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
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NVIDIA/skills --skill bionemo-diffdock-nimgit clone --depth 1 https://github.com/NVIDIA/skillsWrote 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-diffdock-nim)<a href="https://agentmods.dev/skills/nvidia/skills/bionemo-diffdock-nim"><img src="https://agentmods.dev/badge/skills/nvidia/skills/bionemo-diffdock-nim/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-diffdock-nim"><img src="https://agentmods.dev/badge/skills/nvidia/skills/bionemo-diffdock-nim.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 | $0.00062 | $0.01143 |
| Opus 5.5 | $0.00025 | $0.00457 |
| Sonnet 5.5 | $0.00012 | $0.00229 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
diffdock-nim scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
until curl -sf http://localhost:8000/v1/health/ready; do sleep 5; done How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DiffDock NIM
Predict protein-ligand binding poses with blind docking. Use this guide for first-pass hosted/local usage; load supplemental files only when needed:
references/api.md: exact hosted/local endpoints, schemas, Docker flags.references/science.md: docking use cases, limits, and handoffs.references/parameters.md: ligand formats, pose counts, diffusion controls.references/validation.md: receptor, ligand, pose, and confidence checks.references/examples.md: compact hosted/local and pose-saving patterns.
Choose Mode
Ask only when context is unclear:
Hosted NVIDIA API or local Docker NIM?
- Hosted:
https://health.api.nvidia.com/v1/biology/mit/diffdock - Local:
http://localhost:8000/molecular-docking/diffdock/generate
The hosted and local paths differ. Local has no /v1/ prefix and uses the
/molecular-docking/ route. Hosted requests use Authorization: Bearer $NGC_API_KEY. Supported local Docker
startup uses NGC_API_KEY (or NVIDIA_API_KEY via the preflight) for
registry login, entitlement checks, and first-run model downloads; pass it
into the container with -e NGC_API_KEY. Local inference requests use no
auth header after readiness. Warm-cache key-free startup varies by
image/version and should not be assumed.
Local Docker
For the exact local preflight (.env load, NVIDIA_API_KEY fallback,
LOCAL_NIM_CACHE, NVIDIA_VISIBLE_DEVICES=0, --shm-size=2G, both --ulimit
flags, docker login, and the docker run for nvcr.io/nim/mit/diffdock:2.2.0),
copy the command block in references/api.md under
Docker Reference verbatim.
Readiness:
until curl -sf http://localhost:8000/v1/health/ready; do sleep 5; done
Prepare Inputs
Protein receptor must be ATOM records only. Strip headers, water, and HETATM.
from pathlib import Path
raw_pdb = Path("protein.pdb").read_text()
protein = "\n".join(line for line in raw_pdb.splitlines() if line.startswith("ATOM"))
if not protein:
raise ValueError("protein.pdb has no ATOM records")
What ships with it
13 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 6.9 KB
- config/skillspector-baseline.yml 876 B
- evals/config.yml 117 B
- evals/evals.json 6.5 KB
- evals/files/protein.pdb 247 KB
- evals/trigger_evals.json 2.2 KB
- references/api.md 4.5 KB
- references/examples.md 2.0 KB
- references/parameters.md 998 B
- references/science.md 1.9 KB
- references/validation.md 1.8 KB
- skill-card.md 4.3 KB
- skill.oms.sig 6.5 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.
- 1mo ago First seen · 119 lines · 62 tokens per session scan A e095daf0c7d9
diffdock-nim is a skill published in the GitHub repository NVIDIA/skills (3,873 stars, last pushed yesterday), licensed Apache-2.0. It adds 62 tokens to every session and 1,143 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-30.
diffdock-nim compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| diffdock-nimNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 62 | Claude Code |
| experiment-tracking-and-reproducibilitymakifbaysal/tasktrooper | Skill | 120 | 16d ago | Apache-2.0 | A | 64 | Claude Code, Codex |
| qec-constructMuuuun/luxas | Skill | 1.2k | 12d ago | MIT | A | 148 | Claude Code, Codex |
| arxiv-summarizer-orchestratorInternLM/WildClawBench | Skill | 534 | yesterday | MIT | A | 75 | Codex |
| manim-videoWrongStack/WrongStack | Skill | 404 | yesterday | MIT | A | 101 | Claude Code, Codex |
| ui-ux-craftmakifbaysal/tasktrooper | Skill | 120 | 16d ago | Apache-2.0 | A | 43 | Claude Code, Codex |
| analiz-human-review-gatemakifbaysal/tasktrooper | Skill | 120 | 16d ago | Apache-2.0 | A | 33 | Claude Code, Codex |