Machine Learning

Generates YAML frontmatter metadata (date/time, git commit, branch, repository) for workflow documentation. Use when creating research docs, plans, or work summaries.

Build mithril-dedup for ML dataset deduplication. Use when implementing MinHash, LSH, clustering, or document I/O.

Asenkron işlemleri analiz eder, race conditions bulur, error handling problemlerini tespit eder ve async/await patterns'ı optimize eder.

Write valid XHTML-strict HTML5 markup. Use when creating HTML files, editing markup, building web pages, or writing any HTML content. Ensures semantic structure and XHTML syntax.

PR 作成後に .github/workflows/ci.yml が失敗したときの対応手順。ローカルで pytest 全ケースを実行し、エラー有無で分岐。エラーがあれば修正して commit-push スキルでコミット・プッシュ、無ければ GitHub Actions のログを確認して原因を特定する。

Best practices for creating, optimizing, and deploying MCP servers to Smithery. Use this skill when:(1) Creating new MCP servers for Smithery deployment(2) Optimizing quality scores (achieving 90/100)(3) Troubleshooting deployment issues (0/0 tools, missing annotations, low scores)(4) Migrating existing MCP servers to Smithery format(5) Understanding Smithery's schema format requirements(6) Adding workflow prompts, tool annotations, or documentation resources(7) Configuring smithery.yaml and package.json for deployment

Generate Docker and Traefik deployment configurations for any application (Node.js, Python, Go, Rust, Java). Creates Dockerfile, docker-compose.yml, docker-compose.for-traefik.yml overlay, and .env.sample with production best practices. Use when: dockerize app, containerize, add Docker, deploy with Traefik, reverse proxy setup, HTTPS/SSL, Let's Encrypt certificates, production deployment, docker-compose setup. Requires: Docker, docker-compose.

QML + C++ Desktop UI 앱 개발 가이드. CMake 프로젝트 설정, C++ 백엔드 연동, Model-View 데이터 바인딩, 스타일링, 배포. Qt Quick Controls 기반 데스크톱 앱 생성 시 사용.

Develop with Gleam using idiomatic patterns, TDD, and type-driven design. Activate when working with .gleam files, gleam.toml, or user mentions Gleam, BEAM, or Erlang.

Execute end-to-end tests for Nikita using Telegram MCP, Gmail MCP, Supabase MCP, Chrome DevTools MCP, and gcloud CLI. Use when verifying implementations, testing user journeys, validating integrations, performing regression testing, or after completing any feature implementation. MANDATORY after /implement completes.

Guide for using uv - an extremely fast Python package and project manager written in Rust. Use when installing Python, managing virtual environments, adding dependencies, running scripts, building packages, or working with pyproject.toml. Replaces pip, pip-tools, pipx, poetry, pyenv, twine, and virtualenv.

Use when packaging Python libraries, creating CLI tools, or distributing Python code. Covers proper project structure, pyproject.toml, and publishing to PyPI.

Expert guidance on statistical analysis methodologies and Monte Carlo simulation for fantasy football. Use this skill when selecting regression approaches, designing simulations, performing variance analysis, or conducting hypothesis tests. Covers regression types (OLS, Ridge, Lasso, GAMs), Monte Carlo frameworks, regression-to-mean analysis, and statistical best practices for player performance modeling.

EditorConfig file validation and template for enforcing consistent coding styles across editors and IDEs in monorepos. Includes 4 required standards (root declaration, universal settings with UTF-8/LF/2-space defaults, language-specific sections for JS/TS/JSON/YAML/Markdown/Python/Shell/SQL/Docker/Prisma, root-only placement in monorepos). Use when creating or auditing .editorconfig files to ensure consistent code formatting.

LLM生成システムの検証設計スキル。assay-kitフレームワークを活用し、LLM特有の失敗モード（幻覚、例への過学習、部分的処理）を考慮した総合的なテストケース設計を支援する。使用タイミング:- LLMベースのワークフロー/エージェントの評価設計時- ゴールデンデータセット（golden-dataset.yaml）の設計・拡張時- 既存テストが特定パターンに過学習していないか検証時- LLM出力の品質スコアラー設計時- 「なぜこのテストケースが必要か」の根拠を示す時

Convierte archivos Markdown a HTML single-file con estilos profesionales corporativos

Complete knowledge domain for Cloudflare Browser Rendering - Headless Chrome automationwith Puppeteer and Playwright on Cloudflare Workers for screenshots, PDFs, web scraping,and browser automation workflows.Use when: taking screenshots, generating PDFs from HTML or URLs, web scraping content,crawling websites, browser automation tasks, testing web applications, managing browser sessions,performing batch browser operations, integrating with AI for content extraction, or encounteringbrowser rendering errors, XPath selector errors, browser timeout issues, concurrency limits,memory exceeded errors, or "Cannot read properties of undefined (reading 'fetch')" errors.Keywords: browser rendering cloudflare, @cloudflare/puppeteer, @cloudflare/playwright,puppeteer workers, playwright workers, screenshot cloudflare, pdf generation workers,web scraping cloudflare, headless chrome workers, browser automation, puppeteer.launch,playwright.chromium.launch, browser binding, session management, puppeteer.sessions,

Package entire code repositories into single AI-friendly files using Repomix. Capabilities include pack codebases with customizable include/exclude patterns, generate multiple output formats (XML, Markdown, plain text), preserve file structure and context, optimize for AI consumption with token counting, filter by file types and directories, add custom headers and summaries. Use when packaging codebases for AI analysis, creating repository snapshots for LLM context, analyzing third-party libraries, preparing for security audits, generating documentation context, or evaluating unfamiliar codebases.

Develop Python applications using modern patterns, uv, and functional-first design. Activate when working with .py files, pyproject.toml, uv commands, or user mentions Python, itertools, functools, pytest, mypy, ruff, async, or functional programming patterns.

Create interactive single-file HTML prototypes for UX validation. Use when the user asks to create a prototype, mockup, or interactive wireframe based on specs/architecture/ux.md or any UX specification. Triggers include requests like "create a prototype", "build a prototype from the UX spec", "make an interactive mockup", "prototype the user flow", or "validate the UX".