OpenParable
Skip to content
← Back to skills

Chai1

Apps & Automation
chai1

Chai1 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.

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/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:

  1. Convert the research question into an input manifest with chains, sequences, ligands, nucleic acids, templates, restraints, and seeds.
  2. Verify the available execution path before running: local model, managed endpoint, Modal job, SSH host, or documented remote API.
  3. Capture package/model version, exact input manifest, hardware, command or request body, and all raw output files.
  4. Save structure files and confidence artifacts in the active Feynman output folder.
  5. 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.