Coding agents are now being trained as scientists. scientific-agent-skills, the top agent skills…
coding agents are now being trained as scientists. scientific-agent-skills, the top agent skills library for science at 44.6k stars, ships 165 validated skills across 100+ databases and claims 190,000 scientists already use it.
the lab bench is becoming a plugin.
Context
The k-dense-ai/scientific-agent-skills repository, MIT licensed and created 19 October 2025, describes itself as the number one agent skills library for science, used by 190,000+ scientists, with 165 ready-to-use validated skills plus 100+ scientific databases. In the same fetch on 4 October 2026 its README body says 163 skills, and it showed 40,826 stars.
It is a library of skills, instructions and scripts an agent loads, and nothing is trained, so coding agents are being trained as scientists is the author's metaphor. Number one and 190,000 scientists are the repo's own claims with no usage evidence read. The 165 and the 163 differ within the same page, and a search snippet showed 175,000+ scientists, so these are different snapshots. Stars were 40,826 against the note's 44.6k, a different window and unverified. Validated is the repo's term and its method was not read. That the lab bench is becoming a plugin is the author's thesis.
Related work
- Note on the skills ecosystem ↗Broader skills ecosystem.
Watch next
- The repo's validation docs and star history.
Sources
- scientific-agent-skills (GitHub)github.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 20 September 2026 at 08:17 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →