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

Chai1 Structure Prediction

by BioTender-max in BioTender-max/awesome-bio-agent-skills

Chai-1 structure prediction for protein complexes and design validation.

MITAuto-check passedResearch & Science

Install Chai1 Structure Prediction

skills CLI
$ npx skills add BioTender-max/awesome-bio-agent-skills --skill chai1-structure-prediction -a claude-code

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

GitHub CLI
$ gh skill install BioTender-max/awesome-bio-agent-skills chai1-structure-prediction --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/BioTender-max/awesome-bio-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/bioclaw_hub/chai1-structure-prediction .claude/skills/chai1-structure-prediction && 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
chai1-structure-prediction
GitHub stars
199
Token cost
~1.7k tokens
SKILL.md length
366 words
Files
3 (incl. references)
Skills in repo
23
Repo updated
First seen
Licence
MIT

At a glance

Chai-1 structure prediction for protein complexes and design validation.

  • Predicting protein-protein complex structures
  • SKILL.md covers Prerequisites, How to run, FASTA Format and Key parameters, plus 11 more sections
  • Calls pip, modal and python; reaches github.com
  • Validating designed binders

What it does

Chai1 Structure Prediction is an agent skill from BioTender-max/awesome-bio-agent-skills. Chai-1 structure prediction for protein complexes and design validation. Use this skill when: (1) Predicting protein-protein complex structures, (2) Validating designed binders, (3) Predicting protein-ligand complexes, (4) Using the Chai API for high-throughput prediction, (5) Need an alternative to AlphaFold2. For QC thresholds, use protein-design-qc. For AlphaFold2 prediction, use alphafold2-multimer. For ESM-based analysis, use esm2-sequence-scoring.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `README.md` and `references/api-reference.md`).

It sits in Research & Science, covering Protein structure and design. The repository describes itself as: A curated collection of AI agent skills for biomedical research, covering genomics, proteomics, single-cell analysis, clinical AI, and protein design. The licence is MIT.

When your agent uses it

  • Predicting protein-protein complex structures
  • Validating designed binders
  • Predicting protein-ligand complexes
  • Using the Chai API for high-throughput prediction

Example prompts

  • “/chai1-structure-prediction”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 8cbdd18. 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:

    • pip
    • modal
    • python
    • git

    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

Chai1 Structure Prediction loads about 1.7k tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 121 tokens; SKILL.md has 366 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~121
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.6k

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 BioTender-max/awesome-bio-agent-skills at commit 8cbdd18, republished under its MIT licence (© BioTender-max). 366 words, ~1,740 tokens.

Download SKILL.mdSave it as .claude/skills/chai1-structure-prediction/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
chai1-structure-prediction
description
Chai-1 structure prediction for protein complexes and design validation. Use this skill when: (1) Predicting protein-protein complex structures, (2) Validating designed binders, (3) Predicting protein-ligand complexes, (4) Using the Chai API for high-throughput prediction, (5) Need an alternative to AlphaFold2. For QC thresholds, use protein-design-qc. For AlphaFold2 prediction, use alphafold2-multimer. For ESM-based analysis, use esm2-sequence-scoring.
license
MIT
category
design-tools
tags
structure-prediction, validation, foundation-model
biomodals_script
modal_chai1.py

Chai-1 Structure Prediction

Plain-language role: Use Chai when you want a modern structure-prediction model for validating designed binders or complexes.

Prerequisites

RequirementMinimumRecommended
Python3.10+3.11
CUDA12.0+12.1+
GPU VRAM24GB40GB (A100)
RAM32GB64GB

How to run

First time? See Installation Guide to set up Modal and biomodals.

