21 skills · sorted by relevance
Add safety checks to LLM applications with NeMo Guardrails. This skill guides input and output validation, detection of attempts to bypass safety rules, personal information masking, and checks for unsupported or inaccurate answers.
Configure safety checks for LLM applications with NeMo Guardrails. Covers attempts to bypass safety rules, input and output validation, masking personal information, and checking factual claims through programmable rules and integrations.
Design a fact-checking protocol for AI-generated text, extending SIFT with AI-specific adaptations for hallucination detection. Use when students need to verify AI claims and citations.
The English summary is being prepared. Showing the original description.
Implement comprehensive observability for LLM applications including tracing (Langfuse/Helicone), cost tracking, token optimization, RAG evaluation metrics (RAGAS), hallucination detection, and production monitoring. Essential for debugging, optimizing costs, and ensuring AI output quality. Use when ", llm-monitoring, tracing, langfuse, helicone, cost-tracking, ragas, evaluation, hallucination-detection, prompt-caching" mentioned.
The English summary is being prepared. Showing the original description.
Design a fact-checking protocol for AI-generated text, extending SIFT with AI-specific adaptations for hallucination detection. Use when students need to verify AI claims and citations.
The English summary is being prepared. Showing the original description.
AI situational awareness — internal threat detection for hallucination risk, scope creep, and context degradation. Maps Cooper color codes to reasoning states and OODA loop to real-time decisions. Use during any task where reasoning quality matters, when operating in unfamiliar territory, after detecting early warning signs such as an uncertain fact or suspicious tool result, or before high-stakes output like irreversible changes or architectural decisions.
The English summary is being prepared. Showing the original description.
Build hallucination detection systems for AI. TRIGGERS - Use when user needs help with ai-hallucination-detector related tasks.
The English summary is being prepared. Showing the original description.
Build hallucination detection systems for AI. TRIGGERS - Use when user needs help with ai-hallucination-detector related tasks.
The English summary is being prepared. Showing the original description.
Adversarial verification for AI-generated legal content. Use when fact-checking legal documents, validating citations, detecting hallucinations, scoring document quality, or assessing distribution readiness.
The English summary is being prepared. Showing the original description.
Use this skill during Phase 6 convergence checks. Provides four-dimensional convergence analysis, hallucination detection, and duplicate finding identification.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Assigns confidence scores to agent outputs based on multiple factors including source quality, consistency, and reasoning depth. Produces calibrated confidence estimates. Activate on 'confidence score', 'how confident', 'certainty level', 'output confidence', 'reliability score'. NOT for validation (use dag-output-validator) or hallucination detection (use dag-hallucination-detector).
The English summary is being prepared. Showing the original description.
Validates agent outputs against expected schemas and quality criteria. Ensures outputs meet structural requirements and content standards. Activate on 'validate output', 'output validation', 'schema validation', 'check output', 'output quality'. NOT for confidence scoring (use dag-confidence-scorer) or hallucination detection (use dag-hallucination-detector).
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Use when working with Aws Billing — analyze, break down, and report AWS costs and bills. Covers cost breakdown by service, account, or usage type; monthly/daily billing trends; cost anomaly detection; RI/SP utilization; cost forecasting; credit/discount analysis; and multi-account cost comparison. Uses anti-hallucination rules, mandatory currency/credit detection workflow, and reusable Cost Explorer functions.
The English summary is being prepared. Showing the original description.
Validates agent outputs against expected schemas and quality criteria. Reports structural and content checks within the declared evidence scope. Activate on 'validate output', 'output validation', 'schema validation', 'check output', 'output quality'. NOT for confidence scoring (use dag-confidence-scorer) or hallucination detection (use dag-hallucination-detector).
The English summary is being prepared. Showing the original description.
Monitor and evaluate RAG systems with retrieval quality metrics, groundedness checks, hallucination detection, and continuous regression testing.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Use when working with Gcp Idle Resources — detect unused and idle GCP resources that incur cost without providing value. Covers unattached Persistent Disks, unused external IPs, stopped VMs, idle Cloud NAT, idle load balancers, old snapshots, idle Cloud SQL instances, abandoned GKE node pools, unused VPC connectors, and orphaned Filestore instances. Includes estimated monthly waste per resource and anti-hallucination rules for safe detection.
The English summary is being prepared. Showing the original description.
Use when working with Aws Idle Resources — detect unused and idle AWS resources that incur cost without providing value. Covers detached EBS volumes, idle load balancers, unused Elastic IPs, stopped EC2 instances, idle NAT Gateways, old snapshots, and unused ENIs. Includes estimated monthly waste per resource and anti-hallucination rules for safe detection.
The English summary is being prepared. Showing the original description.