Agent skill · nvidia

complexa-evaluate-pdbs

Agent runbook for evaluating an existing PDB directory through the separately installed first-party Proteina-Complexa CLI. Use to refold or score designs, compute interface pAE, i_pLDDT, scRMSD, motif RMSD, or designability, run complexa analysis, or assess third-party BindCraft, AlphaProteo, or RFdiffusion outputs. SKILL.md selects and invokes the evaluation configuration; bundled executables only inspect local readiness and write a run manifest.

What it needs

About 6k tokens when loaded.

What this skill does

Complexa Evaluate-PDBs Skill Score a directory of pre-existing PDB files against the same metrics Proteina-Complexa uses internally. Wraps complexa analysis <evaluateconfig> ++samplestoragepath=<dir>: the CLI runs the evaluate step (refold + interface metrics + monomer metrics) and then the analyze step (success thresholds, diversity, pass-rate CSVs). Do not run complexa generate here — the inputs already exist. What this skill enables Re-fold a directory of designed PDBs with AF2 (colabdesign), RF3 (rf3latest), ESMFold (esmfold), or Boltz2 (boltz2default). Compute binder interface metrics: ipAE, minipAE, ipTM, pLDDT, binder/complex scRMSD. Compute monomer designability (ProteinMPNN-redesigned scRMSD) and codesignability (original sequence refold scRMSD). For motif inputs: motif RMSD (CA + all-atom), motif-region designability/codesignability, sequence recovery. Aggregate into per-PDB CSVs plus pass-rate summaries using the default thresholds for the resulttype. Step 1: Pre-flight Always check GPU / disk / tool binaries before launching a refold job. RF3 and ColabDesign-AF2 are large. Surface from preflight.json: gpu.available and gpu.vramgb — colabdesign/RF3 need ≥40 GB; ESMFold tolerates ≥24 GB. env.missingrequired — must include the keys for the chosen folding backend: colabdesign → AF2DIR rf3latest → RF3CKPTPATH, RF3EXECPATH esmfold → ESMFold weights resolvable tools.{foldseek,mmseqs} — required by aggregation.computediversity / computemmseqsdiversity (both default true). If any required key is missing, route the user to the complexa-setup skill. Step 2: Identify the design type Like complexa design, evaluation has one default flow (protein binder) and two extensions (ligand binder, AME). The evaluate config you pass to complexa analysis decides everything else (which metrics, which refolder defaults, which thresholds the analyze step applies). …

How to use it

Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:

@skills nvidia/bionemo-complexa-evaluate-pdbs

View the source on GitHub

Browse the @skills marketplace