Back to catalog / Integrations
Screen an Existing Protein Binder Library
Rank supplied protein, peptide, or antibody candidates against a target.
Skills
This workflow screens an existing library rather than designing new binders. Normalize the target and candidate sequences as complex inputs, run `estimate-cost`, show the estimate, and wait for explicit user approval before submission. Rank by `binding_confidence` and inspect structures for leading hits. Check target variant, chain assignments, and residue mapping; a model score is not experimental binding evidence.
Permissions
Prerequisites
- An authenticated Boltz API CLI, target sequence, and candidate library; job execution requires budget approval.
Permissions
- Uploads user-provided sequence/complex data and submits a remote job that may incur charges; downloading writes structures and result files. Require explicit approval of the estimate before submission.
Limitations
Rankings are computational leads, not experimental validation or medical advice. Chain definitions, templates, and target versions affect results.
Pinned upstream source
- Repository
- openai/plugins
- File path
- plugins/boltz-api-cli/skills/boltz-protein-screen/SKILL.md
- Pinned commit
0722921d5542fc593105c27bd52630babd8b8c2a- Source checked
- 2026-10-14 · Reviewed against the pinned upstream source
Repository metrics
These values describe the upstream repository, not popularity or likes for an individual skill or playbook.
- Stars
- Not collected
- Forks
- Not collected
- Observed at
- Not collected
No metrics snapshot is available yet.
License: MIT
Compatible tools
Boltz API CLI
Main topic
Turn ecommerce campaign materials into a reviewable weekly brief