ReddRadar
Agent skill
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.
Install this agent skill to your Project
npx add-skill https://github.com/adaptyvbio/protein-design-skills/tree/main/skills/setup
SKILL.md
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:
| Step | Check | Fix |
|---|---|---|
| 1. Modal CLI | modal --version |
pip install modal |
| 2. Modal auth | modal token show |
modal setup |
| 3. biomodals | ls biomodals/modal_*.py |
git clone https://github.com/hgbrian/biomodals |
| 4. Test | cd biomodals && modal run modal_boltzgen.py --help |
See 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
modal run modal_rfdiffusion.py --pdb target.pdb --contigs "A1-150/0 70-100" --num-designs 100
# Validate with Chai
modal run modal_chai1.py --input-faa designs.fasta
GPU selection
Set GPU with environment variable:
GPU=A10G modal run modal_rfdiffusion.py --pdb target.pdb --contigs "A1-100/0 50-80" --num-designs 10
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
| GPU | VRAM | Best For |
|---|---|---|
| T4 | 16GB | ProteinMPNN, ESM |
| A10G | 24GB | RFdiffusion, Chai |
| L40S | 48GB | BoltzGen, BindCraft |
| A100 | 40-80GB | Large 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 Installation Guide
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
adaptyvbio/protein-design-skills
proteinmpnn
Design protein sequences using ProteinMPNN inverse folding. Use this skill when: (1) Designing sequences for RFdiffusion backbones, (2) Redesigning existing protein sequences, (3) Fixing specific residues while designing others, (4) Optimizing sequences for expression or stability, (5) Multi-state or negative design. For backbone generation, use rfdiffusion or bindcraft. For ligand-aware design, use ligandmpnn. For solubility optimization, use solublempnn.
adaptyvbio/protein-design-skills
campaign-manager
Goal-oriented binder design campaign planning and health assessment. Use this skill when: (1) Planning a complete binder design campaign, (2) Converting high-level goals into runnable pipelines, (3) Assessing campaign health and pass rates, (4) Diagnosing why designs are failing QC, (5) Estimating time, cost, and expected yields, (6) Selecting between design tools for a specific target. This skill orchestrates the other protein design tools. For individual tool parameters, use the specific tool skills.
adaptyvbio/protein-design-skills
esm
ESM2 protein language model for embeddings and sequence scoring. Use this skill when: (1) Computing pseudo-log-likelihood (PLL) scores, (2) Getting protein embeddings for clustering, (3) Filtering designs by sequence plausibility, (4) Zero-shot variant effect prediction, (5) Analyzing sequence-function relationships. For structure prediction, use chai or boltz. For QC thresholds, use protein-qc.
adaptyvbio/protein-design-skills
binding-characterization
Guidance for SPR and BLI binding characterization experiments. Use when: (1) Planning binding kinetics experiments, (2) Troubleshooting poor/no binding signal, (3) Interpreting kinetic data artifacts, (4) Choosing between SPR vs BLI platforms.
adaptyvbio/protein-design-skills
cell-free-expression
Guidance for cell-free protein synthesis (CFPS) optimization. Use when: (1) Planning CFPS experiments, (2) Troubleshooting low yield or aggregation, (3) Optimizing DNA template design for CFPS, (4) Expressing difficult proteins (disulfide-rich, toxic, membrane).
adaptyvbio/protein-design-skills
ligandmpnn
Ligand-aware protein sequence design using LigandMPNN. Use this skill when: (1) Designing sequences around small molecules, (2) Enzyme active site design, (3) Ligand binding pocket optimization, (4) Metal coordination site design, (5) Cofactor binding proteins. For standard protein design, use proteinmpnn. For solubility optimization, use solublempnn.
Didn't find tool you were looking for?