Protein Structure
- 14 installs
- 869 repo stars
- Updated June 8, 2026
- beita6969/scienceclaw
protein-structure is a Claude skill that guides analysis and prediction of protein 3D structures, including AlphaFold interpretation, binding-site detection, and molecular docking.
About
This skill directs an agent through structural-biology analysis of proteins: retrieving or predicting 3D structures, assessing quality (resolution, pLDDT/PAE), identifying binding sites, running molecular docking, and comparing structures via alignment. It names databases (PDB, AlphaFold DB, UniProt) and tools (AutoDock Vina, PyMOL, ChimeraX). Researchers use it when working with PDB files, protein folding, or binding-site analysis.
- 7-step methodology for protein structure retrieval, prediction, and analysis
- Covers AlphaFold/ESMFold, molecular docking, and structural alignment (RMSD/TM-score)
- References PDB, AlphaFold DB, UniProt, BindingDB and viz tools (PyMOL, ChimeraX)
Protein Structure by the numbers
- 14 all-time installs (skills.sh)
- Ranked #1,388 of 2,065 Data Science & ML skills by installs in the Skillselion catalog
- Data as of Aug 2, 2026 (Skillselion catalog sync)
protein-structure capabilities & compatibility
Free; uses public databases (PDB, AlphaFold DB, UniProt) and open tools.
- Capabilities
- data analysis
- Use cases
- research · data analysis
- Pricing
- Free
What protein-structure says it does
Analyzes protein 3D structures, performs homology modeling, interprets AlphaFold predictions, conducts molecular docking, and evaluates protein-ligand interactions
Align structures using TM-align or FATCAT. Report RMSD and TM-score.
npx skills add https://github.com/beita6969/scienceclaw --skill protein-structureAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 14 |
|---|---|
| repo stars | ★ 869 |
| Last updated | June 8, 2026 |
| Repository | beita6969/scienceclaw ↗ |
What it does
Analyze and predict protein 3D structures, binding sites, and docking for structural biology.
Who is it for?
PDB-file analysis, AlphaFold interpretation, binding-site detection, and docking.
When should I use this skill?
Users ask about PDB files, protein folding, binding sites, or structural biology.
What you get
- Structure quality reports
- Binding-site and docking analyses
- Structural alignments with RMSD/TM-score
By the numbers
- 7-step methodology
- 7-item quality checklist
Files
When to Trigger
Activate this skill when the user mentions:
- Protein folding, AlphaFold, ESMFold, RoseTTAFold
- PDB files, structural analysis, Ramachandran plots
- Molecular docking, binding affinity, binding pockets
- Homology modeling, threading, ab initio structure prediction
- Protein-protein interactions (PPI), interface analysis
- Structural alignment, RMSD, TM-score
- Cryo-EM, X-ray crystallography data interpretation
Step-by-Step Methodology
1. Retrieve or predict structure - Search PDB for experimental structures (by UniProt ID or gene name). If unavailable, use AlphaFold DB or run ESMFold. Check pLDDT confidence scores for predicted structures. 2. Quality assessment - For experimental structures: check resolution, R-free, and completeness. For predictions: evaluate pLDDT per-residue and PAE (predicted aligned error) matrices. 3. Structural analysis - Identify secondary structure elements (helices, sheets, loops). Compute solvent-accessible surface area. Map conserved residues and functional domains. 4. Binding site identification - Use fpocket, SiteMap, or DoGSiteScorer for pocket detection. Cross-reference with known ligand binding from PDBe or BindingDB. 5. Molecular docking - Recommend AutoDock Vina, GNINA, or Glide. Define grid box around binding site. Report binding energy (kcal/mol) and key interactions (H-bonds, hydrophobic, pi-stacking). 6. Structural comparison - Align structures using TM-align or FATCAT. Report RMSD and TM-score. Identify conformational changes between states. 7. Visualization guidance - Recommend PyMOL, ChimeraX, or Mol* for rendering. Specify coloring schemes (by chain, B-factor, electrostatics, or conservation).
Key Databases and Tools
- PDB / PDBe - Experimental protein structures
- AlphaFold DB - AI-predicted structures for UniProt entries
- UniProt - Protein sequences, domains, and annotations
- InterPro / Pfam - Domain classification
- BindingDB / ChEMBL - Binding affinity data
- RCSB PDB REST API - Programmatic structure queries
- PDBe-KB - Aggregated structural annotations
Output Format
- Report structures with PDB ID, resolution, method, and chain identifiers.
- Binding energies in kcal/mol with interaction fingerprints.
- Structural alignments with RMSD (in Angstroms) and TM-score.
- Residue numbering must match the canonical UniProt sequence or PDB SEQRES.
- Include PyMOL/ChimeraX commands for reproducing visualizations.
Quality Checklist
- [ ] Structure source and method (X-ray, cryo-EM, NMR, predicted) clearly stated
- [ ] Resolution or confidence metric (pLDDT) reported
- [ ] Binding site residues listed with chain and numbering
- [ ] Docking results include top poses and interaction details
- [ ] Limitations of predicted structures acknowledged where relevant
- [ ] All PDB IDs verified as valid and current
- [ ] Biological assembly vs. asymmetric unit distinguished
Related skills
Microsoft FoundryDeploy, evaluate, and continuously improve Microsoft Foundry agents from a single agent interface.490k1.3k
Ai Research ReproductionOrchestrate trustworthy, auditable reproduction of deep learning repositories directly from their READMEs.176k511Run TrainSafely execute selected deep learning training commands with standardized evidence capture.176k511Explore RunSafely run isolated exploratory experiments with clear recording and conservative selection before committing changes.176k511Paper Context ResolverFetch precise reproduction-critical details like dataset splits, preprocessing steps, or evaluation protocols from the original academic paper when the repo README leav141k511Repo Intake And PlanScan unfamiliar AI research repositories and receive a minimal, trustworthy reproduction target before investing significant time.140k511FAQ
What structure sources does this skill use?
It searches the PDB for experimental structures, falls back to AlphaFold DB or ESMFold predictions, and checks pLDDT confidence scores.
How does it compare two protein structures?
It aligns them with TM-align or FATCAT and reports RMSD in Angstroms and TM-score, identifying conformational changes.