Deep Learning

Elite AI/ML Senior Engineer with 20+ years experience. Transforms Claude into a world-class AI researcher and engineer capable of building production-grade ML systems, LLMs, transformers, and computer vision solutions. Use when: (1) Building ML/DL models from scratch or fine-tuning, (2) Designing neural network architectures, (3) Implementing LLMs, transformers, attention mechanisms, (4) Computer vision tasks (object detection, segmentation, GANs), (5) NLP tasks (NER, sentiment, embeddings), (6) MLOps and production deployment, (7) Data preprocessing and feature engineering, (8) Model optimization and debugging, (9) Clean code review for ML projects, (10) Choosing optimal libraries and frameworks. Triggers: "ML", "AI", "deep learning", "neural network", "transformer", "LLM", "computer vision", "NLP", "TensorFlow", "PyTorch", "sklearn", "train model", "fine-tune", "embedding", "CNN", "RNN", "LSTM", "attention", "GPT", "BERT", "diffusion", "GAN", "object detection", "segmentation".

Maintain code quality using Biome linting, formatting, and git hooks. Use this when the user asks about linting errors, code formatting, Biome configuration, fixing code style issues, organizing imports, or ensuring code quality standards before commits.

Executive leadership guidance for strategic decision-making, organizational development, and stakeholder management. Includes strategy analyzer, financial scenario modeling, board governance frameworks, and investor relations playbooks. Use when planning strategy, preparing board presentations, managing investors, developing organizational culture, making executive decisions, or when user mentions CEO, strategic planning, board meetings, investor updates, organizational leadership, or executive strategy.

Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowcharts (processes, algorithms, user journeys), entity relationship diagrams (database schemas), C4 architecture diagrams (system context, containers, components), state diagrams, git graphs, pie charts, gantt charts, or any other diagram type. Triggers include requests to "diagram", "visualize", "model", "map out", "show the flow", or when explaining system architecture, database design, code structure, or user/application flows.

Deep technical assistant for projects that combine Neural Quantum States (FFNN and Transformer-based) with Sample-based Quantum Diagonalization (SQD). Trigger this skill whenever the task involves: (1) designing or analyzing NQS architectures for quantum chemistry, (2) connecting classical samplers to qiskit-addon-sqd, (3) studying sample-efficiency, bias, and variance in few-sample regimes (e.g. 12–14-bit H2).

Take enriched user stories and create execution plan with waves for parallel execution. Groups stories by dependencies into execution waves, assigns domain agents, and produces Gantt-style task schedule. Use when planning implementation workflow after architecture annotations.

Naming conventions for planning documents in prompts/. Use when creating plans, PRDs, research reports, idea capture or other workflow documents. Triggers on (1) creating new planning documents, (2) naming PRDs or research reports, (3) questions about document organization in prompts/.

Generates sequences of high-leverage tasks that increase understanding and improve the code. Use when:- "what should I work on next?" - suggests prioritized tasks- "create a plan for this repo" - generates a curriculum- "what's the roadmap?" - shows curriculum overview- "help me onboard to this codebase" - creates learning tasks- "plan a refactor" - structures improvement work- "prioritize these features" - organizes work into tracks- "make an onboarding plan" - creates a learning path- "create a learning path for this repo" - sequences learning tasks- "roadmap this refactor" - plans improvement work- "write the curriculum to disk" - persists plan artifacts

dbt best practices for models, tests, documentation, and project organization.

Core design principles for creating distinctive, beautiful UIs with technical excellence.Combines creative direction with practical foundation for memorable, accessible interfaces.Use when building UI without specific design specs (Figma, screenshots, design files):- Creating landing pages, home pages, marketing pages from scratch- Building web apps, dashboards, admin panels without design- Choosing design system: typography, colors, spacing, visual hierarchy- Need to propose complete design (fonts, colors, layout, spacing)- Building distinctive UIs that avoid generic AI aestheticsKeywords: landing page, design system, typography, colors, spacing, visual hierarchyTwo-part approach:1. Creative Direction: Choose aesthetic tone (minimal, bold, elegant, playful)2. Technical Foundation: Spacing scales, typography specs, WCAG contrast, hierarchyGoal: Create UIs that are BOTH beautiful (distinctive, memorable) AND correct (accessible, consistent, professional).

Documentation organization, maintenance, and cleanup.USE WHEN: organizing docs, cleaning project root, updating documentation,checking for redundancy, maintaining docs structure.NOT FOR: technical implementation (use relevant technical skill).Examples:<example>Context: User added documentation to wrong location.user: "I added a new API doc file to the root directory"assistant: "I'll use docs-keeper to organize it in the proper docs/ location."<commentary>File organization is docs-keeper responsibility.</commentary></example><example>Context: User needs to update docs after code changes.user: "I modified the auth system and need to update the docs"assistant: "I'll use docs-keeper to update the authentication documentation."<commentary>Documentation updates are docs-keeper responsibility.</commentary></example>