struct-predictor
Local protein structure prediction with AlphaFold, Boltz, or Chai. Compare predicted structures, compute RMSD, visualise 3D models.
Best use case
struct-predictor is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Local protein structure prediction with AlphaFold, Boltz, or Chai. Compare predicted structures, compute RMSD, visualise 3D models.
Teams using struct-predictor should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/struct-predictor/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How struct-predictor Compares
| Feature / Agent | struct-predictor | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Local protein structure prediction with AlphaFold, Boltz, or Chai. Compare predicted structures, compute RMSD, visualise 3D models.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Struct Predictor You are the **Struct Predictor**, a specialised agent for protein structure prediction and analysis. ## Core Capabilities 1. **Structure Prediction**: Run AlphaFold (ColabFold), Boltz-1, or Chai locally 2. **PDB Retrieval**: Fetch experimental structures from PDB via OpenBio 3. **Structure Comparison**: Compute RMSD, TM-score between predicted and reference structures 4. **Confidence Mapping**: Visualise pLDDT and PAE confidence metrics 5. **Report Generation**: Markdown with 3D renders, confidence plots, and comparison tables ## Dependencies - `colabfold_batch` or `boltz` or `chai` (at least one local predictor) - `biopython` (PDB parsing) - Optional: `pymol` (3D rendering), `py3Dmol` (interactive visualisation) ## Example Queries - "Predict the structure of this protein sequence: MKWVTF..." - "Compare AlphaFold prediction of BRCA1 to the experimental PDB structure" - "Show the pLDDT confidence plot for my predicted structure" - "What is the RMSD between these two PDB files?" ## Status **Planned** -- implementation targeting Week 4-5 (Mar 20 - Apr 2).
Related Skills
collecting-infrastructure-metrics
This skill enables Claude to collect comprehensive infrastructure performance metrics across compute, storage, network, containers, load balancers, and databases. It is triggered when the user requests "collect infrastructure metrics", "monitor server performance", "set up performance dashboards", or needs to analyze system resource utilization. The skill configures metrics collection, sets up aggregation, and helps create infrastructure dashboards for health monitoring and capacity tracking. It supports configuration for Prometheus, Datadog, and CloudWatch.
detecting-infrastructure-drift
This skill enables Claude to detect infrastructure drift from a desired state. It uses the `drift-detect` command to identify discrepancies between the current infrastructure configuration and the intended configuration, as defined in infrastructure-as-code tools like Terraform. Use this skill when the user asks to check for infrastructure drift, identify configuration changes, or ensure that the current infrastructure matches the desired state. It is particularly useful in DevOps workflows for maintaining infrastructure consistency and preventing configuration errors. Trigger this skill when the user mentions "drift detection," "infrastructure changes," "configuration drift," or requests a "drift report."
generating-infrastructure-as-code
This skill enables Claude to generate Infrastructure as Code (IaC) configurations. It uses the infrastructure-as-code-generator plugin to create production-ready IaC for Terraform, CloudFormation, Pulumi, ARM Templates, and CDK. Use this skill when the user requests IaC configurations for cloud infrastructure, specifying the platform (e.g., Terraform, CloudFormation) and cloud provider (e.g., AWS, Azure, GCP), or when the user needs help automating infrastructure deployment. Trigger terms include: "generate IaC", "create Terraform", "CloudFormation template", "Pulumi program", "infrastructure code".
checking-infrastructure-compliance
Execute use when you need to work with compliance checking. This skill provides compliance monitoring and validation with comprehensive guidance and automation. Trigger with phrases like "check compliance", "validate policies", or "audit compliance".
suggest-awesome-github-copilot-instructions
Suggest relevant GitHub Copilot instruction files from the awesome-copilot repository based on current repository context and chat history, avoiding duplicates with existing instructions in this repository, and identifying outdated instructions that need updates.
structured-autonomy-plan
Structured Autonomy Planning Prompt
structured-autonomy-implement
Structured Autonomy Implementation Prompt
structured-autonomy-generate
Structured Autonomy Implementation Generator Prompt
import-infrastructure-as-code
Import existing Azure resources into Terraform using Azure CLI discovery and Azure Verified Modules (AVM). Use when asked to reverse-engineer live Azure infrastructure, generate Infrastructure as Code from existing subscriptions/resource groups/resource IDs, map dependencies, derive exact import addresses from downloaded module source, prevent configuration drift, and produce AVM-based Terraform files ready for validation and planning across any Azure resource type.
generate-custom-instructions-from-codebase
Migration and code evolution instructions generator for GitHub Copilot. Analyzes differences between two project versions (branches, commits, or releases) to create precise instructions allowing Copilot to maintain consistency during technology migrations, major refactoring, or framework version upgrades.
folder-structure-blueprint-generator
Comprehensive technology-agnostic prompt for analyzing and documenting project folder structures. Auto-detects project types (.NET, Java, React, Angular, Python, Node.js, Flutter), generates detailed blueprints with visualization options, naming conventions, file placement patterns, and extension templates for maintaining consistent code organization across diverse technology stacks.
copilot-instructions-blueprint-generator
Technology-agnostic blueprint generator for creating comprehensive copilot-instructions.md files that guide GitHub Copilot to produce code consistent with project standards, architecture patterns, and exact technology versions by analyzing existing codebase patterns and avoiding assumptions.