<< All versions

Skill v1.0.1

currentAutomated scan100/100
eightmm/codex-science/cx-boltz-structure-prediction

+2 new

──Details
PublishedNovember 5, 2026 at 08:14 PM
Content Hashsha256:5ac35ca48f010c8e...
Git SHA79a408e0987d
Bump Typepatch
Compare with v1.0.0
──Files
Files (1 file, 2.2 KB)
SKILL.md2.2 KBactive
SKILL.md · 38 lines · 2.2 KB

name: cx-boltz-structure-prediction description: "Predict 3D biomolecular structures and binding affinity with the open-source Boltz model — proteins, complexes, nucleic acids, and protein-ligand systems from sequence. Use when the user wants a predicted structure or affinity from sequence (not an experimental structure or a database lookup). Downloads and installs Boltz into an isolated uv environment and runs it." metadata: version: "1.0.1"


<!-- Generated by scripts/generate_wrappers.py; do not edit. -->

Cx Boltz Structure Prediction

Use this Codex adapter for the pinned upstream scientific skill.

Catalog status

  • Status: active
  • Source: cx
  • Audit reasons: none
  • Upstream license: MIT
  • Inventory: ../../inventory.json
  • Upstream instructions: ../../../authored-skills/boltz-structure-prediction/SKILL.md

Procedure

  1. Resolve the plugin root as three directories above this skill directory.
  2. Run "<plugin-root>/scripts/python_runtime.sh" "<plugin-root>/scripts/search_skills.py" --name cx-boltz-structure-prediction and verify the record's status, reasons, and source path and the source's pinned commit (empty for first-party cx skills) from its output instead of reading inventory.json.
  3. Read the upstream instructions only after confirming this record is still active in the current inventory.
  4. Treat upstream frontmatter as source metadata, not as Codex configuration. Follow the instruction body only where it is compatible with available Codex tools and the current user-approved plan.
  5. Treat tools named for another agent runtime as capability requests. Map them to an available Codex tool only when the behavior is equivalent; otherwise report the unavailable capability.
  6. Ask before credentials, package installation, new network hosts, remote compute, writes, paid services, destructive actions, or imported executable code.
  7. Use $science-provenance for produced scientific outputs and $science-review before presenting scientific claims.

Boundaries

  • This wrapper does not grant credentials, network access, package installation, or script execution.
  • Do not change an inactive record to active from inside a research task.
  • Preserve failures, uncertainty, source identifiers, and licensing constraints.
← v1.0.0All versions