OpenParable
Skip to content
← Back to skills

Fair Esm2

Research
fair-esm2

Fair Esm2 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.

Use ESM2 protein language models for embeddings, mutation scoring, remote homology, or representation analysis. Use when a task needs protein embeddings, zero-shot variant scores, clustering, or sequence-function triage.

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/fair-esm2/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/fair-esm2, 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.

Fair ESM2

Use this skill for ESM2-style protein language model analysis.

Workflow:

  1. Normalize proteins into FASTA with stable identifiers and mutation notation.
  2. Verify the local package, checkpoint, endpoint, or notebook route before execution.
  3. Save embeddings, variant-score tables, clustering plots, model version, command, and runtime logs.
  4. Compare model-derived rankings against UniProt, structures, conservation, assays, or literature.
  5. Mark sequence regions with poor coverage, disorder, low homology, or domain-boundary ambiguity.

Use ESM2 outputs as features or hypotheses unless a source-backed validation step supports the conclusion.