Skip to content

vimalinx/bio-agent / .claude/skills/protein-structure

protein-structure

Verified

Use when planning or staging protein-structure prediction or structure-design work in this workspace, especially when deciding between missing local predictors and the repos that are actually present.

protein-structure

Workspace-level gateway for structure-oriented work. In this repo, the strongest local assets are the checked-out RFdiffusion and evo2 repositories plus Docker, not a ready-to-run AlphaFold/ColabFold desktop stack.

Quick Start

  • Available local assets: /home/vimalinx/Projects/bio_studio/repositories/active/RFdiffusion, /home/vimalinx/Projects/bio_studio/repositories/active/evo2, /usr/bin/docker
  • Fast availability check: command -v colabfold_batch pymol chimera chimerax foldseek mmseqs fpocket
  • Current practical path: use repo-backed Docker workflows rather than assuming local GUI prediction tools exist

When To Use This Tool

  • Deciding how to approach a protein-structure task in this workspace
  • Routing between structure design (RFdiffusion) and sequence-model analysis (evo2)
  • Auditing whether local structure-prediction tools are actually installed before planning around them
  • Staging follow-on structure workflows once prerequisites are satisfied

Common Patterns

# Check which structure tools are really installed
command -v colabfold_batch pymol chimera chimerax foldseek mmseqs fpocket
# Use the local RFdiffusion repo for generative design
cd /home/vimalinx/Projects/bio_studio/repositories/active/RFdiffusion
./test_rfdiffusion.sh
# Inspect the local Evo 2 repo for sequence-model-based analysis
cd /home/vimalinx/Projects/bio_studio/repositories/active/evo2
python examples/run_evo2.py

Recommended Workflow

  1. Verify the required predictor or viewer is actually present before promising a structure workflow.
  2. If you need generative backbone or binder design, start from the local RFdiffusion repo.
  3. If you need sequence-model scoring or embeddings on DNA-scale inputs, evaluate whether Evo 2 is the right supporting asset.
  4. Install missing prediction/visualization tools explicitly before planning around ColabFold, PyMOL, or Chimera-based steps.

Guardrails

  • colabfold_batch, pymol, chimera, chimerax, foldseek, mmseqs, and fpocket are not currently on PATH in this workspace.
  • RFdiffusion is present locally, but its Docker image is not prebuilt yet.
  • The local Evo 2 repo exists, but direct import evo2 currently fails because vortex is missing.
  • Do not present RFdiffusion as a native fold-prediction replacement; it is primarily a generative structure-design workflow.
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 318kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 196kUpdated Claude CodeCodexVerifiedInstall