agentsclimarketplace

Setup

Skill adaptyvbio/protein-design-skills/skills/setup

First-time setup for protein design tools. Use this skill when: (1) User is new and hasn't run any tools yet, (2) Commands fail with "file not found" or "modal: command not found", (3) Modal authentication errors occur, (4) User asks how to get started or set up the environment, (5) biomodals directory is missing or tools aren't working.From its SKILL.md

Install
npx -y skills add adaptyvbio/protein-design-skills --skill setup

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • runs commandsInstructs the agent to run 8 commands, including `pip install modal` and 7 more.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.5 KB, 875 tokens by cl100k_base, as published. Nobody here has run it

Setup Guide

Help users get their environment ready to run protein design tools.

Quick checklist

Run through this checklist when a user encounters setup issues:

StepCheckFix
1. Modal CLImodal --versionpip install modal
2. Modal authmodal token showmodal setup
3. biomodalsls biomodals/modal_*.pygit clone https://github.com/hgbrian/biomodals
4. Testcd biomodals && modal run modal_boltzgen.py --helpSee troubleshooting

Diagnosing issues

Error: "modal: command not found"

Cause: Modal CLI not installed.

Fix:

pip install modal

Then restart the terminal or run hash -r.

Error: "Permission denied" or "Unauthorized"

Cause: Modal not authenticated.

Fix:

modal setup

This opens a browser. Click "Authorize" to complete authentication.

Error: "No such file or directory: modal_boltzgen.py"

Cause: biomodals repository not cloned or not in correct directory.

Fix:

git clone https://github.com/hgbrian/biomodals
cd biomodals

Error: "uvx: command not found"

Cause: uvx is an optional wrapper from the uv package. It's not required.

Fix: Run modal directly (recommended):

modal run modal_boltzgen.py --help

Or install uv if you prefer using uvx:

pip install uv

Full setup steps

Step 1: Install Modal CLI

pip install modal

Verify: modal --version

Step 2: Authenticate Modal

modal setup

This opens a browser. Click "Authorize".

Verify: modal token show

Step 3: Clone biomodals

git clone https://github.com/hgbrian/biomodals
cd biomodals

Verify: ls modal_*.py should show files like modal_boltzgen.py

Step 4: Test the Setup

cd biomodals
modal run modal_boltzgen.py --help

Expected: Usage instructions appear showing --input-yaml, --protocol, --num-designs options.

Common workflows after setup

Once setup is complete, users can:

cd biomodals

# Design binders with BoltzGen (requires YAML config)
modal run modal_boltzgen.py --input-yaml binder.yaml --protocol protein-anything --num-designs 50

# Generate backbones with RFdiffusion (official repo, not biomodals)
python run_inference.py inference.input_pdb=target.pdb contigmap.contigs=[A1-150/0 70-100] inference.num_designs=100

# Validate with Chai
modal run modal_chai1.py --input-faa designs.fasta

GPU selection

Set GPU with environment variable:

GPU=L40S modal run modal_boltzgen.py --input-yaml config.yaml --num-designs 50
GPU=A100 modal run modal_chai1.py --input-faa complex.fasta
GPUVRAMBest For
T416GBProteinMPNN, ESM
A10G24GBRFdiffusion, Chai
L40S48GBBoltzGen, BindCraft
A10040-80GBLarge complexes

Modal free tier

Modal offers $30/month in free credits - enough for:

  • ~500 BoltzGen designs
  • ~2000 RFdiffusion backbones
  • ~1000 Chai predictions

Full documentation: See Getting started

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most project setup skills give in 875 tokens

Counted across 1,553 of the 3,091 authors here whose files we hold, read 2026-09-06

  • Write the configuration filein 36 of 1553
  • Create the directory structurein 35 of 1553, across 33 files
  • Verify the setupin 31 of 1553, across 28 files
  • Run the setup scriptin 30 of 1553, across 29 files
  • Pre-determine the required sample sizein 29 of 1553, across 12 files
  • Check if the configuration already existsin 29 of 1553
  • Document every testin 26 of 1553, across 10 files
  • Start with a hypothesisin 26 of 1553, across 11 files
  • Ask one question at a timein 22 of 1553
  • Test a single variable per testin 21 of 1553, across 9 files
  • Read product marketing context before asking questionsin 19 of 1553, across 8 files
  • Do not peek and stop earlyin 18 of 1553, across 7 files

Said here and by no other author read

  • Install the modal CLI
  • Authenticate modal
  • Test the modal setup

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.