New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Boltzgen

by adaptyvbio in adaptyvbio/protein-design-skills

All-atom protein design using BoltzGen diffusion model. An agent skill from adaptyvbio/protein-design-skills.

MITAuto-check passedResearch & Science

Install Boltzgen

skills CLI
$ npx skills add adaptyvbio/protein-design-skills --skill boltzgen -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install adaptyvbio/protein-design-skills boltzgen --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/adaptyvbio/protein-design-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/boltzgen .claude/skills/boltzgen && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
boltzgen
GitHub stars
163
Used in
4 other repos
Token cost
~2k tokens
SKILL.md length
451 words
Files
2 (incl. references)
Skills in repo
24
Repo updated
First seen
Licence
MIT

At a glance

All-atom protein design using BoltzGen diffusion model. An agent skill from adaptyvbio/protein-design-skills.

  • Need side-chain aware design from the start
  • SKILL.md covers Prerequisites, How to run, Key parameters (CLI) and YAML configuration, plus 7 more sections
  • Calls modal, git and pip; reaches github.com
  • Designing around small molecules

What it does

Boltzgen is an agent skill from adaptyvbio/protein-design-skills. All-atom protein design using BoltzGen diffusion model. Use this skill when: (1) Need side-chain aware design from the start, (2) Designing around small molecules or ligands, (3) Want all-atom diffusion (not just backbone), (4) Require precise binding geometries, (5) Using YAML-based configuration. For backbone-only generation, use rfdiffusion. For sequence-only design, use proteinmpnn. For structure validation, use boltz.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/yaml-spec.md`).

It sits in Research & Science, covering Protein structure and design and Diffusion and image models. The repository describes itself as: Claude Code skills for protein design. The licence is MIT.

When your agent uses it

  • Need side-chain aware design from the start
  • Designing around small molecules
  • Want all-atom diffusion (not just backbone)
  • Require precise binding geometries

Example prompts

  • “/boltzgen”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 59dd633. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • modal
    • git
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Boltzgen loads about 2k tokens when it runs, and up to ~3.6k if it reads all its reference files. Until then it costs about 109 tokens; SKILL.md has 451 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~109
When it runs · the whole SKILL.md, loaded when a task matches
~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from adaptyvbio/protein-design-skills at commit 59dd633, republished under its MIT licence (© adaptyvbio). 451 words, ~2,014 tokens.

Download SKILL.mdSave it as .claude/skills/boltzgen/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
boltzgen
description
All-atom protein design using BoltzGen diffusion model. Use this skill when: (1) Need side-chain aware design from the start, (2) Designing around small molecules or ligands, (3) Want all-atom diffusion (not just backbone), (4) Require precise binding geometries, (5) Using YAML-based configuration. For backbone-only generation, use rfdiffusion. For sequence-only design, use proteinmpnn. For structure validation, use boltz.
license
MIT
category
design-tools
tags
structure-design, sequence-design, diffusion, all-atom, binder
proteinbase_slug
boltzgen
proteinbase_url
https://proteinbase.com/design-methods/boltzgen
biomodals_script
modal_boltzgen.py

BoltzGen All-Atom Design

Prerequisites

RequirementMinimumRecommended
Python3.11+3.12
CUDA12.0+12.1+
GPU VRAM24GB48GB (L40S)
RAM32GB64GB

How to run

First time? See Getting started to set up Modal and biomodals.

bash
# Clone biomodals
git clone https://github.com/hgbrian/biomodals && cd biomodals

# Run BoltzGen (requires YAML config file)
modal run modal_boltzgen.py \
  --input-yaml binder_config.yaml \
  --protocol protein-anything \
  --num-designs 50

# With custom GPU
GPU=L40S modal run modal_boltzgen.py \
  --input-yaml binder_config.yaml \
  --protocol protein-anything \
  --num-designs 100

GPU: L40S (48GB) recommended | Timeout: 120min default

Available protocols: protein-anything, peptide-anything, protein-small_molecule, nanobody-anything, antibody-anything

Option 2: Local installation
bash
git clone https://github.com/HannesStark/boltzgen.git
cd boltzgen
pip install boltzgen   # or: pip install -e .

