Skill UI

A specialized skill for architecting, building, and productionizing complex Agent Development Kit (ADK) agents and multi-agent systems. This process emphasizes best practices, including clean module structure, robust tool integration, comprehensive regression testing, and deployment automation for reliable, shippable AI solutions. Use this when requiring the creation of structured, enterprise-grade agent code.

Design multi-agent system architectures using patterns like supervisor, swarm, and pipeline. Generate provider-ready tool schemas for Anthropic and OpenAI. Evaluate execution logs to identify bottlenecks, latency, and costs. Use for complex agent workflows requiring structured design and optimization, not simple automation scripts.

A systematic workflow designed to significantly improve the reliability and performance of existing AI agents. It covers detailed performance analysis, including gathering metrics (e.g., task success rate, latency), classifying failure modes, and advanced prompt engineering techniques (like Chain-of-Thought and Constitutional AI). The process culminates in structured A/B testing and controlled deployment, ensuring measurable, robust improvements.

This skill defines the coordination protocol for multi-agent execution during development sprints. It governs how project architects must spawn specialized agents (e.g., backend, frontend, QA), manage dependencies via shared contracts, and collect comprehensive, structured reports. It ensures systematic, parallel, and controlled project iteration development.

Guide to automate Agenty tasks through Composio’s Agenty toolkit by orchestrating Rube MCP workflows, ensuring schema discovery, connection checks, and structured tool execution.

Analyzes application logs to spot slow requests, recurring errors, and resource warnings, helping troubleshoot performance issues and inform structured logging or monitoring improvements.

Analyzes application logs to spot slow requests, recurring errors, and resource warnings, helping troubleshoot performance issues and inform structured logging or monitoring improvements.

Guides a structured walkthrough for onboarding into unfamiliar codebases by covering quick overviews, stack detection, directory mapping, pattern spotting, workflow checks, and summary reporting so teams can answer "how does this work" with confidence.

Automate Apify web scraping Actors inside Claude Code to run crawlers synchronously or asynchronously, manage datasets, inspect logs, create reusable tasks, and pull structured results without leaving your workflow.

This tool collects comprehensive diagnostic evidence for troubleshooting issues with the Apollo.io API. It generates a structured JSON bundle containing environment details (Node.js version, platform), connectivity test results, rate limit status, key type verification, and detailed reports on multiple core API endpoints. Essential for preparing detailed support tickets.

A structured runbook for handling Apollo.io API outages and production failures. It guides users through severity classification (P1-P4), quick diagnosis scripting, implementing circuit breakers, and graceful degradation strategies to maintain service availability during incidents.

Implement comprehensive observability for Apollo.io API integrations. This skill provides structured instrumentation covering Prometheus metrics (request count, latency, rate limits, credits used), structured logging with PII redaction, and OpenTelemetry tracing. It ensures reliable tracking of API health, performance, and resource consumption.