OpenParable
Skip to content
← Back to skills

Alphafold2

Research
alphafold2

Alphafold2 is an Agent Skill for research published in the companion-inc/feynman repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Predict or audit protein structures with AlphaFold2-style workflows. Use when a research task needs monomer/multimer structure prediction, MSA/template handling, confidence metrics, or comparison against PDB/AlphaFold references.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/companion-inc/feynman/blob/HEAD/skills/alphafold2/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/alphafold2, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

AlphaFold2

Use this skill for protein-structure prediction or parity checks around AlphaFold2-style outputs.

Workflow:

  1. Capture the biological question, sequence identifiers, FASTA input, oligomer state, organism, and expected cofactors or partners.
  2. Verify the execution route before running: local install, managed endpoint, Modal/SSH job, or a documented public source. Do not assume weights, databases, or GPUs exist.
  3. Save inputs, command or endpoint payload, model settings, stdout/stderr, and raw outputs under the active Feynman artifact folder.
  4. Report pLDDT, PAE, ranking confidence, chain coverage, truncation, templates/MSA provenance, and any residues or interfaces that should not be trusted.
  5. Compare against known structures or AlphaFold DB records when the claim depends on novelty, domain movement, interface geometry, or mutation impact.

Outputs should include the FASTA, predicted PDB/mmCIF, confidence files when available, a short method note, and a .provenance.md sidecar.