Skill UI

Guides building reliable autonomous agents by covering agent loops, goal decomposition, reflection, and tooling patterns while stressing guardrails, human review, and auditability to curb compounding failure rates in production.

A comprehensive system for implementing policy guardrails in data enrichment pipelines. It enforces critical controls including credit spending limits, blocks the enrichment of sensitive PII (e.g., SSN, bank details), and validates input data quality. Essential for maintaining compliance (GDPR/CCPA) and managing costs when processing large volumes of personal and business data.

This skill is designed to configure a Rails project workspace to function correctly within Conductor, a platform for parallel coding agents. It sets up the necessary scaffolding, including `conductor.json`, executable setup scripts, and server scripts. Additionally, it updates critical Rails configuration files (such as Sidekiq, Cable, and development environment settings) to ensure proper environment variable handling, Redis isolation, and port management for reliable parallel agent execution.

This guide details how to implement and handle Documenso webhooks for real-time document lifecycle notifications. Learn to set up secure webhook endpoints to receive critical events—such as document creation, signing completion, rejection, or opening. Use this when you need to trigger automated downstream workflows (e.g., updating CRMs, sending alerts, or logging audit trails) based on any status change in a document signing process.

Mastery of advanced system design patterns, including Event Sourcing, CQRS, and Event-Driven Architecture (EDA). This skill covers designing event stores, building read/write projections, orchestrating sagas, and managing eventual consistency. It is ideal for building complex microservices that require guaranteed audit trails, historical state querying (temporal queries), and robust handling of business workflows with compensating actions.

A comprehensive guardrail system for external search APIs (like Exa). It enforces content safety policies, manages domain access via allow/blocklists, sanitizes queries to prevent misuse, implements result freshness checks, and enforces per-user usage quotas. Essential for building reliable, secure, and cost-controlled integrations.

This skill provides robust, automated guardrails for web scraping pipelines using Firecrawl. It enforces critical policies to ensure compliance and stability, including domain blocklists (preventing scraping prohibited sites), managing API credit budgets, filtering low-quality content (e.g., error pages, thin content), and implementing granular per-domain rate limiting. Use this when building highly reliable, legal, and cost-efficient scraping solutions.

LlamaGuard is Meta’s 7–8B safety-specialized LLM that filters both prompts and responses by classifying six threat categories, enabling fast inference via vLLM/SageMaker and integration into NeMo Guardrails for end-to-end moderation.

Implement robust, structured logging for API requests, capturing performance metrics, correlation IDs, and detailed security audit trails. This skill ensures compliance by handling PII redaction and providing comprehensive, JSON-formatted logs suitable for ELK Stack or Loki. Essential for debugging, performance analysis, and maintaining SOC 2 compliance in distributed microservices.

This comprehensive guide details the workflow, core invariants, and guardrails for developing, modifying, and verifying TypeScript MCP servers and applications using the mcp-use package. It covers everything from project scaffolding and tool referencing to advanced features like authentication and skills over MCP, ensuring developers adhere to the latest architectural best practices.

This comprehensive workflow guide covers all production-ready patterns for Mistral AI chat completions. It demonstrates critical advanced features including multi-turn conversation management, real-time streaming responses, structured JSON output using schemas, and implementing robust guardrails and moderation. Ideal for building scalable, production-grade conversational AI applications and advanced chat interfaces.

NVIDIA’s NeMo Guardrails adds runtime safety rails to LLM apps, covering jailbreak detection, hallucination and fact-checking, PII filtering, and toxicity checks via Colang 2.0 rules and integrations for production use on T4 GPUs.