Option 1: Modal
bash
cd biomodals
modal run modal_chai1.py \
  --input-faa complex.fasta \
  --out-dir predictions/

GPU: A100 (40GB) | Timeout: 30min default

bash
pip install chai_lab

python -c "
import chai_lab
from chai_lab.chai1 import run_inference

# Run prediction
run_inference(
    fasta_file='complex.fasta',
    output_dir='predictions/',
    num_trunk_recycles=3
)
"
Option 3: Local installation
bash
git clone https://github.com/chaidiscovery/chai1-structure-prediction-lab.git
cd chai1-structure-prediction-lab
pip install -e .

chai1-structure-prediction-lab predict \
  --fasta complex.fasta \
  --output predictions/

FASTA Format

Protein complex
>binder
MKTAYIAKQRQISFVKSHFSRQLE...
>target
MVLSPADKTNVKAAWGKVGAHAGE...
Protein + ligand
>protein
MKTAYIAKQRQISFVKSHFSRQLE...
>ligand|smiles
CCO
Protein + DNA/RNA
>protein
MKTAYIAKQRQISFVKSHFSRQLE...
>dna
ATCGATCGATCG

Key parameters

ParameterDefaultRangeDescription
num_trunk_recycles31-10Recycles (more = better)
num_diffn_timesteps20050-500Diffusion steps
seed0intRandom seed

Output format

predictions/
├── pred.model_idx_0.cif    # Best model (CIF format)
├── pred.model_idx_1.cif    # Second model
├── scores.json             # Confidence scores
├── pae.npy                 # PAE matrix
└── plddt.npy               # pLDDT values

Note: Chai-1 outputs CIF format. Convert to PDB if needed:

python
from Bio.PDB import MMCIFParser, PDBIO
parser = MMCIFParser()
structure = parser.get_structure("pred", "pred.model_idx_0.cif")
io = PDBIO()
io.set_structure(structure)
io.save("pred.model_idx_0.pdb")
Extracting metrics
python
import numpy as np
import json

# Load scores
with open('predictions/scores.json') as f:
    scores = json.load(f)

plddt = np.load('predictions/plddt.npy')
pae = np.load('predictions/pae.npy')

print(f"pLDDT: {plddt.mean():.3f}")
print(f"pTM: {scores['ptm']:.3f}")
print(f"ipTM: {scores.get('iptm', 'N/A')}")

Use cases

Binder validation
python
# Predict complex with Chai
chai1-structure-prediction-lab predict --fasta binder_target.fasta --output val/

# Check ipTM > 0.5
scores = json.load(open('val/scores.json'))
if scores['iptm'] > 0.5:
    print("Design passes validation")
Protein-ligand complex
python
# FASTA with SMILES
fasta = """
>protein
MKTA...
>ligand|smiles
CCO
"""

# Chai handles both protein and small molecules
Batch prediction
bash
# Multiple sequences
for fasta in sequences/*.fasta; do
    chai1-structure-prediction-lab predict \
        --fasta "$fasta" \
        --output "predictions/$(basename $fasta .fasta)"
done

Comparison with AF2

AspectChai-1AlphaFold2
MSA requiredNoYes
Small moleculesYesNo
DNA/RNAYesLimited
SpeedFasterSlower
AccuracyComparableReference

Sample output

Successful run
$ chai1-structure-prediction-lab predict --fasta complex.fasta --output predictions/
[INFO] Loading Chai-1 model...
[INFO] Running inference...
[INFO] Saved 5 models to predictions/

predictions/scores.json:
{
  "ptm": 0.82,
  "iptm": 0.71,
  "ranking_score": 0.76
}

What good output looks like:

  • pTM: > 0.7 (confident global structure)
  • ipTM: > 0.5 (confident interface, > 0.7 for high confidence)
  • CIF files with reasonable atom positions

Decision tree

Should I use Chai?
│
├─ What are you predicting?
│  ├─ Protein-protein complex → Chai ✓ or ColabFold
│  ├─ Protein + small molecule → Chai ✓
│  ├─ Protein + DNA/RNA → Chai ✓
│  └─ Single protein only → Use ESMFold (faster)
│
├─ Need MSA?
│  ├─ No / want speed → Chai ✓
│  └─ Yes / want accuracy → ColabFold
│
└─ Priority?
   ├─ Highest accuracy → ColabFold with MSA
   ├─ Speed / no MSA → Chai ✓
   └─ Ligand binding → Chai ✓

Typical performance

Campaign SizeTime (A100)Cost (Modal)Notes
100 complexes30-60 min~$10Standard validation
500 complexes2-4h~$45Large campaign
1000 complexes5-8h~$90Comprehensive

Per-complex: ~20-40s for typical binder-target complex.

