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/InternScience/ChemClawnpx agentmods add skills/internscience/chemclaw/adme-predictionWrote 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/adme-prediction)<a href="https://agentmods.dev/skills/internscience/chemclaw/adme-prediction"><img src="https://agentmods.dev/badge/skills/internscience/chemclaw/adme-prediction.svg" alt="Measured on agentmods" 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 | $0.00096 | $0.03449 |
| Opus 5 | $0.00048 | $0.01724 |
| Sonnet 5 | $0.00019 | $0.00690 |
| Haiku 4.5 | $0.00010 | $0.00345 |
Grade A, and why
adme-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 8d 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 — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ADME Prediction
ADME（吸收、分布、代谢、排泄）性质预测技能，用于药物发现和开发早期的药物动力学性质评估。
支持的 ADME 性质
| 性质 | 数据集 | 类型 | 说明 |
|---|---|---|---|
| Caco-2 通透性 | Caco2_Wang | 回归 | 预测 Caco-2 细胞有效通透性 (log Papp) |
| PAMPA 通透性 | PAMPA_NCATS | 分类 | 预测人工膜通透性 (高/低 - 中) |
| 肠道吸收 | HIA_Hou | 分类 | 预测人体肠道吸收 (活性/非活性) |
| Pgp 抑制 | Pgp_Broccatelli | 分类 | 预测 P-糖蛋白抑制 (抑制剂/非抑制剂) |
| 生物利用度 | Bioavailability_Ma | 分类 | 预测口服生物利用度 (高/低) |
| 亲脂性 | Lipophilicity_AstraZeneca | 回归 | 预测亲脂性 (logD) |
使用方法
对话框中使用
用户可以直接提供 SMILES 并要求预测：
预测这个分子的 ADME 性质：CCO
计算 Caco-2 通透性：c1ccccc1
这个化合物的肠道吸收怎么样？CC(=O)O
预测 Pgp 抑制活性：CCN(CC)CC
命令行使用
# 预测单个分子
python3 scripts/adme_predictor.py --smiles "CCO"
# 预测特定性质
python3 scripts/adme_predictor.py --smiles "c1ccccc1" --property Caco2_Wang
# 批量预测（从文件读取 SMILES）
python3 scripts/adme_predictor.py --file molecules.smi --output results.json
# 列出所有可用性质
python3 scripts/adme_predictor.py --list
# JSON 输出
python3 scripts/adme_predictor.py --smiles "CCO" --json
参数说明
| 参数 | 简写 | 说明 | 默认值 |
|---|---|---|---|
--smiles |
-s |
SMILES 字符串 | 必需（或 --file） |
--file |
-f |
包含 SMILES 的文件（每行一个） | 必需（或 --smiles） |
--property |
-p |
要预测的性质（可多个） | 全部 |
--output |
-o |
输出文件路径 | 标准输出 |
--json |
-j |
以 JSON 格式输出 | 表格格式 |
--list |
-l |
列出所有可用性质 | - |
--model-dir |
-m |
模型目录 | 默认模型目录 |
工作流程
1. 分子输入
支持多种输入方式：
# 单个 SMILES
smiles = "CCO"
# 从文件读取
with open("molecules.smi") as f:
smiles_list = [line.strip() for line in f]
# 从其他格式转换
from rdkit import Chem
mol = Chem.MolFromMolFile("input.mol")
smiles = Chem.MolToSmiles(mol)
2. 指纹计算
使用 Morgan 指纹（ECFP4）表示分子：
from rdkit.Chem import AllChem
fp = AllChem.GetMorganFingerprintAsBitVect(
mol,
radius=2, # ECFP4
nBits=2048 # 指纹长度
)
3. 性质预测
加载预训练模型进行预测：
# 加载模型
import pickle
with open("models/Caco2_Wang.pkl", "rb") as f:
model = pickle.load(f)
# 预测
prediction = model.predict([fp])[0]
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.
- models/Bioavailability_Ma_metadata.json 556 B
- models/Bioavailability_Ma.pkl 933 KB
- models/Caco2_Wang_metadata.json 644 B
- models/Caco2_Wang.pkl 2666 KB
- models/HIA_Hou_metadata.json 543 B
- models/HIA_Hou.pkl 744 KB
- models/Lipophilicity_AstraZeneca_metadata.json 623 B
- models/Lipophilicity_AstraZeneca.pkl 6048 KB
- models/PAMPA_NCATS_metadata.json 559 B
- models/PAMPA_NCATS.pkl 1725 KB
- models/Pgp_Broccatelli_metadata.json 564 B
- models/Pgp_Broccatelli.pkl 2025 KB
- requirements.txt 64 B
- scripts/adme_predictor.py 12 KB runs code
- scripts/train_tdc_models.py 16 KB runs code
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.
- 8d ago First seen · 438 lines · 96 tokens per session scan A 19bd5fedc8ef
adme-prediction is a skill published in the GitHub repository InternScience/ChemClaw (52 stars, last pushed 5mo ago), licensed MIT. It adds 96 tokens to every session and 3,449 once invoked, about $0.0005 per session on Opus 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
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for 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
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
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.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…