DevOps

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.

This skill should be used proactively before writing any Scala code for the first time in a session. It ensures all Scala code adheres to project-specific coding standards, formatting rules, naming conventions, and architectural patterns defined in the comprehensive style guide. Trigger this skill when about to write Scala classes, traits, objects, or modify existing Scala files.

This skill should be used when the user asks to analyze BAM/SAM/CRAM alignment files from WGS/WES sequencing. Triggers include requests to extract reads from specific regions, identify insertions and deletions, calculate coverage statistics, or export read data as JSON for downstream analysis.

Avaliar e aprimorar observabilidade do serviço Spring (Micrometer, Prometheus, tracing) garantindo métricas, logs estruturados e dashboards alinhados ao ecossistema.

MCPを使用してNext.jsランタイムを検査し、エラー診断、ログ、メタデータ、Server Actionsを確認します。エラーのデバッグ、ルートのチェック、コンポーネントの検査、プロジェクト構造の理解に使用します。

Build and orchestrate tasks using Nuke build system. Use when task involves running Nuke build targets, orchestrating complex build workflows, or managing build pipelines.

Use when working with Quetrex's voice interface, OpenAI Realtime API, WebRTC, or echo cancellation. Knows Quetrex's specific voice architecture decisions and patterns. CRITICAL - prevents breaking working voice system.

Orchestrator agent that coordinates all BarqNet specialized agents (backend, integration, client, documentation, audit, testing) to execute complete end-to-end workflows. Plans multi-agent deployments, manages task dependencies, tracks progress across all platforms, and ensures comprehensive completion. Use for complex multi-component tasks, full-stack features, or production deployments.

Expert methodology for breaking down complex problems into fundamental truths and rebuilding solutions from the ground up. Use when users need breakthrough innovation (not incremental improvement), question industry assumptions, face seemingly impossible problems, want to understand root causes, ask "why does this have to be this way", "rethink from scratch", "reimagine this", request analysis "from first principles", want to challenge conventional wisdom, question everything, or need to deconstruct problems to their core elements. Ideal for strategic decisions, innovation challenges, cost optimization, and escaping local optima.

Follow these patterns when implementing data pipelines, ETL, data ingestion, or data validation in OptAIC. Use for point-in-time (PIT) correctness, Arrow schemas, quality checks, and Prefect orchestration.

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.

Target-agnostic bug bounty hunting methodology with parallel recon, systematic testing workflows, and vulnerability-specific exploitation guidance

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.

Integrate the Blueprint multi-tenancy pattern into new features and modules. Use this skill when adding Blueprint-aware functionality, implementing BlueprintMember access control, handling Blueprint ownership (User vs Organization), enforcing resource isolation, and integrating with BlueprintEventBus. Ensures proper multi-tenant architecture where Blueprint defines permission boundaries and all resources respect Blueprint context.

Convert local images referenced in Hugo front matter to modern formats (WebP) and update front matter using ci/convert_page_images.py.

This skill provides complete coverage of Google Gemini embeddings API (gemini-embedding-001) for building RAG systems, semantic search, document clustering, and similarity matching. Use when implementing vector search with Google's embedding models, integrating with Cloudflare Vectorize, or building retrieval-augmented generation systems. Covers SDK usage (@google/genai), fetch-based Workers implementation, batch processing, 8 task types (RETRIEVAL_QUERY, RETRIEVAL_DOCUMENT, SEMANTIC_SIMILARITY, etc.), dimension optimization (128-3072), and cosine similarity calculations. Prevents 8+ embedding-specific errors including dimension mismatches, incorrect task types, rate limiting issues (100 RPM free tier), vector normalization mistakes, text truncation (2,048 token limit), and model version confusion. Includes production-ready RAG patterns with Cloudflare Vectorize integration, chunking strategies, and caching patterns. Token savings: ~60%. Production tested. Keywords: gemini embeddings, gemini-embedding-001, google embeddings, semantic search, RAG, vector search, document clustering, similarity search, retrieval augmented generation, vectorize integration, cloudflare vectorize embeddings, 768 dimensions, embed content gemini, batch embeddings, embeddings api, cosine similarity, vector normalization, retrieval query, retrieval document, task types, dimension mismatch, embeddings rate limit, text truncation, @google/genai

Concurrent branch development with devcontainers using clone-based isolation

Calculates Net Income, Personal Income Tax (PIT), and Social Insurance (BHXH) based on Vietnam's progressive tax brackets.

Ensure code follows DDD architecture and DAL separation principles. Triggers: DDD, arch, 架構, 新功能, 新模組, new feature, scaffold, 骨架, domain.

Condenses long documents, conversation logs, or transcripts into concise summaries. Supports retrieval from memory/files, multiple output formats (bullet points, paragraphs, executive summary), and customizable detail levels. Use when the user needs to quickly understand large amounts of text content.