Skill UI

Automates 21risk workflows through Composio's 21risk toolkit via Rube MCP, guiding users to discover tools, verify active connections, and run schema-compliant executions with explicit memory and session management.

Automates creation of acceptance criteria within enterprise workflows, guiding through best practices, generating code and configurations, and validating outputs against standards whenever acceptance criteria creator requests arrive.

Provides WCAG 2.1 based accessibility audit guidance for web interfaces, covering perceivable, operable, understandable, and robust principles along with code snippets for alt text, contrast, keyboard, focus, and media alternatives.

Automates guidance for frontend accessibility audit runners, triggering on relevant requests and offering best practices, production-ready snippets, and validation against accessibility standards.

This expert conducts comprehensive audits to ensure digital products comply with WCAG standards. It specializes in identifying accessibility barriers, testing user experiences for users with disabilities, and providing step-by-step remediation guidance. Use it for auditing web or mobile platforms, establishing compliance, and improving overall inclusivity.

Outlines WCAG 2.2 accessibility patterns for web apps, covering semantic HTML, ARIA roles, keyboard navigation, form handling, and contrast checks to keep interfaces usable for assistive technologies.

Generates production-ready Claude-powered agents with Google’s ADK, bundling React-style loops, tool-augmented capabilities, multi-agent orchestration, workflow automation, and test scaffolding.

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.

Guides connecting Rube MCP to Composio’s Adyntel toolkit, searching for live tool schemas, validating connections, and executing multi-tool workflows while handling session reuse, memory, and pagination requirements.

Guides automating Affinda tasks through Composio's Rube MCP client, detailing connection setup, tool discovery, multi-tool execution, and reminders about schema searches, sessions, and pagination safety.

Automatically detects and loads specialized agent instructions from the `AGENTS.md` file in the current working directory. This skill seamlessly integrates project-specific rules and behavioral guidelines into the AI's session context, ensuring the AI operates according to project standards without manual intervention. It is crucial for maintaining specialized agent behaviors across different development tasks and directory changes.

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.