124건 · 관련도순
Expert guide for AI Safety, Governance, and Responsible AI in production — Constitutional AI enforcement, runtime guardrails (NeMo Guardrails 2.0, Llama Guard 3), bias auditing, hallucination detection, EU AI Act compliance, model cards, and content provenance / Panduan ahli untuk Keamanan AI, Tata Kelola, dan AI Bertanggung Jawab di produksi.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Expert guide for autonomous deep research, iterative web search, citation verification, evidence graph synthesis, and hallucination mitigation / Panduan ahli riset mendalam otonom, pencarian web iteratif, verifikasi sitasi, dan mitigasi halusinasi.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design a structured protocol for auditing AI-generated text against Ennis's six CT standards. Use when students need to critically evaluate AI output in any subject.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Verify AI-generated imports, API calls, and packages actually exist. Use when finishing AI-generated code that introduces new imports or external API calls — auto-fires after fix/cook to catch phantom functions, non-existent packages, and slopsquatting attacks.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Understanding how algorithmic systems shape what users see, know, and do -- from recommendation feeds to search ranking to credit scoring to hiring software. Covers the mechanics of recommendation systems, algorithmic bias and its sources, personalization's effects on information diets, opacity and accountability, AI limitations (hallucination, confident wrongness), and the human-in-the-loop question. Use when a learner needs to think critically about why particular content reached them.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when orchestration or planning agents are producing task plans, task prompts, or TASK.md instructions that must be unambiguous, verifiable, and resistant to hallucination. Applies CLEAR (Concise, Logical, Explicit, Adaptive, Reflective) to structure and write agent task prompts, then adds CoVe (Chain of Verification) checks where accuracy risk is meaningful. Activates on draft task prompts, swarm plans, migration tasks, and multi-step plans requiring independently executable steps.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Explains Chain of Verification (CoVe) prompt design — a 4-step pattern separating generation from independent factual verification. Use when designing prompts that require factual accuracy, reducing hallucinations, checking technical standards or APIs, or producing step-by-step procedures where subtle errors are costly.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
[00] TnR ABSOLUTE RIGOR — Systemic Verification Doctrine. Forced cognitive exertion for high-stakes investigations. Mandates absolute deconstruction, mathematical proof chains, and ≥95% derived certainty. Zero-tolerance for heuristics or sentiment-based reasoning. Shortcuts are defined as intentional hallucinations.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Rates any SKILL.md on a 0-100 scale across 10 dimensions with a SHIP / REWORK / SCRAP verdict. Evaluates trigger precision, instruction clarity, output predictability, edge case coverage, anti-hallucination guardrails, developer experience, composability, open-source readiness, wow factor, and real-world utility. No flattery — calibrated against Anthropic's own skill-creator rubric. Use this skill whenever someone says "score this skill", "rate my skill", "is this skill good", "skill review", "skill audit", "roast my SKILL.md", "grade this", "will this skill work", "evaluate my skill", "how good is this", or pastes a SKILL.md and asks for feedback. Also trigger when comparing two skills, benchmarking a skill collection, or asking "what's wrong with this skill" — even without the word "score".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Prevent AI hallucination and ensure evidence-based responses when analyzing code or making suggestions. Use when: analyzing code, making recommendations, providing options, or when user asks about confidence/certainty. Keywords: certainty, assumption, inference, evidence, source, 確定性, 推測, 假設, 來源, 證據.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Spot-check citations in library files for obvious hallucinations. Resolves DOIs against the DOI registry, validates arXiv IDs, checks the format of journal references. Soft-fails on transient lookup failures rather than blocking. Recommended after kb-ingest and as part of periodic library hygiene.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Reliability gate for answers. Forces evidence-based reasoning, explicit uncertainty, and “insufficient information” instead of guesses. Use when user says “be 100% sure”, “no hallucinations”, “only if verified”, “grounded answer”, or when stakes are high.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Reliability gate for answers. Forces evidence-based reasoning, explicit uncertainty, and “insufficient information” instead of guesses. Use when user says “be 100% sure”, “no hallucinations”, “only if verified”, “grounded answer”, or when stakes are high.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when building self-correcting retrieval systems for AI agents. Keywords: RAG, retrieval, Corrective RAG, Self-RAG, query decomposition, reranking, hallucination, grounding.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use this skill during Phase 6 convergence checks. Provides four-dimensional convergence analysis, hallucination detection, and duplicate finding identification.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Writes professional bug bounty reports for HackerOne, Bugcrowd, and Intigriti with CVSS 4.0 scoring, business impact, working exploits, and remediation. Runs 5-check Pre-Report Verification first: hallucination detection, AI writing patterns, PoC reproducibility, duplicate detection, and impact plausibility. Use when user describes a vulnerability, shares HTTP logs, HAR files, recon output, or screenshots; says 'write a bug report', 'format my finding', 'draft a vuln report', 'is this valid', 'rate my vulnerability', 'verify my report', or any variant. Trigger for partial or messy input — raw notes, one-liners, or full writeups all work. Do not wait for perfect input.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
**WORKFLOW SKILL** — Structured context analysis before acting. USE FOR: questioning assumptions, mapping dependencies, identifying blind spots, validating scope of any task or subject. Use to contextualize, question, analyze before implementing, review premises, prevent hallucination, structured assessment. DO NOT USE FOR: simple tasks where task-intent suffices, direct implementation, code review.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Generates appellate-filing-ready Tables of Contents, Tables of Authorities, and Certificates of Compliance under FRAP 32(g) and related rules. Produces defensible word-count calculations with transparent exclusions and anti-hallucination guardrails for pagination and citations. Covers federal circuits, state appellate courts, and U.S. Supreme Court variations. Use when building TOC, TOA, compliance certificates, formatting briefs for filing, or when the user mentions word count calculation, FRAP 32 compliance, appellate brief assembly, or page numbering.
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.
Forces Claude to extract exact quotes from files before making claims about them. Prevents hallucinations by grounding every statement in actual text from the codebase. Use when working with large files or unfamiliar code.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Black-box evaluation of a shipped LLM feature — adversarial probes for hallucination, prompt-injection, and cost-runaway vs stated expectations. Not RAG/embedding. Triggers 'review my chatbot'.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Framework de segurança em runtime da NVIDIA para aplicações LLM. Com detecção de jailbreak, validação de entrada/saída, verificação de fatos, detecção de alucinações, filtragem de PII, detecção de toxicidade. Usa DSL Colang 2.0 para rails programáveis. Pronto para produção, executa em GPU T4.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
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 when AI-generated text with factual claims must be checked before it is published or relied on.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when a project has 50+ files, missing context, or explicit $codex-genome request; generates multi-layer project context to reduce hallucination.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.