Results for “irail”

Queries Belgian railway (NMBS/SNCB) schedules via the iRail CLI, including departures, connections, train compositions, and service disruptions.

Build web interfaces that fuse Swiss typographic design with military terminal aesthetics, using rigid grids, extreme type scale contrast, utilitarian color, and analog degradation effects for data-heavy dashboards, portfolios, or editorial sites.

Check current Railway project status for this directory. Use when user asks "railway status", "is it running", "what's deployed", "deployment status", or about uptime. NOT for variables or configuration queries - use railway-environment skill for those.

Assess AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, and agent tool abuse, with MITRE ATLAS mapping and guardrail recommendations.

Use when planning an IROS project timeline from venue fit through the spring paper deadline, the separate video deadline, the summer review silence, the June notification, the July camera-ready, IEEE Xplore publication, registration, and presentation, with backward-planning offsets for a real-robot paper on the fall IEEE/RSJ calendar.

Irr reference tool. Use when working with irr in finance contexts.

Gerenciar deployments do Railway - visualizar logs, reimplementar, reiniciar ou remover deployments. Use para ciclo de vida de deployment (remover, parar, reimplementar, reiniciar), visibilidade de deployment (listar, status, histórico) e troubleshooting (logs, erros, falhas, travamentos). NÃO é para deletar serviços - use a skill railway-environment com isDeleted para isso.

Add programmable safety guardrails to LLM applications at runtime, including jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, and toxicity detection.

Verificar o status atual do projeto Railway para este diretório. Use quando o usuário perguntar "status railway", "está rodando", "o que está deployado", "status de deployment" ou sobre uptime. NÃO para queries de variáveis ou configuração - use a skill railway-environment para isso.

Optimizes Active Record queries, implements Turbo Frames and Streams, configures Action Cable, sets up Sidekiq workers, and writes RSpec test suites for Rails 7+ applications.

Listar, alternar e configurar projetos do Railway. Use quando o usuário quiser listar todos os projetos, alternar entre projetos, renomear um projeto, ativar/desativar deploys de PR, tornar um projeto público/privado ou modificar configurações do projeto.

Implements AI safety guardrails including input validation, output filtering, robustness testing, human oversight, and monitoring to prevent harmful outputs and ensure system reliability.

Instaura/atua em IRDR — Incidente de Resolucao de Demandas Repetitivas (CPC 976, requisitos simultaneos: I efetiva repeticao sobre questao unicamente de direito + II risco a isonomia/seguranca; legitimados 977; admissibilidade 981; suspensao no Estado/regiao 982 I; tese aplicada a todos e aos casos futuros 985; revisao 986; REsp/RE 987) ou IAC — Incidente de Assuncao de Competencia (CPC 947, questao relevante de grande repercussao social SEM repeticao; acordao vinculante §3), com efeito vinculante da tese (CPC 927 III). Use quando o operador disser IRDR, incidente de resolucao de demandas repetitivas, IAC, assuncao de competencia, tese vinculante regional, muitos processos iguais, suspensao por IRDR.

Adds input and output guardrails to an agent, including validation, content filtering, domain scoping, and rate limiting, with TypeScript examples and wiring instructions.

Builds input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs using NeMo Guardrails, Presidio, and Guardrails AI.

Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.

Deploy code to Railway using "railway up". Use when user wants to push code, says "railway up", "deploy", "ship", or "push". For initial setup or creating services, use railway-new skill. For Docker images, use railway-environment skill.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

Expert en tests d'agents IA (tests unitaires, intégration, régression, guardrails, red teaming agents)

Use this skill when the user asks about International Fuel Tax Agreement (IFTA) compliance — quarterly returns, jurisdiction reporting, fuel + miles reconciliation, IFTA-100/101 forms, base jurisdiction selection, IFTA license + decals, recordkeeping requirements, common IFTA audit findings, or how to handle non-IFTA jurisdictions. Cite IFTA Articles of Agreement.

Template do pack (ai-ml/03-rag-pipeline.md). Orienta o agente em integracao de IA/ML, LLM e pipelines de dados alinhado a esse contexto.

Sets up internationalization by extracting hardcoded user-facing strings to locale files, auto-detecting the framework, configuring the appropriate i18n library, handling pluralization, formatting, and RTL support.

Manage Railway deployments - view logs, redeploy, restart, or remove deployments. Use for deployment lifecycle (remove, stop, redeploy, restart), deployment visibility (list, status, history), and troubleshooting (logs, errors, failures, crashes). NOT for deleting services - use railway-environment skill with isDeleted for that.

Safety guardrails for autonomous agents. Intercepts destructive actions and vets skills, requires structured approval before irreversible operations, with CLI-backed cryptographic audit trails and policy enforcement.

Use this skill to differentiate IFTA (fuel tax) and IRP (apportioned registration). Covers what each is for, deadlines, and how they interact.

AI Safety Specialist IA — Expert en sécurité IA (alignment, guardrails, filtrage de contenu, test de biais, red teaming)

Applies ITIL principles to design scalable, maintainable, and interoperable enterprise systems and solutions.

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.

Check current Railway project status for this directory. Use when user asks "railway status", "is it running", "what's deployed", "deployment status", or about uptime. NOT for variables or configuration queries - use railway-environment skill for those.

Fazer deploy de código para Railway usando "railway up". Use quando o usuário quer enviar código, diz "railway up", "deploy", "ship" ou "push". Para configuração inicial ou criação de serviços, use a skill railway-new. Para imagens Docker, use a skill railway-environment.

Deployment runbook for IntelliVerse Kubernetes services. Use when deploying a new service, updating an existing deployment, rolling back, applying manifests, updating images, scaling, or managing namespaces in the aicart cluster.

Manage Railway deployments - view logs, redeploy, restart, or remove deployments. Use for deployment lifecycle (remove, stop, redeploy, restart), deployment visibility (list, status, history), and troubleshooting (logs, errors, failures, crashes). NOT for deleting services - use railway-environment skill with isDeleted for that.

Debug local web or Electron apps interactively using a persistent Playwright session with js_repl, enabling fast iterative UI debugging and visual QA.

Sync tests with TestRail. Use when user mentions "testrail", "test management", "test cases", "test run", "sync test cases", "push results to testrail", or "import from testrail".

List, switch, and configure Railway projects. Use when user wants to list all projects, switch projects, rename a project, enable/disable PR deploys, make a project public/private, or modify project settings.