# Driven by the boltzgen CLI with a YAML design spec
boltzgen run binder_config.yaml \
  --output out/ \
  --protocol protein-anything \
  --num_designs 50

The first run downloads model weights (~6GB) to ~/.cache. Verify a spec with boltzgen check binder_config.yaml before a full run.

GPU: L40S (48GB) | Time: ~30-60s per design

Key parameters (CLI)

ParameterDefaultDescription
--input-yamlrequiredPath to YAML design specification
--protocolprotein-anythingDesign protocol
--num-designs10Number of designs to generate
--stepsallPipeline steps to run (e.g., design inverse_folding)

YAML configuration

BoltzGen uses an entity-based YAML format where you specify designed proteins and target structures as entities.

Important notes:

  • Residue indices use label_seq_id (1-indexed), not author residue numbers
  • File paths are relative to the YAML file location
  • Target files should be in CIF format (PDB also works but CIF preferred)
  • Run boltzgen check config.yaml to verify your specification before running
Basic Binder Config
yaml
entities:
  # Designed protein (variable length 80-140 residues)
  - protein:
      id: B
      sequence: 80..140

  # Target from structure file
  - file:
      path: target.cif
      include:
        - chain:
            id: A
      # Specify binding site residues (optional but recommended)
      binding_types:
        - chain:
            id: A
            binding: 45,67,89
Binder with Specific Binding Site
yaml
entities:
  - protein:
      id: G
      sequence: 60..100

  - file:
      path: 5cqg.cif
      include:
        - chain:
            id: A
      binding_types:
        - chain:
            id: A
            binding: 343,344,251
      structure_groups: "all"
Peptide Design (Cyclic)
yaml
entities:
  - protein:
      id: S
      sequence: 10..14C6C3  # With cysteines for disulfide

  - file:
      path: target.cif
      include:
        - chain:
            id: A

constraints:
  - bond:
      atom1: [S, 11, SG]
      atom2: [S, 18, SG]  # Disulfide bond

Design protocols

ProtocolUse Case
protein-anythingDesign proteins to bind proteins or peptides
peptide-anythingDesign cyclic peptides to bind proteins
protein-small_moleculeDesign proteins to bind small molecules
nanobody-anythingDesign nanobody CDRs
antibody-anythingDesign antibody CDRs

Output format

output/
├── sample_0/
│   ├── design.cif         # All-atom structure (CIF format)
│   ├── metrics.json       # Confidence scores
│   └── sequence.fasta     # Sequence
├── sample_1/
│   └── ...
└── summary.csv

Note: BoltzGen outputs CIF format. Convert to PDB if needed:

python
from Bio.PDB import MMCIFParser, PDBIO
parser = MMCIFParser()
structure = parser.get_structure("design", "design.cif")
io = PDBIO()
io.set_structure(structure)
io.save("design.pdb")

Sample output

Successful run
$ modal run modal_boltzgen.py --input-yaml binder.yaml --protocol protein-anything --num-designs 10
Running: boltzgen run binder.yaml --output /tmp/out --protocol protein-anything --num_designs 10
[INFO] Loading BoltzGen model...
[INFO] Generating designs...
[INFO] Running inverse folding...
[INFO] Running structure prediction...
[INFO] Filtering and ranking...
[INFO] Pipeline complete

Results saved to: ./out/boltzgen/2501161234/

Output directory structure:

out/boltzgen/2501161234/
├── intermediate_designs/           # Raw diffusion outputs
│   ├── design_0.cif
│   └── design_0.npz
├── intermediate_designs_inverse_folded/
│   ├── refold_cif/                 # Refolded complexes
│   └── aggregate_metrics_analyze.csv
└── final_ranked_designs/
    ├── final_10_designs/           # Top designs
    └── results_overview.pdf        # Summary plots

What good output looks like:

  • Refolding RMSD < 2.0A (design folds as predicted)
  • ipTM > 0.5 (confident interface)
  • All designs complete pipeline without errors

Decision tree

Should I use BoltzGen?
│
├─ What type of design?
│  ├─ All-atom precision needed → BoltzGen ✓
│  ├─ Ligand binding pocket → BoltzGen ✓
│  └─ Standard miniprotein → RFdiffusion (faster)
│
├─ What matters most?
│  ├─ Side-chain packing → BoltzGen ✓
│  ├─ Speed / diversity → RFdiffusion
│  ├─ Highest success rate → BindCraft
│  └─ AF2 optimization → ColabDesign
│
└─ Compute resources?
   ├─ Have L40S/A100 (48GB+) → BoltzGen ✓
   └─ Only A10G (24GB) → Consider RFdiffusion
Show full SKILL.md (184 more words)Show less

Typical performance

Campaign SizeTime (L40S)Cost (Modal)Notes
50 designs30-45 min~$8Quick exploration
100 designs1-1.5h~$15Standard campaign
500 designs5-8h~$70Large campaign

Per-design: ~30-60s for typical binder.

Adaptyv's own tests of these models showed BoltzGen costing about $1.80 per accepted design, averaged across 7 targets (the generation estimates above do not include the extra sampling and refolding needed to reach an accepted design).

Verify

bash
find output -name "*.cif" | wc -l  # Should match num_samples

Troubleshooting

Verify config first: Always run boltzgen check config.yaml before running the full pipeline Slow generation: Use fewer designs for initial testing, then scale up OOM errors: Use A100-80GB or reduce --num-designs Wrong binding site: Residue indices use label_seq_id (1-indexed), check in Molstar viewer

Error interpretation
ErrorCauseFix
RuntimeError: CUDA out of memoryLarge design or long proteinUse A100-80GB or reduce designs
FileNotFoundError: *.cifTarget file not foundFile paths are relative to YAML location
ValueError: invalid chainChain not in targetVerify chain IDs with Molstar or PyMOL
modal: command not foundModal CLI not installedRun pip install modal && modal setup

Next: Validate with boltz or chai → protein-qc for filtering.

© adaptyvbio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/boltzgen of adaptyvbio/protein-design-skills.

  • SKILL.md
  • references/yaml-spec.md

Open the folder on GitHubat commit 59dd633

Used in 4 other repositories

We found 9 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 4 other GitHub owners. This page covers the copy in adaptyvbio/protein-design-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Boltzgen next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Boltzgen compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Boltzgen this skilladaptyvbio/protein-design-skills1634 repos~2kAutomated safety check: PassMIT
Alphafold Database Fetch And Analyzegoogle-deepmind/science-skills3.2k2 repos~1.2kAutomated safety check: PassApache-2.0
Pymol VisualizationChatMol/ChatMol372—~1.2kAutomated safety check: PassMIT
Complexa Binder DesignNVIDIA-BioNeMo/bionemo-agent-toolkit478—~3.1kAutomated safety check: NotesApache-2.0
DiffDock Molecular DockingK-Dense-AI/scientific-agent-skills48k1 repos~3kAutomated safety check: NotesMIT
Biopipelineslocbp-uzh/biopipelines109—~2.4kAutomated safety check: PassMIT

Similar skills

  • Alphafold Database Fetch And Analyze

    google-deepmind/science-skills

    Retrieve and analyze AlphaFold predicted structures for a protein.

    3.2k GitHub starsUsed in 2 repos~1.2k tokens
    Research & ScienceAuto-check passed

  • Pymol Visualization

    ChatMol/ChatMol

    Generate publication-quality molecular visualization images using PyMOL.

    372 GitHub stars~1.2k tokensUpdated 6 mo ago
    Research & ScienceAuto-check passed

  • Complexa Binder Design

    NVIDIA-BioNeMo/bionemo-agent-toolkit

    Run a complete protein binder design campaign with NVIDIA Proteina-Complexa: resolve a target structure and hotspots from a name/sequence/PDB, co-design binder sequence+structure with reward-guided…

    478 GitHub stars~3.1k tokensUpdated yesterday
    Research & ScienceAuto-check: notes

  • DiffDock Molecular Docking

    K-Dense-AI/scientific-agent-skills

    Predicts how small molecules bind to a protein with DiffDock, covering batch docking, pose ranking by confidence and checks on the results; not for binding affinity.

    48k GitHub starsUsed in 1 repo~3k tokens
    Research & ScienceAuto-check: notes

  • Biopipelines

    locbp-uzh/biopipelines

    Design and run computational protein and ligand workflows on a GPU: binder and enzyme design, de novo backbone generation, inverse folding and sequence redesign, structure prediction, protein-ligand…

    109 GitHub stars~2.4k tokensUpdated 8 days ago
    Research & ScienceAuto-check passed

  • Protein Binder Design

    NVIDIA-BioNeMo/bionemo-agent-toolkit

    Orchestrate an end-to-end de novo protein binder design campaign against a protein target by composing BioNeMo NIM skills.

    478 GitHub stars~1.4k tokensUpdated yesterday
    Research & ScienceAuto-check: notes

More from adaptyvbio/protein-design-skills

All 24 skills in this repo

  • Alphafold

    adaptyvbio/protein-design-skills

    Validate protein designs using AlphaFold2 structure prediction.

    163 GitHub starsUsed in 4 repos~1.2k tokens
    Auto-check passed

  • Bindcraft

    adaptyvbio/protein-design-skills

    End-to-end binder design using BindCraft hallucination. An agent skill from adaptyvbio/protein-design-skills.

    163 GitHub starsUsed in 4 repos~1.3k tokens
    Auto-check passed

  • Chai

    adaptyvbio/protein-design-skills

    Structure prediction using Chai-1, a foundation model for molecular structure.

    163 GitHub starsUsed in 4 repos~1.5k tokens
    Auto-check passed

  • Protein Design Workflow

    adaptyvbio/protein-design-skills

    End-to-end guidance for protein design pipelines. An agent skill from adaptyvbio/protein-design-skills.

    163 GitHub starsUsed in 4 repos~1.2k tokens
    Auto-check passed

  • Protein Qc

    adaptyvbio/protein-design-skills

    Quality control metrics and filtering thresholds for protein design.

    163 GitHub starsUsed in 4 repos~3.2k tokens
    Auto-check passed

  • Proteinmpnn

    adaptyvbio/protein-design-skills

    Design protein sequences using ProteinMPNN inverse folding. An agent skill from adaptyvbio/protein-design-skills.

    163 GitHub starsUsed in 4 repos~1.8k tokens
    Auto-check passed

Categories

Questions about Boltzgen

What does Boltzgen do?

All-atom protein design using BoltzGen diffusion model. An agent skill from adaptyvbio/protein-design-skills. Boltzgen is an agent skill from adaptyvbio/protein-design-skills. All-atom protein design using BoltzGen diffusion model.

When should I use Boltzgen?

Boltzgen fits situations like: need side-chain aware design from the start; designing around small molecules; want all-atom diffusion (not just backbone); require precise binding geometries.

How do I install Boltzgen in Claude Code?

Run `npx skills add adaptyvbio/protein-design-skills --skill boltzgen -a claude-code`. Or copy the skill folder (skills/boltzgen in adaptyvbio/protein-design-skills) into .claude/skills/boltzgen in your project. Claude Code loads it when a task matches its description.

How do I install Boltzgen in Codex?

Run `npx skills add adaptyvbio/protein-design-skills --skill boltzgen -a codex`. Or copy the skill folder (skills/boltzgen in adaptyvbio/protein-design-skills) into .agents/skills/boltzgen in your project. Codex loads it when a task matches its description.

Can I use Boltzgen in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add adaptyvbio/protein-design-skills --skill boltzgen -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/boltzgen, .gemini/skills/boltzgen, .github/skills/boltzgen and .opencode/skills/boltzgen in your project.

What does Boltzgen need to run?

Going by SKILL.md and its folder, Boltzgen needs the command-line tools its instructions call (modal, git and pip). Our summary lists: Python 3.

Does Boltzgen access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Boltzgen safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Boltzgen use?

Boltzgen is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Boltzgen use?

About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.5k tokens, read only when the agent opens those files.

What are the alternatives to Boltzgen?

Skills that share tags, products or a category with Boltzgen: Alphafold Database Fetch And Analyze (google-deepmind/science-skills, 3.2k stars), Pymol Visualization (ChatMol/ChatMol, 372 stars), Complexa Binder Design (NVIDIA-BioNeMo/bionemo-agent-toolkit, 478 stars) and DiffDock Molecular Docking (K-Dense-AI/scientific-agent-skills, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Boltzgen?

adaptyvbio (a GitHub organization) maintains it in adaptyvbio/protein-design-skills, which has 163 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on June 11, 2026.

Source: adaptyvbio/protein-design-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.