Verify

bash
find predictions -name "*.cif" | wc -l  # Should match input count
Show full SKILL.md (157 more words)Show less

Troubleshooting

Low pLDDT: Increase num_trunk_recycles Low ipTM: Check chain order, interface region OOM errors: Use A100-80GB or reduce batch Slow prediction: Reduce num_diffn_timesteps

Error interpretation
ErrorCauseFix
RuntimeError: CUDA out of memoryComplex too largeUse A100-80GB or split prediction
KeyError: 'iptm'Single chain predictedEnsure FASTA has multiple chains
ValueError: invalid SMILESMalformed ligandValidate SMILES with RDKit
torch.cuda.OutOfMemoryErrorGPU exhaustedReduce num_diffn_timesteps to 100

Next: protein-design-qc for filtering and ranking.

Inputs

  • Protein sequences or complexes in FASTA format, optionally with ligand or molecular context.
  • Prediction parameters such as diffusion steps, seeds, and output directory.
  • A GPU or API-backed runtime configured for Chai inference.

Outputs

  • Predicted structures and accompanying confidence metrics for each input sequence or complex.
  • Model artifacts suitable for extracting pLDDT, ipTM, PAE, and ranking metadata.
  • A validation set that can flow directly into protein-design-qc and ipsae.

Next Step

Run protein-design-qc on the prediction outputs, then use ipsae if you need binder-focused ranking.

© BioTender-max, 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 2 other files (references) in skills/bioclaw_hub/chai1-structure-prediction of BioTender-max/awesome-bio-agent-skills.

  • SKILL.md
  • README.md
  • references/api-reference.md

Open the folder on GitHubat commit 8cbdd18

Compare with similar skills

Chai1 Structure Prediction 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.

Chai1 Structure Prediction compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Chai1 Structure Prediction this skillBioTender-max/awesome-bio-agent-skills199—~1.7kAutomated safety check: PassMIT
Alphafold Database Fetch And Analyzegoogle-deepmind/science-skills3.2k2 repos~1.2kAutomated safety check: PassApache-2.0
Alphafoldadaptyvbio/protein-design-skills1643 repos~1.2kAutomated safety check: PassMIT
Pymol VisualizationChatMol/ChatMol373—~1.2kAutomated safety check: PassMIT
Complexa Binder DesignNVIDIA-BioNeMo/bionemo-agent-toolkit478—~3.1kAutomated safety check: NotesApache-2.0
Bindcraftadaptyvbio/protein-design-skills1643 repos~1.3kAutomated 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

  • Alphafold

    adaptyvbio/protein-design-skills

    Validate protein designs using AlphaFold2 structure prediction.

    164 GitHub starsUsed in 3 repos~1.2k tokens
    Research & ScienceAuto-check passed

  • Pymol Visualization

    ChatMol/ChatMol

    Generate publication-quality molecular visualization images using PyMOL.

    373 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

  • Bindcraft

    adaptyvbio/protein-design-skills

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

    164 GitHub starsUsed in 3 repos~1.3k tokens
    Research & ScienceAuto-check passed

  • 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

More from BioTender-max/awesome-bio-agent-skills

All 23 skills in this repo

  • AI Scientist Evaluator

    BioTender-max/awesome-bio-agent-skills

    Critically review, score, compare, and rank one or more AI scientist outputs for biology, bioinformatics, computational life science, or adjacent research tasks.

