
Audit small molecules from an Ersilia screening run and prioritise them for drug discovery. Use this skill whenever the user has a CSV file from Ersilia model outputs and wants to rank, score, or filter molecules based on activity, drug-likeness, or ADMET properties. Also trigger when the user asks to evaluate candidates from a screening, understand what the Ersilia scores mean, identify promising compounds, prepare a hit list for follow-up, or find novel vs known-like antibiotic candidates. Even if the user just says "can you look at these molecules" and they provide a CSV with model output columns, this skill is the right tool.
Produce the weekly Ersilia literature digest covering AI/ML for drug discovery, antibiotic and antimicrobial discovery, NTDs and AMR, and open science for global health — through an explicit LMIC and decolonisation lens. Use this skill whenever the user asks to prepare, run, or refresh the literature digest. Triggers include: "weekly literature digest", "literature digest for Ersilia", "/literature-digest", "lit digest this week", "what did we miss last week", "digest the literature". Always use this skill for digest requests even if the ask seems simple.
Integrate the code of a new ML model into an Ersilia model template repository. Use this skill whenever the user has: (1) a source model repository with the original ML code, (2) an ersilia-model-template repository (already forked/cloned), and (3) optionally a PDF of the scientific article — and needs to wire up the actual model code. The skill handles all coding steps: copying checkpoints with git-lfs tracking, adapting main.py to replace the molecular-weight placeholder with real inference, creating run_columns.csv, updating install.yml with pinned versions, and producing run_input.csv and run_output.csv by actually running the model. Trigger on phrases like "incorporate model code", "fill in the template", "adapt main.py", "add checkpoints", "create run_columns", "create install.yml for ersilia", "generate example files for ersilia model", or any request to wire a source model into the eos-template format.
Tests an Ersilia Model Hub model before hub incorporation. Runs `ersilia test --shallow` on a locally cloned model repository, reads the results, identifies failing checks, and proposes a debugging strategy to the user — but does not apply fixes automatically. Use this skill whenever a user wants to test, validate, or debug an Ersilia model before submitting it to the hub, mentions test failures, says "the test is failing", or is preparing a model for hub incorporation. Trigger even if the user just says "test the model" or "run ersilia test" in any Ersilia context.
A minimal test skill to verify that the ersilia-skills repository and local setup (symlinks, git hook) are working correctly. Use this skill to confirm that skill loading, slash commands, and the setup.sh workflow are functioning as expected. Trigger on phrases like "run test skill", "check skill setup", or "verify ersilia skills".
Create LinkedIn post drafts and end-of-month newsletter content for Ersilia Open Source Initiative. Use this skill whenever the user asks to plan LinkedIn posts, draft a monthly content schedule, write a weekly post, or create the monthly newsletter digest. Triggers include: "start of month", "end of month", "write a LinkedIn post", "prepare this month's posts", "draft the newsletter", "monthly update", "weekly post", or any request to create content for Ersilia's LinkedIn or newsletter. Also triggers when the user uploads a content calendar (PDF or text) and asks for posts for a given month. Always use this skill for any Ersilia content creation request, even if the ask seems simple.
How to create Python plots using the stylia package — Ersilia's matplotlib wrapper for publication-ready figures. ALWAYS use this skill when the user says anything like "make a plot", "plot this", "plot the results", "visualize", "prepare a plotting function", "show me a chart", "can you plot", "add a figure", or any similar phrasing during a coding session. This includes scatter plots, line plots, bar charts, heatmaps, histograms, ROC curves, and any other chart type. Also trigger on requests to visualize data, compare values, show distributions, or create any kind of figure — even if the user does not mention stylia or matplotlib explicitly. Never generate matplotlib figures without stylia — always use stylia.create_figure() instead of plt.figure() or plt.subplots().
Fills in the required metadata fields for an Ersilia Model Hub model, given the original publication as a PDF and the link to the original code repository. Use this skill whenever a user wants to populate, complete, or update a metadata.yml file for an Ersilia model, mentions an Ersilia model contribution, or is working on model metadata for the Ersilia Model Hub. Trigger even if the user just says "fill in the metadata" or "help me with the metadata.yml" in any Ersilia context.
Write the monthly Ersilia newsletter digest from a summary of the month's events. Use this skill whenever the user asks to write, draft, or prepare the monthly newsletter, end-of-month digest, or newsletter content blocks for Ersilia. Triggers include: "write the newsletter", "prepare the newsletter", "end of month newsletter", "draft the monthly update", "newsletter for [month]", or any request to produce newsletter content for Ersilia Open Source Initiative. Always use this skill for newsletter requests even if the ask seems simple.