Chai1
Apps & Automationchai1Chai1 is an Agent Skill for apps & automation 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 prepare Chai-1 structure predictions for biomolecular complexes. Use when a task asks for Chai-1 inputs, multimers, ligand/nucleic acid structure prediction, or confidence review.
QUICK START
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.
Prompt to paste
Inspect the Agent Skill at https://github.com/companion-inc/feynman/blob/HEAD/skills/chai1/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/chai1, 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.
Chai-1
Use this skill for Chai-1-style biomolecular structure prediction and review.
Workflow:
- Convert the research question into an input manifest with chains, sequences, ligands, nucleic acids, templates, restraints, and seeds.
- Verify the available execution path before running: local model, managed endpoint, Modal job, SSH host, or documented remote API.
- Capture package/model version, exact input manifest, hardware, command or request body, and all raw output files.
- Save structure files and confidence artifacts in the active Feynman output folder.
- Review chain coverage, interface confidence, ligand plausibility, stereochemistry warnings, and conflicts with known structures.
Use the structure as evidence only after the provenance and confidence checks are attached.