NVIDIA/skills is a catalogue of portable instruction sets that teach coding agents how to use NVIDIA software for robotics, simulation, CUDA, retrieval-augmented generation, and related workflows. Developers install these skills in agents such as Claude Code or Codex, while the catalogue mirrors skills maintained in separate NVIDIA product repositories.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/NVIDIA/skillsnpx agentmods add skills/nvidia/skills/bionemo-complexa-evaluate-pdbsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nvidia/skills/bionemo-complexa-evaluate-pdbs)<a href="https://agentmods.dev/skills/nvidia/skills/bionemo-complexa-evaluate-pdbs"><img src="https://agentmods.dev/badge/skills/nvidia/skills/bionemo-complexa-evaluate-pdbs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nvidia/skills/bionemo-complexa-evaluate-pdbs"><img src="https://agentmods.dev/badge/skills/nvidia/skills/bionemo-complexa-evaluate-pdbs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00108 | $0.03395 |
| Opus 5.5 | $0.00043 | $0.01358 |
| Sonnet 5.5 | $0.00022 | $0.00679 |
| Haiku 4.5 | $0.00011 | $0.00340 |
Grade A, and why
complexa-evaluate-pdbs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Complexa Evaluate-PDBs Skill
Score a directory of pre-existing PDB files against the same metrics Proteina-Complexa uses internally. Wraps complexa analysis <evaluate_config> ++sample_storage_path=<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 (rf3_latest), ESMFold (esmfold), or Boltz2 (boltz2_default). - Compute binder interface metrics:
i_pAE,min_ipAE,i_pTM,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
result_type.
Step 1: Pre-flight
Always check GPU / disk / tool binaries before launching a refold job. RF3 and ColabDesign-AF2 are large.
bash scripts/preflight.sh
Surface from preflight.json:
gpu.availableandgpu.vram_gb— colabdesign/RF3 need ≥40 GB; ESMFold tolerates ≥24 GB.env.missing_required— must include the keys for the chosen folding backend:colabdesign→AF2_DIRrf3_latest→RF3_CKPT_PATH,RF3_EXEC_PATHesmfold→ ESMFold weights resolvable
tools.{foldseek,mmseqs}— required byaggregation.compute_diversity/compute_mmseqs_diversity(both defaulttrue).
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).
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- BENCHMARK.md 7.7 KB
- config/skillspector-baseline.yml 1.2 KB
- evals/evals.json 5.0 KB
- evals/trigger_evals.json 1.4 KB
- references/CONFIGURATION_GUIDE.md 35 KB
- references/eval_configs.md 12 KB
- references/EVALUATION_METRICS.md 56 KB
- references/hardware.md 4.8 KB
- references/INFERENCE.md 15 KB
- references/SEARCH_METADATA.md 7.7 KB
- references/SWEEP.md 11 KB
- scripts/preflight.sh 8.4 KB runs code
- scripts/write_manifest.py 9.6 KB runs code
- skill-card.md 5.3 KB
- skill.oms.sig 7.0 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 219 lines · 108 tokens per session scan A 0fbdb6f6dfe5
complexa-evaluate-pdbs is a skill published in the GitHub repository NVIDIA/skills (3,722 stars, last pushed today), licensed Apache-2.0. It adds 108 tokens to every session and 3,395 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-22.
Other skills, from other repositories
experiment-tracking-and-reproducibility
Use when a change trains a model, reports a metric, or touches seeds, data or model versions, the lockfile, MLflow or DVC — what every run must log, seeding, environment pinning, data versioning and keeping tests off the shared tracking server.
qec-construct
Verifier-in-the-loop CONSTRUCTION of quantum error-correcting codes with transversal non-Clifford gates (CCZ/T). Applies whenever the project goal is a new or better code/construction — INCLUDING search-phrased goals ("find codes beating X"), where the construct-loop (propose algebraic rule → qverify → debug) is the…
manim-video
Create mathematical, geometric and scientific videos with Manim Community in Python. Use when animating equations, graphs, transformations or educational explanations; distinguish Manim Community from ManimGL and deliver a rendered, inspected video.
arxiv-summarizer-orchestrator
End-to-end orchestration skill for periodic arXiv collection and reporting using three sub-skills: arxiv-search-collector, arxiv-paper-processor, and arxiv-batch-reporter. Supports manual language control across all markdown outputs and Stage-B processing strategy (subagentparallel default max 5, or serial).
ui-ux-craft
Use when designing or building any screen, section or component that a user sees — visual hierarchy, typography, colour, spacing, states, forms and how to avoid the generic AI look.
analiz-human-review-gate
Use when you finish an analiz report - the human must approve the analysis before any implementation task is created, via the analizreview column.