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 InternScience/ChemClaw --skill nmr-predictiongit clone --depth 1 https://github.com/InternScience/ChemClawWrote 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/internscience/chemclaw/nmr-prediction)<a href="https://agentmods.dev/skills/internscience/chemclaw/nmr-prediction"><img src="https://agentmods.dev/badge/skills/internscience/chemclaw/nmr-prediction/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/internscience/chemclaw/nmr-prediction"><img src="https://agentmods.dev/badge/skills/internscience/chemclaw/nmr-prediction.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 | $0.00061 | $0.01186 |
| Opus 5.5 | $0.00024 | $0.00474 |
| Sonnet 5.5 | $0.00012 | $0.00237 |
| Haiku 4.5 | $0.00006 | $0.00119 |
Grade A, and why
nmr-prediction 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 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.
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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NMR Chemical Shift Prediction Skill
When to use this
Use this skill when the user provides a SMILES string and wants:
- Per-atom ¹H or ¹³C liquid-phase NMR chemical shifts (ppm)
- Simulated NMR spectrum image (Lorentzian line-shape)
- Quick deep-learning based prediction without DFT
Inputs
- SMILES string (required, e.g.
CCOfor ethanol) --nucleus H | C | both(optional, defaultboth)
Outputs
/tmp/chemclaw/nmr_1H_<smiles>.png— ¹H NMR spectrum/tmp/chemclaw/nmr_13C_<smiles>.png— ¹³C NMR spectrum- Console: per-atom chemical shifts (ppm)
目录结构
nmr-prediction/
├── SKILL.md
├── nmr_prediction.py
├── requirements.txt
└── assets/
├── NMRNet/ ← NMRNet 精简推理代码 + `oc_limit_dict.txt`
└── Uni-Core/ ← Uni-Core 基础库(需要先 install)
模型权重(大文件,不放进 repo)存放于 /tmp/weights/,通过 --setup 自动下载。
环境安装 (首次)
1. 准备 assets/
# 将 NMRNet 放入 assets/(从 GitHub 下载 zip 后解压)
cp -r ~/Downloads/NMRNet-main nmr-prediction/assets/NMRNet
# 将 Uni-Core 放入 assets/ 并安装
cp -r ~/Downloads/Uni-Core-main nmr-prediction/assets/Uni-Core
cd nmr-prediction/assets/Uni-Core
python setup.py install # macOS 默认禁用 CUDA,直接执行
2. 安装 Python 依赖
cd nmr-prediction
pip install -r requirements.txt
# 如果还没装 torch:pip install torch (CPU 版即可)
3. 下载模型权重 + scaler → /tmp/weights/
cd nmr-prediction
python nmr_prediction.py --setup
此命令通过 remotezip 从 Zenodo 仅提取所需文件:
- H/C 模型 checkpoint(各 ~560 MB)→
/tmp/weights/finetune/liquid/.../ - H/C 液相 scaler(各 623 B)→ 同上目录
注意:NMRNet 仓库自带的
demo/notebook/scaler/是固态 NMR scaler,不适用于液相预测。 当前 skill 只保留 NMRNet 的精简推理代码与oc_limit_dict.txt,不依赖demo/数据目录。
How to run(环境已准备好时)
cd nmr-prediction
# 预测乙醇的 ¹H + ¹³C 谱
python nmr_prediction.py "CCO"
# 只预测苯的 ¹³C 谱
python nmr_prediction.py "c1ccccc1" --nucleus C
# 预测咖啡因的 ¹H 谱
python nmr_prediction.py "Cn1cnc2c1c(=O)n(c(=O)n2C)C" --nucleus H
运行原理(Pipeline)
SMILES
↓ RDKit: AddHs + EmbedMolecule + MMFFOptimize
3D 分子坐标 (atoms + coordinates)
↓ atoms_target_mask: 标记目标元素 (H 或 C) 为 1
NMRNet 数据记录 (dict)
↓ UniMatModel (SE(3)-Transformer, unimol_large 架构)
每原子预测化学位移 (scaled)
↓ TargetScaler.inverse_transform
化学位移 (ppm)
↓ Lorentzian 叠加
NMR 谱图 PNG
What ships with it
60 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.
