DevOps

Orchestrate comprehensive planning phase from ideation to development-ready specifications using 4 specialized agents

ETL pipelines, Apache Spark, data warehousing, and big data processing. Use for building data pipelines, processing large datasets, or data infrastructure.

Expert guidance on writing in Chamath Palihapitiya's communication style across 5 formats (Annual Letters, Customer Briefs, Emails, Policy Ideas Briefs, Learn with Me Presentations). Use when helping with any writing task, document creation, editing, reviewing communications, or answering questions about how to write something. Includes 10 universal principles, format-specific playbooks, internal team email guidance, templates, decision frameworks, and quality control checklists. MODULAR ARCHITECTURE: Optimized for LLM consumption with selective context loading (core + format).

Main coordinator for the automated Advent of Code workflow. Orchestrates puzzle fetching, TDD solving, and submission for daily AoC challenges. Use when running the full automated solving pipeline or when user requests to solve an AoC day.

Provides guidance on spec-driven, test-driven, iterative development methodology. Activated when user asks about MVP-first development, iterative workflows, TDD cycles, specification writing, or how to structure feature development.

Creates and configures hosted Model Context Protocol (MCP) server connections for OpenAI Agents SDK

Plan-first development methodology that creates detailed specifications before coding. Creates structured plans with phases, file-level details, and verification steps. Includes automatic AI review, modification application, and validation.

Create or update the feature specification from a natural language feature description. Only invoke when user explicitly requests to create a specification, spec, or feature specification.

Ensures deterministic intent artifacts are generated for governed pipeline runs and admission gate responses are recorded.

Comprehensive target validation assessing druggability, disease association strength, tractability, and competitive landscape. Use for go/no-go decisions on target selection. Keywords: target validation, druggability, tractability, disease association, genetic validation

Enforces online documentation research before any technical implementation. Use when implementing features to ensure code follows current best practices by researching official documentation first.

Automated build, deploy, and documentation workflow for backend and combined (frontend+Theia) services to GKE. Use when starting a new build, deploying code changes to production GKE, or need consistent deployment documentation.

Human writing standards to eliminate AI-generated text patterns. This skill should be used for any copywriting, marketing content, documentation, or professional writing to ensure output reads as genuinely human. Covers banned vocabulary, punctuation discipline, sentence variety, and tone guidelines.

Autonomous project orchestrator - assesses state, reasons, decides, executes, evaluates, iterates

Portfolio optimization using PyPortfolioOpt for mean-variance optimization, efficient frontier analysis, risk modeling, and discrete allocation. Use when building investment portfolios, calculating optimal weights, analyzing risk-return tradeoffs, maximizing Sharpe ratio, minimizing volatility, or converting weights to share allocations. Supports HRP, CVaR, semivariance, and custom objectives.

LLM observability with self-hosted Langfuse 3.x - tracing, evaluation, monitoring, prompt management, and cost tracking

Assess companies for Azure Ascent prospect fit using NICE framework and Reality-Map classification

Validate images against tacosdedatos illustration style guide. Use this skill when reviewing generated images, checking uploaded images for brand consistency, providing quality feedback on visual assets, or deciding if an image is ready for publication. Returns pass/fail with specific actionable feedback.

Create bold, high-end, production-grade frontend interfaces with the mindset of a professional UI/UX designer and frontend engineer. This skill is used when the user asks to design or redesign web interfaces (components, pages, dashboards, or applications) that must feel intentional, distinctive, and non-generic. The model should actively draw inspiration from a wide range of real-world design references (e.g. modern product interfaces, editorial layouts, design systems, experimental web design, trends seen on platforms like Pinterest, Awwwards, Dribbble), without copying any single source. The output must be real, implementation-ready code, but should avoid rigid, template-like, or overly symmetric “AI-looking” components. Layouts, spacing, typography, hierarchy, and interaction patterns should feel designed, not generated. Preference is given to strong visual direction, thoughtful UX decisions, and controlled experimentation over safe or conventional UI patterns.

Templates and patterns for requirements documents. Use when creating specifications, validating spec structure, or managing requirements documentation.