Back to catalog / Integrations
Screen Small Molecules Against a Target
Rank a supplied SMILES library against a target and inspect the accompanying ADME estimates.
Skills
Use a user-supplied compound library and protein target. Normalize SMILES and target inputs, leaving server-side filters at their defaults unless custom filters are requested. Estimate cost, disclose it, and wait for approval before submitting the remote screen. After download, rank by `binding_confidence` or another explicitly chosen objective and inspect each compound’s status and structure; treat ADME as an early auxiliary estimate.
Permissions
Prerequisites
- An authenticated Boltz CLI, target protein, and readable SMILES/CSV/text library; job execution requires budget approval.
Permissions
- Uploads target and compound data, submits a potentially billable job, and saves remote outputs and local structures. Run only after the user approves the estimate.
Limitations
This screens an existing library against a target; it is not de novo design or target-free ADME. Model ranking does not replace experiments, and library size affects cost.
Pinned upstream source
- Repository
- openai/plugins
- File path
- plugins/boltz-api-cli/skills/boltz-small-molecule-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