Machine Learning

Use this skill when developing Streamlit applications with uv package manager. Covers project setup, running apps, testing (unit/e2e), and development workflows. Trigger when user mentions "streamlit", "uv run streamlit", "streamlit testing", or asks about building data apps with Python.

Gera e manipula apresentacoes PowerPoint (.pptx) para o PCA Camocim. Converte dashboards HTML em slides e preenche templates oficiais.

Automated IRS Form 990-EZ preparation and review system that streamlines nonprofit tax compliance through intelligent data collection, multi-level validation, and expert guidance.

Modern Rust development best practices for 2025. Use when working on Rust projects including: (1) Project setup and Cargo.toml configuration, (2) Clippy/rustfmt linting and formatting, (3) Error handling with thiserror/anyhow, (4) Async programming with Tokio, (5) Testing strategies (unit, integration, property-based), (6) CI/CD pipelines and security scanning, (7) Performance optimization and profiling, (8) Observability with tracing, (9) Unsafe code review.

Accessibility principles for inclusive design - keyboard navigation, screen readers,ARIA, color contrast, and focus management. WCAG compliance for interfaces usable by all.Use when implementing interactive UI components requiring accessibility:- Forms, buttons, links, interactive elements needing keyboard access- Keyboard navigation, focus management, tab order- Screen reader support with semantic HTML and ARIA attributes- Color contrast validation for text/buttons (WCAG AA/AAA standards)- Modals, dialogs, dropdowns needing focus trapping- User mentions "accessible", "WCAG", "disabilities", "keyboard", "screen reader"Keywords: accessible, accessibility, WCAG, keyboard, screen reader, ARIA, contrast, a11yFocus on making UI usable via keyboard, screen readers, assistive technologies.

Multi-agent system for predicting BTC 15-minute candle outcomes (UP/DOWN vs Price to Beat) for prediction markets. Uses Continuity Ledger pattern for compaction-safe context persistence. Three agents: Data Fetcher, Data Analyst/Trainer, Decision Maker. Use when building BTC prediction systems, training crypto ML models, or implementing multi-agent trading systems.

Expert knowledge of Google Cloud Build CI/CD pipelines including cloudbuild.yaml syntax, build steps, builders, substitution variables, triggers, secrets, artifact handling, and deployment to Cloud Run. Use when working with Cloud Build configurations, troubleshooting build pipelines, or deploying to Google Cloud Platform.

Implement accessible user interfaces with semantic HTML, keyboard navigation, sufficient color contrast, screen reader support, ARIA attributes, and proper focus management. Use this skill when creating or editing React components (.tsx, .jsx files), when implementing forms with labels and inputs, when building interactive elements (buttons, modals, menus, dialogs), when implementing keyboard navigation, when choosing colors and ensuring contrast ratios, when adding ARIA attributes, when testing with screen readers, when implementing focus states and focus management, or when creating heading structures and page landmarks.

A skill for setting up and running end-to-end browser tests using Playwright. It includes guidance on project setup, the Page Object Model, user flow testing, visual regression, cross-browser configuration, and CI integration. Use this when a user wants to implement browser-based E2E testing.

Final SEO audit and technical implementation. Use at the END of a project to verify all pages, implement technical SEO (sitemap.xml, robots.txt, schema), and check for ranking readiness. Triggers on "SEO audit", "final SEO check", "verify SEO", "implement technical SEO".

Guided workflow for implementing HTML design prototypes as production React components with glassmorphism styling and quality standards enforcement. Use when converting design prototypes to production code.

Use this skill when creating, updating, or querying AI-optimized tracking artifacts (progress files, context notes, bug fixes, observation logs) in YAML+Markdown hybrid format for 95% token reduction. Invoke for: creating phase progress tracking, updating task status and blockers, querying pending work across phases, generating session handoff reports, validating artifact completeness, or migrating existing markdown files to hybrid format. Provides three embedded agents (artifact-tracker, artifact-query, artifact-validator) plus Python migration tools for efficient multi-phase project tracking.

ML 모델 파일 서버 간 동기화. "모델 동기화", "모델 배포", "rsync 모델", "서버로 전송" 요청 시 활성화됩니다.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.

Personal project implementation and modification guide. Use when creating or modifying Python 3.13 personal projects with FastAPI/Typer, pyproject.toml, and uv package manager.

Data Science Captain - ML models, analytics, forecasting, and data-driven insights

WinUI 3 and XAML patterns for the Pomodoro Time Tracker. Activates when working with ViewModels, XAML pages, data binding, or UI components.

System 테스트 작성 및 실행. pytest 기반, docker-compose.acceptance.yml 필수, 4단계 순서(infra→component→integration→scenarios). 네이밍 test_{대상}_{시나리오}_{예상결과}. poetry run pytest system-tests/ 실행. Fail Fast - 모든 응답 필드/타입/에러 엄격 검증, 예상외 필드/부작용은 실패 처리.

Run automated accessibility tests on URLs or HTML content using axe-core engine to WCAG 2.2 AA standards, then format findings as standardized issue reports. Use this skill when users want to test website accessibility, find WCAG violations, audit pages for accessibility issues, check if sites are accessible, analyze HTML for accessibility problems, or create accessibility issue tickets. Triggers on requests like "test accessibility", "check for WCAG violations", "audit this URL", "is this page accessible", "find accessibility issues", or "write accessibility issues".

Systematic debugging workflow to reproduce, isolate, and fix hard software bugs, resolve related lint issues, and add tests and guardrails to prevent regressions. This skill should be used for complex bugs that teams struggle to fix, flaky/intermittent failures, production-only bugs, and environment-specific issues where code changes must be lint-clean.