Skill UI

Provides comprehensive patterns and techniques for securing AI agent systems. Learn how to enforce governance policies, including tool allow/block lists, content filtering, rate limiting, and human approval workflows. Essential for building robust, compliant, and trustworthy agents in multi-agent or production environments that interact with external APIs and sensitive data.

Conducts comprehensive AI prompt safety reviews that analyze bias, misinformation, injection, and privacy risks while delivering effectiveness evaluations, security guidance, and best-practice recommendations for prompt engineers.

Defines and runs LLM-as-judge evaluators on Arize via ax commands, handling evaluator creation, continuous monitoring, column mapping, trigger runs, and evaluation spans or experiments with configurable templates, models, and query filters.

Use production trace data and the ax CLI to locate LLM prompts, collect annotations/evals, and iterate on prompt templates for data-driven improvements.

Downloads spans, traces, and sessions from Arize via the ax CLI to debug LLM applications, using IDs, filters, sampling rules, and bulk/export safeguards while writing output to .arize-tmp-traces.

Interactive workflow that interrogates scope, deliverables, constraints, and success criteria while guiding users to refine task prompts; copies the final markdown with Joyride clipboard commands and never writes code.

This guide outlines the structure and content guidelines for an AGENTS.md file. This file serves as a comprehensive 'README for agents,' providing detailed, technical context and operational instructions (such as setup, development workflow, testing procedures, and code style) that enable advanced AI coding agents to interact with and understand a codebase effectively. It greatly complements traditional READMEs by focusing purely on machine-readable technical requirements.

Creates a machine-readable specification template tailored for Generative AI solutions, covering purpose, requirements, constraints, interfaces, dependencies, and validation so implementation stays unambiguous.

Automate Datadog monitoring tasks via Rube MCP’s Composio toolkit—query metrics, search logs, manage monitors/dashboards, and create events or downtimes while respecting live tool schemas.

Three-layer verification pipeline that extracts verifiable claims from AI output, searches the web for supporting or contradicting sources, flags hallucinations, and builds structured reports for human review.

Builds an eval-driven QA pipeline for Python LLM apps, instrumenting execution, inserting controlled inputs, running pixie test to score responses via evaluators, and iterating on failures to ensure quality.

FAF Expert configures IANA-registered .faf projects to deliver championship-grade AI-readiness, syncing context across Claude, Cursor, Gemini and more while managing MCP servers, scoring, and legacy modernization via a CLI workflow.