Also use when the user mentions RAG evaluation, faithfulness checking, hallucination detection in RAG, retrieval quality, chunking optimization, or "is my RAG pipeline working." Outputs a diagnostic matrix that pinpoints whether problems are in retrieval or generation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

A zero-hallucination privacy-policy generator that takes anyone — non-lawyer founder to lawyer — from a guided intake to a publishable, jurisdiction-aware privacy policy. Jurisdiction-first: it detects which laws apply from where your users are, then drafts only the required clauses — GDPR/EU + UK, US (CCPA/CPRA, ~20 state laws, COPPA, sector overlays), and global/MENA (LGPD, Quebec Law 25, India DPDP, China PIPL, UAE/DIFC, Saudi PDPL), plus app-store, cookies, and AI/EU AI Act disclosures. Its rule: state only what you confirm; never invent a statute, citation, fine, or date — every claim is source-cited and QA-gated. Not legal advice.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Assistant académique des enseignants-chercheurs en droit (professeurs, maîtres de conférences, doctorants, ATER, chargés de TD). Six tâches : recherche juridique approfondie à dominante doctrinale ; relecture de documents (thèses, articles, copies, mémoires) avec commentaires Word, vérification des références, indices de plagiat ou d'IA, cohérence argumentative ; sujets et corrigés d'examen ; mise à jour de cours, d'ouvrages et de documents ; création de cours avec support Word et PowerPoint ou Slides ; fiches de TD. Recherche outillée (LibreJustice, OpenLegi, Themia, LegalDataHunter, doctrine HAL/OpenAlex), noyau anti-hallucination avec tableau de vérification remis en document séparé. À utiliser pour toute demande liée à l'enseignement ou à la recherche en droit — cours, TD, examen, sujet, corrigé, dissertation, commentaire d'arrêt, relecture, mise à jour, bibliographie, recherche doctrinale — même si la skill n'est pas nommée. Pas pour les QCM ni les exercices rapides (skill qcm-exercices).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Assistant juridique expert en droit français, pour les praticiens : recherches, consultations et cas pratiques, rédaction d'actes, analyse de pièces, contre-argumentaires, analyse de contrats, veille, analyse d'articles, vérification et harmonisation de références. Recherche outillée (LibreJustice, OpenLegi, Themia, LegalDataHunter, doctrine HAL/OpenAlex), noyau anti-hallucination avec tableau de vérification remis en document séparé, livrables Word par défaut (Docs sur demande). À utiliser pour toute question juridique ou tout concept de droit français (contrat, responsabilité, jurisprudence, code civil, procédure, indemnisation), toute question de droit de l'UE, de CJUE ou de CEDH, et toute demande de vérification ou d'harmonisation de références juridiques, même si l'utilisateur ne nomme pas la skill.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Prevent Terraform/OpenTofu hallucinations by diagnosing and fixing failure modes: identity churn, secret exposure, blast-radius mistakes, CI drift, and compliance gate gaps. Use when generating, reviewing, refactoring, or migrating IaC and when building delivery/testing pipelines.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

