Boltz
ResearchboltzBoltz 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.
Run or plan Boltz biomolecular structure predictions for proteins, complexes, ligands, or nucleic-acid assemblies. Use when a task asks for Boltz setup, inputs, outputs, confidence interpretation, or reproduction.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/companion-inc/feynman/blob/HEAD/skills/boltz/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/boltz, 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.
Boltz
Use this skill when the active research run needs Boltz-style biomolecular prediction.
Workflow:
- Normalize inputs into explicit entities: protein chains, nucleic-acid chains, ligands, covalent links, templates, constraints, and seeds.
- Verify the available execution route from Feynman Settings, notebook runtimes, managed endpoints, Modal, SSH, or local installs before claiming the model can run.
- Run only from a recorded input manifest. Preserve exact sequences, ligand identifiers, model parameters, seed, hardware, package version, and command.
- Save structures, confidence outputs, logs, and rendered previews as Feynman artifacts.
- Interpret the output as a hypothesis: separate high-confidence local folds from weak interfaces, ligand poses, flexible regions, and unsupported biological claims.
Do not treat a single attractive structure as proof. Add verification checks against source literature, known structures, or orthogonal experiments when the result drives a decision.