Research

Use when working with Planetscale — planetScale branch management, deploy requests, schema analysis, query insights, and database health.

Foundational problem framing for design sprints and product strategy. Based on Google Design Sprint "Understand" phase methodology. Use when teams need to establish shared understanding before ideation - defining problem statements, identifying users/stakeholders, setting success criteria, documenting constraints and assumptions, and capturing pain points. Works in solo, team synchronous, or team asynchronous modes. Creates structured problem map document as foundation for HMW exercises and s...

Fornece padrões de engenharia e tipografia digital moderna usando Typst. Cobre sintaxe de marcação, funções customizadas, criação de templates reutilizáveis, regras de exibição (show/set rules), matemática avançada, tabelas, layout de páginas e bibliografia via Hayagriva/BibTeX.

Especialista em Metodologia de Pesquisa Científica, Revisão Sistemática de Literatura (PRISMA 2020), Estruturação PICO/PECO, Avaliação PRESS, Busca em Bases Indexadas (PubMed/MeSH, arXiv, IEEE Xplore, Semantic Scholar, Scopus, SciELO) e Redes de Citação.

Especialista em Química Fundamental e Aplicada, Síntese Orgânica/Inorgânica, Físico-Química e Análise Instrumental baseado nas obras Organic Chemistry (Clayden, Greeves, Warren), Inorganic Chemistry (Miessler, Fischer, Tarr), Physical Chemistry (Atkins, de Paula) e Fundamentals of Analytical Chemistry (Skoog, West, Holler, Crouch). Cobre Termodinâmica de Soluções e Equilíbrio de Fases (Equação de Antoine, Diagramas Azeotrópicos e Ternários), Eletroquímica e Condutometria (Debye-Hückel-Onsager...

Especialista em Biotecnologia, Engenharia de Bioprocessos, Biorreatores Industriais e Tecnologia do DNA Recombinante baseado nas obras Bioprocess Engineering Principles (Pauline M. Doran), Bioprocess Engineering (Shuler, Kargi, DeLisle) e Biotecnologia Industrial (Schmidell et al.). Cobre Modelagem Cinética de Crescimento Celular (Monod, Luedeking-Piret), Hidrodinâmica e Balanços de Massa/Energia em Biorreatores (STR, Airlift, Coluna de Bolhas, Single-Use SUBs), Coeficiente Volumétrico de Tra...

Especialista em Engenharia Biomédica, Instrumentação Médica, Sinais Fisiológicos e Imagens Diagnósticas baseado em John G. Webster (Medical Instrumentation Application and Design) e Jerrold T. Bushberg (The Essential Physics of Medical Imaging). Cobre eletrodos de biopotenciais (Ag/AgCl), amplificadores de instrumentação (INA) com alto CMRR, circuito Right Leg Drive (RLD), sinais fisiológicos (ECG, EEG, EMG), isolamento galvânico e normas de segurança elétrica (IEC 60601-1), física de imagens...

Use this skill when you need part-level segmentation data for training VLMs to understand object parts and fine-grained visual components. Avoid it when object-level segmentation is sufficient.

Use this skill when you want to refine text prompts for image generation to produce higher quality, more faithful synthetic training images. Avoid it when your prompts already produce satisfactory synthetic images.

Use this skill when you want to generate synthetic images with realistic text overlaid on natural scenes for text detection/recognition training. Avoid it when you have sufficient real text detection data or need non-text image generation.

Use this skill when you want to train CLIP-style models entirely on synthetic images generated by Stable Diffusion instead of real web images. Avoid it when you have sufficient real image data or synthetic quality is insufficient.

Use this skill when you want to create region-level instruction data for VLMs that understand and describe image regions with fine-grained detail. Avoid it when image-level understanding is sufficient.

Use this skill when you want to train a high-quality text-to-image model efficiently using carefully curated high-quality captions from an LLM. Avoid it when you already have a well-trained text-to-image model.

Use this skill when you want to train high-capability small models using heavily filtered web data augmented with synthetic textbook-quality data. Avoid it when you are training a large model where data quality filtering is less impactful.

Use this skill when you want to generate synthetic textbook-quality code data for training a small but highly capable code model. Avoid it when you have sufficient high-quality code data or are not training a code model.

Use this skill when you want to build a comprehensive synthetic data generation pipeline using strong models to create instruction data at scale. Avoid it when you have sufficient real instruction data or cannot run large model inference.

Use this skill when you want to augment training data by linearly interpolating between pairs of training examples and their labels. Avoid it when you need discrete, unmodified training examples.

Use this skill when you want to generate instruction data by prompting an aligned LLM with just the system prompt to elicit user-like instructions from the model itself. Avoid it when you have instruction data or prefer structured generation approaches.

Use this skill when you want to train a VLM to evaluate its own outputs for self-improvement without external AI judges. Avoid it when you have access to external AI judges or do not need self-evaluation.

Use this skill when you want to align a VLM with just 200 carefully curated high-quality instruction examples, pushing the LIMA principle to multimodal. Avoid it when you have more than 200 good instruction examples available.

Use this skill when you want to automatically generate grounded segmentation annotations by combining Grounding DINO for text-based detection with SAM for segmentation. Avoid it when you have manual grounding annotations or do not need automated annotation.

Use this skill when you want to improve image generation by training a detailed captioner and recaptioning training data. Avoid it when you are not building an image generation model or already have detailed captions.

Use this skill when you want to apply photometric augmentations (color jitter, brightness, contrast) to CLIP training images for improved robustness. Avoid it when standard random crop and flip are sufficient.

Use this skill when you want to learn optimal data augmentation policies using reinforcement learning to search over augmentation transforms. Avoid it when RandAugment's simpler approach is sufficient.