- assets/NMRNet/.gitignore 3.3 KB
- assets/NMRNet/data/README.md 21 B
- assets/NMRNet/figure/framework.jpg 1034 KB
- assets/NMRNet/LICENSE 1.0 KB
- assets/NMRNet/oc_limit_dict.txt 92 B
- assets/NMRNet/README.md 5.3 KB
- assets/NMRNet/script/finetune_5cv.sh 3.5 KB runs code
- assets/NMRNet/script/infer.sh 1.5 KB runs code
- assets/NMRNet/script/pretrain_rcut.sh 2.8 KB runs code
- assets/NMRNet/uninmr/__init__.py 97 B runs code
- assets/NMRNet/uninmr/data/__init__.py 973 B runs code
- assets/NMRNet/uninmr/data/conformer_dataset.py 2.2 KB runs code
- assets/NMRNet/uninmr/data/cropping_dataset.py 1.5 KB runs code
- assets/NMRNet/uninmr/data/distance_dataset.py 3.3 KB runs code
- assets/NMRNet/uninmr/data/key_dataset.py 1.8 KB runs code
- assets/NMRNet/uninmr/data/lattice_dataset.py 1.7 KB runs code
- assets/NMRNet/uninmr/data/lmdb_dataset.py 5.5 KB runs code
- assets/NMRNet/uninmr/data/mask_points_chunk_dataset.py 5.5 KB runs code
- assets/NMRNet/uninmr/data/mask_points_dataset.py 5.4 KB runs code
- assets/NMRNet/uninmr/data/normalize_dataset.py 1.3 KB runs code
- assets/NMRNet/uninmr/data/pad_dataset.py 5.6 KB runs code
- assets/NMRNet/uninmr/data/remove_hydrogen_dataset.py 1.1 KB runs code
- assets/NMRNet/uninmr/data/resample_dataset.py 4.3 KB runs code
- assets/NMRNet/uninmr/data/select_token_dataset.py 2.0 KB runs code
- assets/NMRNet/uninmr/infer.py 4.1 KB runs code
- assets/NMRNet/uninmr/losses/__init__.py 272 B runs code
- assets/NMRNet/uninmr/losses/atom_regloss.py 12 KB runs code
- assets/NMRNet/uninmr/losses/regloss.py 18 KB runs code
- assets/NMRNet/uninmr/losses/unimat_rcut.py 7.3 KB runs code
- assets/NMRNet/uninmr/losses/unimat.py 6.7 KB runs code
- assets/NMRNet/uninmr/models/__init__.py 229 B runs code
- assets/NMRNet/uninmr/models/transformer_encoder_with_pair.py 5.5 KB runs code
- assets/NMRNet/uninmr/models/unimat.py 23 KB runs code
- assets/NMRNet/uninmr/tasks/__init__.py 271 B runs code
- assets/NMRNet/uninmr/tasks/unimat_rcut.py 10 KB runs code
- assets/NMRNet/uninmr/tasks/unimat.py 9.6 KB runs code
- assets/NMRNet/uninmr/tasks/uninmr.py 18 KB runs code
- assets/NMRNet/uninmr/utils/__init__.py 74 B runs code
- assets/NMRNet/uninmr/utils/data_preparation/__init__.py 34 B runs code
- assets/NMRNet/uninmr/utils/data_preparation/nmrshiftdb2_2018.py 1.7 KB runs code
- assets/NMRNet/uninmr/utils/data_preparation/nmrshiftdb2_2024.py 9.9 KB runs code
- assets/NMRNet/uninmr/utils/data_preparation/qm9nmr.py 3.0 KB runs code
- assets/NMRNet/uninmr/utils/data_preparation/write_lmdb.py 811 B runs code
- assets/NMRNet/uninmr/utils/data_scaler.py 2.6 KB runs code
- assets/NMRNet/uninmr/utils/get_result.py 5.4 KB runs code
- assets/NMRNet/uninmr/utils/parse.py 395 B runs code
- assets/NMRNet/weight/README.md 54 B
- assets/Uni-Core/.github/workflows/cuda/cu102-Linux-env.sh 240 B runs code
- assets/Uni-Core/.github/workflows/cuda/cu102-Linux.sh 734 B runs code
- assets/Uni-Core/.github/workflows/cuda/cu113-Linux-env.sh 248 B runs code
- assets/Uni-Core/.github/workflows/cuda/cu113-Linux.sh 701 B runs code
- assets/Uni-Core/.github/workflows/cuda/cu116-Linux-env.sh 248 B runs code
- assets/Uni-Core/.github/workflows/cuda/cu116-Linux.sh 701 B runs code
- assets/Uni-Core/.github/workflows/cuda/cu117-Linux-env.sh 210 B runs code
- assets/Uni-Core/.github/workflows/cuda/cu117-Linux.sh 719 B runs code
- assets/Uni-Core/.github/workflows/cuda/cu118-Linux-env.sh 210 B runs code
- assets/Uni-Core/.github/workflows/cuda/cu118-Linux.sh 719 B runs code
- assets/Uni-Core/.github/workflows/docker_rdma_latest.yml 1.8 KB
- assets/Uni-Core/.github/workflows/env.sh 1.1 KB runs code
- assets/Uni-Core/.github/workflows/publish.yml 654 B
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 · 118 lines · 61 tokens per session scan A ee6524a0721a
nmr-prediction is a skill published in the GitHub repository InternScience/ChemClaw (53 stars, last pushed 6mo ago), licensed MIT. It adds 61 tokens to every session and 1,186 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
presenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.