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 computational biologists with the tools to automate the analysis of protein structures and genetic variants. By bridging AI models with biological databases, it streamlines the process of fetching structural data and assessing variant impacts.
The skills enable a more structured approach to integrating genomic databases into AI workflows, allowing researchers to move from raw sequence data to structural insights with greater precision.
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.
Setup
Google Antigravity Science plugin
Installs: Science plugin · Google Antigravity
Before you start
Latest version of Google Antigravity.
Science skills use uv for dependencies; the agent requests approval to install it on first use.
Some skills require API keys, including AlphaGenome and OpenAlex.
Download and install the latest Google Antigravity from https://antigravity.google/.
In the Antigravity app, go to Customizations > Build with Google > Science > Add.
On first use, follow the agent's request to install uv. The author recommends restarting Antigravity after that installation. Supply any API keys required by the selected skill through the agent's setup guidance.
Installs: Complete Science skills repository bundle; the listed paths are a bounded selection, not its full inventory.
Before you start
Science skills use uv for dependencies; the agent requests approval to install it on first use. Skills requiring uv need it installed and on PATH before their scripts run.
Some skills require API keys, including AlphaGenome and OpenAlex.
Run this command in a terminal to install the Science skills bundle.
npx skills add google-deepmind/science-skills/
On first use, follow the agent's uv installation guidance and ensure uv is on PATH before running dependent skills. Supply API keys when required by the selected skill.
uv installed and on PATH; follow the skill's setup guidance if missing.
Complete the skill's terms-of-use notification if not already recorded in the workspace.
Make sure literature-search-arxiv is installed in your agent before trying this task.
Use the literature-search-arxiv skill to find up to five papers matching my supplied topic or query. Save the search results to a file, then give me each paper's title, authors, a brief summary based on its abstract, and its URL.
uv installed and on PATH; follow the skill's setup guidance if missing.
Complete the skill's gnomAD terms-of-use notification if not already recorded in the workspace.
Make sure gnomad-database is installed in your agent before trying this task.
Use the gnomad-database skill to retrieve constraint metrics for the gene symbol I provide. Report its pLI and LOEUF, identifying the returned oe_lof_upper field as the LOEUF score, and save the result to a JSON file.
A transcription factor name and its species or NCBI Taxon ID.
uv installed and on PATH; follow the skill's setup guidance if missing.
Complete the skill's JASPAR terms-of-use notification if not already recorded in the workspace.
Make sure jaspar-database is installed in your agent before trying this task.
Use the jaspar-database skill to resolve my transcription factor name to a JASPAR Matrix ID using the species or Taxon ID I provide. Retrieve its position frequency matrix and summarize its TF class, family, and available external database links.
Cursor
Gemini CLI
Antigravity