Frontend

Build native Rust ML models with Candle framework. Use when implementing vision transformers, LLMs, or audio models with GPU acceleration.

Use when claims lack multi-method validation, need stronger causality demonstration, or require in vivo confirmation - establishes evidence hierarchy from single-method to CNS-level multi-approach validation

Build browser extensions with WXT framework, Manifest V3, and TypeScript.Use when: creating Chrome extension, Firefox addon, browser plugin.Triggers: "extension", "browser extension", "chrome extension", "firefox addon", "manifest v3", "wxt".

Expert glossary builder who creates comprehensive definitions and descriptions for all terms in a taxonomy. Your goal is to produce clear, accurate, and contextually appropriate definitions that help users understand each concept.

Set up Python Flask development environment for beginners with step-by-step guidance, virtual environment creation, and troubleshooting

Read Jira tickets, extract requirements, summarize in developer-friendly format, optionally search codebase for related files, and update ticket status with transitions

Bootstrap or maintain a Codex skills repo with auto-sync to ~/.codex/skills; use when setting up a shared skills repository, onboarding new clones, or enabling autosync hooks for skills under skills/.

Use when writing raw SQL with GRDB, complex joins across 4+ tables, window functions, ValueObservation for reactive queries, or dropping down from SQLiteData for performance. Direct SQLite access for iOS/macOS with type-safe queries and migrations.

Use this skill when creating, optimizing, or improving prompts for large language models. Applies when users need help designing effective prompts, selecting appropriate prompting techniques, or troubleshooting prompt performance. Provides expert guidance through conversational consulting to build prompts using research-backed best practices and proven patterns.

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Implement proper i18n routing with next-intl, locale-based URLs, and correct parameter handling in Next.js 16 App Router. Use when creating pages, links, metadata, static params, or working with locale parameters.

Build agentic systems using Claude CLI in headless mode or the Claude Agent SDK. Use when building automation pipelines, CI/CD integrations, multi-agent orchestration, or programmatic Claude interactions. Covers CLI flags (-p, --output-format), session management (--resume, --continue), Python SDK (claude-agent-sdk), custom tools, and agent loop patterns.

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

Convert PRD requirements into structured epics, features, and user stories with acceptance criteria and priority rankings

This skill should be used when developing Next.js 16 applications with React, TypeScript, Material-UI V7, and Firebase. Provides comprehensive guidance on setup, best practices, error handling, and advanced patterns for production-ready applications.

Authentication security patterns and standards for NextAuth.js v5. Use when implementing or reviewing authentication code.

ArchR docs served from downloaded_docs/archr_scrape - comprehensive scATAC-seq analysis toolkit with all HTML files explicitly listed

Use when creating animations for business contexts that require seriousness, competence, and trustworthy presentation.

Skill for understanding, refactoring, and extending this React + TypeScript + Vite SPA frontend (components, routing, state, and API calls) whenever the user asks for UI changes, bug fixes, or new frontend features in this project.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation