← All skills
proteinmpnn
75 / 100 · Review before installing
Check before installing.
By adaptyvbio/protein-design-skills (GitHub) · design · 173 stars · scanned at commit 59dd633
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.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
The author does not mention this.
Found in 12 places.
Show 9 more
- skills/proteinmpnn/SKILL.md, line 96
--sampling_temp 0.1 # Float without quotes - may cause errors - skills/proteinmpnn/SKILL.md, line 116
--pdb_path_chains A,B # No spaces - skills/proteinmpnn/SKILL.md, line 121
--pdb_path_chains A, B # Space after comma - skills/proteinmpnn/SKILL.md, line 128
--bias_AA_jsonl '{"A": {"A": 1.5, "W": -2.0}}' - skills/proteinmpnn/SKILL.md, line 140
--pdb_path_chains A,B - skills/proteinmpnn/SKILL.md, line 174
python protein_mpnn_run.py \ - skills/proteinmpnn/SKILL.md, line 185
python protein_mpnn_run.py \ - skills/proteinmpnn/SKILL.md, line 194
python protein_mpnn_run.py \ - skills/proteinmpnn/SKILL.md, line 259
grep -c "^>" output/seqs/*.fa # Should match backbone_count × num_seq_per_target
Downloads and installs other software
The author does not mention this.
Found in 13 places.
Show 10 more
- docs/getting-started.md, line 93
uvx modal run modal_boltzgen.py --input-yaml binder.yaml --protocol protein-anything --num-designs 50 - docs/getting-started.md, line 99
uvx modal run modal_bindcraft.py --input-pdb target.pdb --lengths "70,100" --number-of-final-designs 50 - docs/getting-started.md, line 105
uvx modal run modal_ligandmpnn.py --input-pdb backbone.pdb --params-str "--number_of_batches 8 --temperature 0.1" - docs/getting-started.md, line 111
uvx modal run modal_chai1.py --input-faa designs.fasta --out-dir predictions/ - docs/getting-started.md, line 114
uvx modal run modal_boltz.py --input-faa designs.fasta --out-dir predictions/ - docs/getting-started.md, line 121
GPU=L40S uvx modal run modal_boltzgen.py ... - docs/getting-started.md, line 122
GPU=A100 uvx modal run modal_chai1.py ... - docs/getting-started.md, line 123
MODAL_GPU=A100 uvx modal run modal_esmfold2.py ... - docs/getting-started.md, line 145
pip install modal - docs/getting-started.md, line 151
- Use a larger GPU: `GPU=A100 uvx modal run ...`
Sends data to these websites: files.rcsb.org
The author does not mention this.
Found in 1 place.
Safer alternatives
Low-risk skills in the same category (design) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'proteinmpnn' ] || [ -L ~/.agents/skills/'proteinmpnn' ]; then echo 'A skill folder named proteinmpnn already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/adaptyvbio/protein-design-skills' "$d" && git -C "$d" checkout --quiet '59dd63374314baa2fb1f9864f190775bd7466647' -- 'skills/proteinmpnn' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/proteinmpnn' ~/.agents/skills/'proteinmpnn' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'proteinmpnn' ~/.claude/skills/'proteinmpnn' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for adaptyvbio/protein-design-skills shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/adaptyvbio/protein-design-skills/)
Score history
| Date | Version | Score |
|---|
| 2026-11-07 | 59dd633 | 75 |