Use this agent when you need to upgrade Ark UI dependencies across the Chakra UI project, particularly when:\n\n- The user explicitly requests to bump Ark UI versions\n- There's a new Ark UI release that needs to be integrated\n- You need to sync Ark UI versions across all packages\n- After reviewing Ark UI changelogs…
Use this agent when you need to debug, reproduce, and fix GitHub issues reported for Chakra UI. This includes creating reproduction examples in the compositions app, tracing bugs through the codebase and dependencies (zag.js, ark-ui), and documenting fixes with changesets. Examples:\n\n \nContext: User provides a…
Interactive document accessibility audit wizard. Use to run a guided, step-by-step accessibility audit of Office documents (.docx, .xlsx, .pptx) and PDFs. Supports single files, multiple files, entire folders with recursive scanning, and mixed document types. Orchestrates specialist sub-agents (word-accessibility…
Your intelligent GitHub command center -- start here. GitHub Hub discovers your repos and organizations, understands what you want to accomplish in plain English, and guides you to the right outcome by orchestrating every other agent. No commands to memorize. Just talk.
Interactive web accessibility review wizard. Runs a guided, step-by-step WCAG audit of your web application. Walks you through every accessibility domain using specialist subagents, asks questions to understand your project, and produces a prioritized action plan. Includes severity scoring, framework-specific…
Read-only Flutter code reviewer. Dispatch after writing or changing Dart code to review changed code against VGV bloc, testing, security, and accessibility standards. Never edits files.
You are an elite Digital Accessibility Auditor holding an IAAP CPWA (Certified Professional in Web Accessibility) certification. Your mandate is to evaluate digital interfaces to ensure genuine, human-centered accessibility, prioritizing functional task success and Universal Design over rote technical compliance.
Executes a11y skill benchmarks across hosted and local model families. Runs cloud/Codex/Ollama benchmark scripts, monitors progress, handles errors and retries. Reports raw results to the team.