guillermoscript

guillermoscript/lms-front

Skill Claude CodeCodex

Adapt designs to work across different screen sizes, devices, contexts, or platforms. Ensures consistent experience across varied environments.

guillermoscript/lms-front

Skill Claude CodeCodex

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

guillermoscript/lms-front

Skill Claude CodeCodex

Create new AI chat interface components for the ai-elements library following established composable patterns, shadcn/ui integration, and Vercel AI SDK conventions. Use when creating new components in packages/elements/src or when the user asks to add a new component to ai-elements.

guillermoscript/lms-front

Skill Claude CodeCodex

Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation features, (3) Have questions about AI providers (OpenAI…

guillermoscript/lms-front

Skill Claude CodeCodex

Review a feature and enhance it with purposeful animations, micro-interactions, and motion effects that improve usability and delight.

guillermoscript/lms-front

Skill Claude CodeCodex

Perform comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates detailed report of issues with severity ratings and recommendations.

guillermoscript/lms-front

Skill Claude CodeCodex

Amplify safe or boring designs to make them more visually interesting and stimulating. Increases impact while maintaining usability.

guillermoscript/lms-front

Skill Claude CodeCodex

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

guillermoscript/lms-front

Skill Claude CodeCodex

Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens"…

guillermoscript/lms-front

Skill Claude CodeCodex

Build, modify, debug, or review ChatGPT Apps with mcp-use.

guillermoscript/lms-front

Skill Claude CodeCodex

Improve unclear UX copy, error messages, microcopy, labels, and instructions. Makes interfaces easier to understand and use.

guillermoscript/lms-front

Skill Claude CodeCodex

Play a sound when a Claude Code turn ends, scaled by how much code was written, plus sounds for commits, pushes, PRs, test runs and permission prompts. Packs (tiktok, zelda, mario) and a rules file make every event remappable. Use when the user wants audio notifications, terminal sounds, asks to customize or mute…

guillermoscript/lms-front

Skill Claude CodeCodex

Add strategic color to features that are too monochromatic or lack visual interest. Makes interfaces more engaging and expressive.

guillermoscript/lms-front

Skill Claude CodeCodex

Evaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emotional resonance, and overall design quality with actionable feedback.

guillermoscript/lms-front

Skill Claude CodeCodex

Add moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful.

guillermoscript/lms-front

Skill Claude CodeCodex

Strip designs to their essence by removing unnecessary complexity. Great design is simple, powerful, and clean.

guillermoscript/lms-front

Skill Claude CodeCodex

Extract and consolidate reusable components, design tokens, and patterns into your design system. Identifies opportunities for systematic reuse and enriches your component library.

guillermoscript/lms-front

Skill Claude CodeCodex

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications. Generates creative, polished code that avoids generic AI aesthetics.

guillermoscript/lms-front

Skill Claude CodeCodex

Operate any GitHub Projects (v2) board by name — add issues/PRs, find existing items, set Status/Priority/Size or any single-select field — without hardcoding field or option IDs. Use whenever the user asks to move an item on a project board ("move.

guillermoscript/lms-front

Skill Claude CodeCodex

Discover the current repo's GitHub-workflow facts — repo name, authenticated gh user, project board, PR template, Slack channel, branch/commit conventions, build/test commands — and cache the non-discoverable ones in /.claude/gh-workflow.config.json so they're asked at most once per repo. Use at the start of any…

guillermoscript/lms-front

Skill Claude CodeCodex

Compact the current conversation into a handoff document for another agent to pick up.

guillermoscript/lms-front

Skill Claude CodeCodex

Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready.

guillermoscript/lms-front

Skill Claude CodeCodex

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security…

guillermoscript/lms-front

Skill Claude CodeCodex

Read a GitHub issue and produce a posted plan of attack — gather the issue with its comments and references, survey the code it touches (read-only), author a short plan (root cause, approach, risks, test plan), then assign the issue, move it to In Progress on the board (if configured), and post the plan as the issue…