Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This collection provides the technical bridge between computational models and wet-lab execution. It enables researchers to programmatically design protein binding assays, submit sequences for experimental characterization, and retrieve results from the Adaptyv Bio Foundry.
WHO IT'S FOR
Computational biologists
designing and submitting protein binding assays
Time series data scientists
performing anomaly detection and forecasting on temporal data
Neuroimaging researchers
organizing brain imaging data using BIDS standards
Drug discovery scientists
automating protein screening and thermostability assays
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Follow the documented setup, then try a first task.
Interactive skill installation
Installs: Browse and install skills interactively from the Scientific Agent Skills collection. The repository describes the complete collection as 166 skills; the exact skills selected interactively are not established by the supplied evidence.
In a terminal, start the interactive browser and select the skills you want to install.
An installed pz CLI for macOS or Windows, or an installation completed using the linked official Linux guide
An authenticated Paperzilla session created with pz login
Paperzilla project identifier to replace <project-id>
Check the repository for this skill’s setup.
Use the paperzilla skill to give me the latest recommendations from project <project-id>. Briefly explain why each recommendation may matter. Replace <project-id> with my Paperzilla project identifier, and do not leave feedback or modify the project.
PRIMEKG_DATA pointing to that CSV, unless it is stored at the documented default data/PrimeKG/kg.csv path
Check the repository for this skill’s setup.
Use the primekg skill to produce a concise disease-context summary for <disease-name>, covering its associated genes, drugs, and phenotypes. Replace <disease-name> with the disease I want to investigate, and treat graph associations as research evidence rather than clinical recommendations.
Use the rdkit skill to parse this list of SMILES strings, identify any invalid molecules, and return a compact table containing molecular weight, LogP, TPSA, hydrogen-bond donors and acceptors, and rotatable bonds for each valid molecule.
Claude
Codex
Cursor
Gemini CLI
OpenClaw
Copilot
Amp
Kiro
Hermes
Pi
Antigravity
Paperclip