    199 GitHub stars~2.4k tokensUpdated 3 mo ago
    Auto-check passed

  • Exa Search

    BioTender-max/awesome-bio-agent-skills

    Web toolkit powered by Exa, tuned for scientific and technical content.

    199 GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check: notes

  • Jgi Lakehouse

    BioTender-max/awesome-bio-agent-skills

    Queries JGI Lakehouse (Dremio) for genomics metadata from GOLD, IMG, Mycocosm, Phytozome.

    199 GitHub stars~3.7k tokensUpdated 3 mo ago
    Auto-check passed

  • Pacsomatic

    BioTender-max/awesome-bio-agent-skills

    Operator toolkit for nf-core/pacsomatic matched tumor-normal workflows from BAM inputs.

    199 GitHub stars~1.3k tokensUpdated 3 mo ago
    Auto-check passed

  • Scientific Impact Assessment

    BioTender-max/awesome-bio-agent-skills

    Assess paper and journal impact using OpenAlex citation counts, optional Altmetric data, and curated journal impact-factor references.

    199 GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check passed

  • Arxiv Search

    BioTender-max/awesome-bio-agent-skills

    Search arXiv preprints through the official arXiv API and turn arXiv IDs into local Markdown summaries.

    199 GitHub stars~2.9k tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about Chai1 Structure Prediction

What does Chai1 Structure Prediction do?

Chai-1 structure prediction for protein complexes and design validation. Chai1 Structure Prediction is an agent skill from BioTender-max/awesome-bio-agent-skills. Chai-1 structure prediction for protein complexes and design validation.

When should I use Chai1 Structure Prediction?

Chai1 Structure Prediction fits situations like: predicting protein-protein complex structures; validating designed binders; predicting protein-ligand complexes; using the Chai API for high-throughput prediction.

How do I install Chai1 Structure Prediction in Claude Code?

Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill chai1-structure-prediction -a claude-code`. Or copy the skill folder (skills/bioclaw_hub/chai1-structure-prediction in BioTender-max/awesome-bio-agent-skills) into .claude/skills/chai1-structure-prediction in your project. Claude Code loads it when a task matches its description.

How do I install Chai1 Structure Prediction in Codex?

Run `npx skills add BioTender-max/awesome-bio-agent-skills --skill chai1-structure-prediction -a codex`. Or copy the skill folder (skills/bioclaw_hub/chai1-structure-prediction in BioTender-max/awesome-bio-agent-skills) into .agents/skills/chai1-structure-prediction in your project. Codex loads it when a task matches its description.

Can I use Chai1 Structure Prediction 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 BioTender-max/awesome-bio-agent-skills --skill chai1-structure-prediction -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/chai1-structure-prediction, .gemini/skills/chai1-structure-prediction, .github/skills/chai1-structure-prediction and .opencode/skills/chai1-structure-prediction in your project.

What does Chai1 Structure Prediction need to run?

Going by SKILL.md and its folder, Chai1 Structure Prediction needs the command-line tools its instructions call (pip, modal, python and git). Our summary lists: Python 3.

Does Chai1 Structure Prediction 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 Chai1 Structure Prediction 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 Chai1 Structure Prediction use?

Chai1 Structure Prediction 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 Chai1 Structure Prediction use?

About 1.7k tokens (SKILL.md is roughly 7k 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 854 tokens, read only when the agent opens those files.

What are the alternatives to Chai1 Structure Prediction?

Skills that share tags, products or a category with Chai1 Structure Prediction: Alphafold Database Fetch And Analyze (google-deepmind/science-skills, 3.2k stars), Alphafold (adaptyvbio/protein-design-skills, 164 stars), Pymol Visualization (ChatMol/ChatMol, 373 stars) and Complexa Binder Design (NVIDIA-BioNeMo/bionemo-agent-toolkit, 478 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Chai1 Structure Prediction?

BioTender-max (a GitHub user) maintains it in BioTender-max/awesome-bio-agent-skills, which has 199 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on July 1, 2026.

Source: BioTender-max/awesome-bio-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.