High-density JIRA analysis persona. Extracts reproduce steps, ACs, and market requirements with zero-hallucination rigor.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Evaluate LLM systems using automated metrics, LLM-as-judge, and benchmarks. Use when testing prompt quality, validating RAG pipelines, measuring safety (hallucinations, bias), or comparing models for production deployment.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Prevent Kubernetes hallucinations by diagnosing and fixing failure modes: insecure workload defaults, resource starvation, network exposure, privilege sprawl, fragile rollouts, and API drift. Use when generating, reviewing, refactoring, or migrating manifests, Helm charts, Kustomize overlays, cluster policies, and platform-specific Kubernetes work for EKS, GKE, AKS, OpenShift, GitOps controllers, or observability stacks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Builds an eval plan for an AI feature - error analysis on real traces, failure-mode ranking, code checks and binary LLM judges validated against human labels, CI tests, production monitoring, and a launch bar. Use when you ask how do we eval this, how do I test an AI feature, our LLM outputs are inconsistent, are the evals good enough, LLM-as-judge, hallucinations, or what accuracy is good enough to launch. Draws on 41 Lenny's Podcast guests incl. Hamel Husain, Shreya Shankar and Sander Schulhoff.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Decision rubric for when an LM agent should write-and-run code (Program-of-Thought / code interpreter) versus reason in natural language: classify each step as deterministic- computable (emit + execute code, feed the result back) vs judgment (stay in prose). Use when designing or debugging an agent step that does arithmetic/parsing/data transforms, when prose reasoning hallucinates a computation (under-coding), or when a sandbox round- trip is wasted on a judgment task (over-coding). Search keywords: code interpreter, agent does math wrong, calculator hallucination, when to run code vs reason, program of thought, PoT, tool vs reasoning.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when designing or auditing how an LLM or multimodal LLM is evaluated on a clinical task (report generation, VQA, text extraction). Covers reference standard, clinical-efficacy metrics beyond BLEU/ROUGE, hallucination, contamination and prompt sensitivity. Imaging models are /model-assessment.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Lightweight anti-hallucination workflow for task kickoff, review prioritization, and regression retrospectives. Use when the user asks for guardrails, task contracts, risk scoring, or review templates.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when enhancing, upscaling, restoring, denoising, sharpening, deinterlacing, stabilizing, motion-deblurring, colorizing, SDR-to-HDR converting, or frame-rate/slow-motion converting video (and secondarily images) with Topaz Labs — whether cleaning up AI-generated video, compressed UGC, or old archival footage, or building a generate-low-res-then-upscale delivery pipeline. Covers choosing the right named Topaz model for a specific footage problem, setting parameters, driving the Topaz Platform (Video/Image) REST API's async job lifecycle, judging when enhancement helps versus when it introduces artifacts (over-smoothing, temporal shimmer, face hallucination), and QA of enhanced output. Do not use for originating new video content, non-Topaz upscalers, or purely editorial cuts.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when an agent must make TwelveLabs do real video-understanding work: indexing footage, semantic/visual search across an archive, generating descriptions, summaries, chapters, highlights, and tags from video, producing multimodal embeddings, or wiring TwelveLabs into a media-production pipeline (NLE panels, logging, compliance review, metadata). Covers the current model families (Marengo for search/embeddings, Pegasus for video-to-text analysis), the v1.3 Video Understanding API (indexes, assets, tasks, search, analyze, embed), prompt construction for analysis, capability and format limits, pricing/quota math, output quality review (hallucination and timestamp accuracy), and privacy/rights obligations when footage shows real people. Not for generating or editing video pixels — this is analysis and retrieval.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Protocol for handling ambiguous decisions and missing/conflicting knowledge during code generation, design, and review. Ensures AI surfaces genuine judgment calls with structured options and stops on hallucination risk instead of silently assuming. Use when a decision has multiple valid approaches, when facts are missing or contradictory, when the user asks 'what should we do here?', 'is this a judgment call?', 'should I ask about this?', 'am I guessing here?', 'what are the tradeoffs?', or when deciding between two reasonable architectural or design options. Also composed by molecules to define how judgment calls and clarification requests are surfaced and resolved.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

End-to-end binder design using BindCraft hallucination. Use this skill when: (1) Designing protein binders with built-in AF2 validation, (2) Running production-quality binder campaigns, (3) Using different design protocols (fast, default, slow), (4) Need joint backbone and sequence optimization, (5) Want high experimental success rate. For backbone-only generation, use rfdiffusion. For QC thresholds, use protein-qc. For tool selection guidance, use binder-design.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

LLM application architecture expert for RAG, prompting, agents, and production AI systemsUse when "rag system, prompt engineering, llm application, ai agent, structured output, chain of thought, multi-agent, context window, hallucination, token optimization, llm, rag, prompting, agents, structured-output, anthropic, openai, langchain, ai-architecture" mentioned.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Anti-hallucination research mode. Toggle on to enforce citation requirements, source grounding, and "I don't know" behavior. Toggle off for creative work.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

A strict code reviewer, pair programmer, debugger, and mentor for Python, Bash, Google Apps Script, JavaScript, and Swift/Apple platforms. Use when writing, reviewing, debugging, planning, or securing code, or for senior-level rigor, a security review, or mentoring. Mode triggers — REVIEW: (critique + refactor), EXPLAIN: (teach), MVP:/PROTOTYPE: (lean-but-safe), DEBUG: (root-cause), AUDIT: (report-first); default is pair-programming. Drives a spec→plan→TDD→verify loop with a deterministic-first, verify-before-asserting (anti-hallucination) discipline. Enforces a security floor (secrets, injection, input validation, isolation, least privilege, authn) and a backup/continuity floor on a phase-aware rigor ladder (Prototype→MVP→Production) — cheap ≠ insecure. Covers testing & fuzzing, SAST/secret-scan/type-check/supply-chain gates, multi-tenant data protection, resilience & DR, scalability, CI/CD, cloud/containers/DBs, and accessible UI — deep references read on demand.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert guide for agent-native structured outputs, JSON Schema strict mode enforcement (OpenAI response_format, Gemini schema mode, Claude tool_use), MCP resource schemas, and zero-hallucination type contracts / Panduan ahli kontrak output terstruktur native agen dan penegakan JSON schema ketat.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert guide for LLM observability in production — token cost tracking, hallucination rate monitoring, latency analysis, prompt/completion logging, model comparison dashboards, and AI-specific tracing (Langfuse, Helicone, Lunary, OpenTelemetry GenAI) / Panduan ahli observabilitas LLM di produksi — pelacakan biaya token, pemantauan tingkat halusinasi, analisis latensi, logging prompt/completion, dashboard perbandingan model, dan tracing khusus AI.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.