npx agentspec-cli install 12b6cdb4-7547-4f2e-b4c4-2ea2d890a1a4 --file-type copilot-instructions→ .github/instructions/
## Design Context ### Users - **Who**: Evaluators and administrative staff who manage video evaluation assignments. - **Context**: Evaluators spend long uninterrupted hours analyzing video submission applications for admissions, hiring, or continuous program selections. - **Job to be Done**: Review large volumes of applications with faster, consistent, explainable decision-making utilizing a structured workflow (human-in-the-loop AI screening). - **Core Needs & Emotions**: Needs to inspire *focus* and *calm* to reduce cognitive load during long working sessions. The platform should feel sleek, responsive, and trustworthy. ### Brand Personality - **Voice/Tone**: Calm, efficient, AI-unified. - **3-Word Personality**: Dynamic, Adaptive, Sleek. - **Emotional Goals**: To unify the rigorous manual labor of evaluation with intuitive AI capabilities seamlessly, making the review process feel like a high-end, responsive system. ### Aesthetic Direction - **References**: Stripe, Linear (Sleek interfaces with thoughtful macro/micro details, sophisticated shadow work, high performance, and precision typography). - **Anti-references**: None. - **Visual Tone**: Minimalist, uncluttered SaaS interface targeting distraction-free work. - **Theme**: Full support for both **Light** and **Dark Mode** is crucial to aid the long-hours context of evaluators. - **Colors**: No specific brand palette designated yet, so default to neutral, clean, and highly sophisticated semantic colors that adapt beautifully across both light and dark themes. Include a muted subtle accent color reminiscent of a Stripe-like precision. ### Design Principles 1. **Focus First (Minimalism)**: Prioritize core evaluation content with an "invisible" interface to reduce cognitive fatigue over long sessions. Minimize unnecessary chrome and heavy containers. 2. **Sleek & Unifying**: The experience should feel like a premium, dynamic tool mapping the precision of AI to the judgment of a human evaluator. Achieve this through crisp type hierarchy, smooth interactions, and thoughtful micro-animations. 3. **Adaptive Environments**: Provide exceptional Dark Mode and Light Mode support to accommodate long, varying working hours. 4. **Subtle Context Framing**: When surfacing AI scores, timestamp references, and evidence trails, present them inline and transparently (explainable AI) without overwhelming the reviewer. Allow the AI to be an assistant, not an obstacle.
critique
Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, automated anti-pattern detection, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
by AgentHub Crawler
Agentic Browser Automation Configuration
Cursor IDE rules and conventions for AI-assisted development.
by AgentHub Crawler
Gemini Workspace Context: AI Agency
This document provides a comprehensive overview of the AI Agency project, its architecture, and development practices to be used for context in future Gemini conversations.
by AgentHub Crawler
Sign in to leave a comment.
Contexto do Projeto - Domani Fiscal
Sistema de Gestão Fiscal desenvolvido em Flutter para a **Domani Fiscal**. Interface profissional com design moderno, tema claro/escuro, sidebar responsiva com densidade otimizada e sistema completo de formulários e dialogs.
by AgentHub Crawler