Luis PENAILILLO

@aiwithjainam @matiasmonsalves

4. The Question Generator Most researchers don't know what they don't know. This prompt fixes that. "Based on everything in my uploaded sources, generate: 1) The 10 most important questions someone deeply studying this topic should be able to answer, 2) The 5 questions that my current sources don't fully answer but need to, 3) The 3 questions that would completely change my understanding of this topic if answered differently, 4) What a skeptic or critic would ask to challenge the main conclusions in these documents." Use this to find exactly what's missing from your research before you go any further.

After 6 months of using NotebookLM, I can say it's the research tool that has revolutionized my workflow the most. But only because I learned these 10 prompts. Here's the complete system that turns 200 pages into clear answers in under an hour:

1/ Big update in exercise science: ACSM has revised its resistance training Position Stand for the first time since 2009. That is a 17-year gap, and a lot has changed. 🧵pmc.ncbi.nlm.nih.gov/articles/PMC12…

Los invitamos a participar en la II Jornada de Alergia Alimentaria Pediátrica: Un Desafío Multidisciplinario 📅 12 de junio de 2026 📍 Aula Magna – UAndes Este año tendremos un segmento de presentación de casos clínicos. 🔗 Inscripción e instrucciones: clinicauandes.cl/actividades-ex…

Claude acaba de volverse el asistente de investigación más potente que existe. 9 prompts para convertir 40+ papers en mapas de conocimiento, brechas de investigación y síntesis estructuradas en minutos. Guárdalo.

🚨 Someone just turned Claude into a full AI research scientist. This GitHub repo called claude-scientific-skills just quietly changed what's possible with AI in science. Most people are using Claude to write emails and summarize docs. These researchers are using it to run actual drug discovery pipelines, analyze single-cell RNA sequencing data, interpret clinical variants, and generate publication-ready reports all from a single prompt. Here's how it works: You install one plugin in Claude Code. Claude automatically discovers and uses 140 scientific skills across every major research domain bioinformatics, cheminformatics, proteomics, clinical research, medical imaging, materials science, quantum computing, laboratory automation. The skills connect Claude directly to the databases and tools scientists actually use: → Query ChEMBL for bioactive compounds → Annotate variants with ClinVar and Ensembl → Dock molecules with DiffDock against AlphaFold structures → Analyze 10X genomics data with Scanpy → Search ClinicalTrials. gov and match patients to trials → Generate PDF clinical reports with ReportLab One prompt. Real scientific libraries. Live database APIs. Actual results. This is what happens when someone stops treating Claude like a chatbot and starts treating it like a research platform. /plugin install scientific-skills@claude-scientific-skills 100% Opensource. MIT License. (Link in the comments)

PlotGDP: an AI Agent for Bioinformatics Plotting researchhub.com/paper/11075167…

A paper on the “noble” Tris buffer, who would have thought it can act in the background while we chase the effects of free radicals? Unusually interesting paper, and a reminder that surprises often come from probing what we treat as “obvious”. onlinelibrary.wiley.com/doi/10.1002/an…

Sarcopenia: An overview of emerging therapies and pathophysiological insights in age-related skeletal muscle decline #f0035" target="_blank" rel="nofollow noopener">sciencedirect.com/science/articl…

¿Por qué nadie está hablando en 2026 de cómo la IA puede hacer tu trabajo en 3 minutos? 🚀 Aquí 7 herramientas que cambiarán tu vida (la 1 mi favorita😍) 👇

🏅 Top Cited Review by D Farina et al. (@imperialcollege) The extraction of #neural strategies from the #surfaceEMG: 2004–2024 (ow.ly/ls7k50Y9iEg)

🎉 lactater - Tools for Analyzing Lactate Thresholds- v0.2.0 is out ✅ in this version there is a new function lactate_curve() to retrieve the lactate data for plotting as well as the heart rate response 🔗 #lactate-curve" target="_blank" rel="nofollow noopener">fmmattioni.github.io/lactater/#lact… #rstats

La IA acaba de matar a PowerPoint. No más horas interminables creando presentaciones. Aquí tienes 8 sitios web para crear presentaciones con IA en segundos:

@DelRealMartin2 @SebaGutierrezO

The impact of exercise on mitochondrial biogenesis in skeletal muscle: A systematic review and meta-analysis of randomized trials degruyterbrill.com/document/doi/1…

14 different literature review types categorized by method used

Exercise, Exerkines, and Sarcopenia e-dmj.org/journal/view.p…

All rejected papers share one common flaw: a weak discussion section. I know because I used to write them too. If you're stuck on the discussion section, wondering how to tie it all together, this is for you:

Skeletal muscle‐specific PGC‐1α‐b overexpression prevents eccentric contraction‐induced muscle injury through an utrophin‐independent pathway in mice - Naito - 2026 - Physiological Reports - Wiley Online Library physoc.onlinelibrary.wiley.com/doi/10.14814/p…

Is there a formula for a competitive NIH grant application? This Perspective aims to provide an inclusive roadmap on the elements of NIH funding. Elements of successful NIH grant applications

Friendly reminder: fascicles rarely run straight from end-to-end of muscles, so when using EFOV ultrasound you should plot the path using successive still pictures, draw that path on the skin, then follow that path (and adjust tilt, yaw). Here's an old VL image as example output.

Ten simple rules for developing good reading habits during graduate school and beyond (1/4) @PLOSCompBiol #paperwriting #PhD #PhDlife #academics #AcademicChatter #AcademicTwitter