OpenFold3
SkillProductivityLets your agent run and document protein structure prediction workflows, checking inputs and comparing results for reproducibility.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the OpenFold3 skill
About this capability
Run or plan OpenFold3-style structure prediction workflows. Use when a task asks for open protein or complex prediction, setup, model comparison, or reproducibility around OpenFold-family outputs.
What this skill tells your AI
The instructions your AI receives, as published by companion-inc/feynman in skills/openfold3/SKILL.md and read by ahel’s review.
Use this skill for OpenFold-family structure prediction or comparison.
Workflow:
- Normalize FASTA, chains, templates, MSAs, ligands or partners, seeds, and expected output format.
- Verify model code, checkpoints, databases, and GPU route before running.
- Save the input manifest, environment lockfile, command, logs, structure outputs, confidence files, and runtime metadata.
- Compare against AlphaFold-style, ESMFold-style, PDB, or literature evidence when the result affects a decision.
- Report reproducibility gaps such as missing databases, unavailable weights, failed templates, or route-specific approximations.
Do not present an OpenFold-family output without version and input provenance.
Signals
- GitHub stars
- 9k
- Forks
- 1k
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
openfold3- Source
- github.com/companion-inc/feynman