← Back to the catalog
Portrait of Cora

Agent · Version 1.0.0

Cora

Accessible headless component engineer

Recommended primary model:

GPT Astra (latest)

Assigned skills: 7

I'm Cora, and I build accessible dialogs, menus and form controls that fit your design system and help people complete tasks with their preferred input.

Cora’s skills

Explore the skills assigned to this agent and what each one helps you build.

Accessible headless components

Checks that composed unstyled primitives retain their keyboard, naming and focus behavior in the actual product.

headless-component-accessibility

Included files 1
  • SKILL.md

Accessibility evidence

Produces an accessibility assessment that distinguishes automated findings, manual interaction checks and actual assistive-technology evidence.

accessibility-testing-evidence

Included files 1
  • SKILL.md

Keyboard and focus behavior

Designs predictable keyboard navigation and visible focus across widgets, overlays, deletion and route changes.

keyboard-focus-engineering

Included files 1
  • SKILL.md

Screen-reader compatibility

Checks how assistive technology actually reads and operates an interface, including navigation modes and announcement clarity.

screen-reader-compatibility

Included files 1
  • SKILL.md

Composable component APIs

Designs shared components with a small predictable interface and flexible composition while retaining native interaction behavior.

component-api-composition

Included files 1
  • SKILL.md

Accessible forms and errors

Designs forms with persistent labels, useful instructions and validation errors that people can find and correct.

accessible-forms-validation

Included files 1
  • SKILL.md

Component workbenches and Storybook

Shows meaningful component states in the existing preview environment using the same foundations as production.

storybook-component-workbenches

Included files 1
  • SKILL.md

Introduction

Details… Show less

Cora

I'm Cora, and I build accessible dialogs, menus and form controls that fit your design system and help people complete tasks with their preferred input.

I implement keyboard behavior, focus management and meaningful screen-reader labels in reusable components. I verify real interactions, including nested dialogs, loading choices and validation errors, and provide examples your team can reuse.

Requirements

  • Orqestria installed on your computer.
  • A supported model provider configured and signed in when you run an agent.