I rounded up a few Claude Skills for #RStats users.
Huge thanks to the creators who developed them. They share Skills for everything from tidyverse code to brand.yml files to learning while using AI.
Hope the list is useful, and please let me know what I missed! 🧡
rworks.dev/posts/claude...
Thanks for this handy overview. I’ve been building my own skills for quarto docs and presentations, so helpful to have there for comparison
I was loving Claude Code... until I tried it with #rstats. Constant errors, wouldn't use the tidyverse even when asked, "optimized" functions were slower.
Frustrated, I started a session just to teach R to Claude and summarize what it learned into a CLAUDE.md file gist.github.com/sj-io/3828d6...
Prototype app that makes Bayesian stats code from a flow chart: 'Mermaid to Stan'. Vibe coded in 15 minutes.
#rstats
www.seascapemodels.org/mermaid-to-s...
So many new teaching possibilities become available when you can make apps this quickly: vitaexmachina.substack.com/p/do-we-real...
Conservation is turning to markets for funding, but are the funds sufficient to cover the costs of restoring habitats? In our new study we looked at the financial feasibility of blue carbon to support mangrove restoration.
onlinelibrary.wiley.com/doi/10.1111/... (DM or email me if you need a copy)
Can AI really help protect the planet — and the people defending it?
A new op-ed warns that while COP30 leaders tout AI’s promise for conservation, ethical risks remain. It argues Indigenous experts must guide AI’s development to reflect their priorities and protections.
** Views are authors'.
Great article on where over emphasis on publication metrics has led us to
Substack is the new home for thoughtful writing on the internet, and I'm trying it out. Check out my latest post on coastal habitat restoration
substack.com/inbox/post/1...
#biodiversity #nature #coastalhabitats #restoration
AI generated Santa wish list
State of the world’s kelp forests study now open access (via Aaron Eger)
www.cell.com/one-earth/fu...
Giant kelp is a productivity powerhouse—about 40x more productive than the kelp that’s replaced it on Tasmania’s east coast.
Our new study found that if we restore giant kelp it boosts fisheries like abalone and rock lobster
📖 Read more: doi.org/10.1002/aqc.70242
EEB Postdoctoral Fellowship @ U.Toronto app deadline Jan 15 2026. Opportunity for independent research, encourages collab across labs/disciplines. Lots of great folks to interact with, Come join us!
eeb.utoronto.ca/employment-2/
How do we monitor fisheries to know if seafood is sustainable? It turns out WHERE we monitor is just as important as HOW MUCH we monitor. We argue the “where” needs to be codified in fisheries policies:
Report: www.nature.org/content/dam/...
Blog: www.seascapemodels.org/posts/2025-1...
great title! plan to discuss in lab mtg this week, very good timing for us
Classic paper titles
“This research is important for the conservation and Management of Sharks”: A proposed framework for ensuring that this is actually true
I'd really like to get the "AI water is being hyped up as a problem by the labs because it's so obviously stupid it invalidates AI critics' more serious complaints" people and the "Andy's in the pocket of the labs because he's questioning the AI water issue" people together in the same room
Great work! I think loss of migration knowledge from overfishing is a huge under appreciated issue with fish.
🧵1/9 There are 35,000+ fish species, but we have formal social-behaviour classifications for a tiny fraction. Most knowledge lives in the experience of researchers, fishers, divers, aquarists, naturalists, and Indigenous communities, but almost none of it is centralised. So we built ShoalBase.org.
Teaching stats next year, I’m planning to make it interactive - Stats can be more than numbers and R code, Gelman and Vehtari’s book has lots of ideas for interactive classroom stats activities
And AI works well for quick hits, but if you have the money hire a real human designer for something that is accurate and well thought out
name a style (e.g. below is 'botanical line-art'); include reference images for accurate rendering; ask for white space for easy post-production modifications (e.g. adding a DOI); ...
TLDR: Helps to be clear on your key points; but with web search the AI can sometimes do a good job on its own of figuring these out; use less text, (more text = more chance of errors); ...
New post on making science infographics with Gemini Pro 3 (Nano Banana), my experiences so far
www.seascapemodels.org/posts/2025-1...
The new Gemini image model (AKA nano banana) is pretty impressive, does very accurate infographics based on web-search, can do basic reasoning, including generating images of code and resulting plots (without running that code the image comes out of the AI)
www.seascapemodels.org/posts/2025-1...
Two years ago we got together in a beautiful mountain to learn and develop #rstats packages for ecology
After {labeleR} (ecologyr.github.io/labeleR/) and {BlueCarbon} (ecologyr.github.io/BlueCarbon/), {mappestRisk} is now officially out! See thread by lead author @dario-ssm.bsky.social 👇
@anotherbobsmith.bsky.social just found you on bsky, great paper thanks. very useful for our work in @globalmangroves.bsky.social
Disgraceful & tragic what governments have done to this once science powerhouse! www.abc.net.au/news/2025-11...
"Federal Science Minister...Tim Ayres said the cuts were aimed at refocusing the efforts of the CSIRO towards research priorities, such as critical minerals, iron & steel...in Australia."
Should I post a pre-print? - a short guide of pros and cons written with my students and collaborators, thanks all
www.seascapemodels.org/posts/2025-1...
The implementation plan is part of what has made this map a success for conservation.
Other authors have criticized conservation mapping (e.g. www.nature.com/articles/s41...).
Conservation maps can help save biodiversity. We just need to be clear about what their purpose is.
