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/mol-3d-viewerWrote 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/mol-3d-viewer)<a href="https://agentmods.dev/skills/internscience/chemclaw/mol-3d-viewer"><img src="https://agentmods.dev/badge/skills/internscience/chemclaw/mol-3d-viewer.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 | $0.00048 | $0.04089 |
| Opus 5 | $0.00024 | $0.02044 |
| Sonnet 5 | $0.00010 | $0.00818 |
| Haiku 4.5 | $0.00005 | $0.00409 |
Grade A, and why
mol-3d-viewer 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 7d 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 — 398 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Molecular 3D Viewer
将 SMILES 字符串或化学名称转换为分子 3D 结构，支持生成 SDF 文件、3D 分子图片和 可交互 HTML 网页（可用鼠标旋转观察）。
触发条件
- 用户提供 SMILES 并要求 3D 可视化
- 提到"3D 分子"、"分子 3D"、"3D 结构"
- 说"3D visualization"、"rotate molecule"、"交互分子"
- 要求生成可旋转的分子模型
- 提供分子文件（SDF、MOL、PDB 等）
功能
- ✅ SMILES → 3D 分子结构
- ✅ IUPAC 名称 → 3D 结构（自动通过 OPSIN 转 SMILES）
- ✅ 分子文件支持 - SDF、MOL、PDB 格式
- ✅ 3D 优化 - 使用 RDKit MMFF94 力场优化几何结构
- ✅ SDF 文件输出 - 标准分子结构文件格式
- ✅ 真正的 3D 渲染图片 - 基于 3D 坐标渲染，不是 2D 结构图
- ✅ 可交互 HTML - 生成 WebGL 网页，支持鼠标旋转、缩放
- ✅ 多种渲染样式 - 球棍模型、棍状模型、空间填充模型
- ✅ 聚合物支持 - 正确渲染聚合物 3D 结构
- ✅ 批量生成 - 支持多个分子同时处理
- ✅ 分子信息展示 - HTML 中显示分子式、分子量
三种输出格式
1. SDF 文件 (.sdf)
- 格式: Structure Data File
- 用途: 标准分子结构交换格式
- 内容: 3D 坐标、原子、键信息
- 兼容: 支持所有化学软件（ChemDraw、PyMOL 等）
2. 3D 图片 (.png)
- 格式: PNG 位图
- 渲染: 基于真实 3D 坐标渲染
- 样式: 默认球棍模型（ball_stick）
- 尺寸: 800x600（可自定义）
- 用途: 快速预览、文档插入
3. 可交互 HTML (.html)
- 渲染: 3Dmol.js WebGL
- 功能:
- 🖱️ 鼠标旋转、平移、缩放
- 🎨 多种显示模式切换
- 📊 分子式、分子量展示
- 💾 截图保存功能
- 🔄 自动旋转开关
- 特点: 分子自动居中，打开即可见
使用方法
对话框中使用
生成 ethanol 的 3D 分子结构
SMILES: CCO，创建 3D 可交互网页
可视化 aspirin 的 3D 结构，保存为 HTML
poly[oxy(1-methylethylene)] 生成 3D 模型
从文件 molecule.sdf 生成 3D 展示
批量生成 3D：CCO,C1=CC=CC=C1
命令行使用
# 生成全部三种输出（SDF + 3D 图片 + HTML）
python3 scripts/mol_3d_viewer.py --smiles "CCO" --output ethanol
# 只生成 SDF 文件
python3 scripts/mol_3d_viewer.py --smiles "CCO" --output ethanol --sdf-only
# 只生成 3D 图片
python3 scripts/mol_3d_viewer.py --smiles "CCO" --output ethanol --image-only
# 只生成 HTML
python3 scripts/mol_3d_viewer.py --smiles "CCO" --output ethanol --html-only
# 从名称生成
python3 scripts/mol_3d_viewer.py --name "aspirin" --output aspirin
# 自定义渲染样式
python3 scripts/mol_3d_viewer.py --smiles "CCO" --output ethanol --style ball_stick
# 批量生成
python3 scripts/mol_3d_viewer.py --smiles "CCO,C1=CC=CC=C1" --output-dir ./3d_molecules
参数说明
| 参数 | 简写 | 说明 | 默认值 |
|---|---|---|---|
--smiles |
-s |
SMILES 字符串（可多个） | - |
--name |
-n |
IUPAC 名称 | - |
--input |
-i |
输入分子文件 | - |
--output |
-o |
输出文件基础路径 | 自动生成 |
--output-dir |
-d |
输出目录（批量模式） | ~/.openclaw/media/mol-3d-viewer |
--sdf-only |
只生成 SDF 文件 | false |
|
--image-only |
只生成 3D 图片 | false |
|
--html-only |
只生成 HTML | false |
|
--style |
-S |
渲染样式 | ball_stick |
--width |
-W |
宽度（像素） | 800 |
--height |
-H |
高度（像素） | 600 |
--bg-color |
-b |
背景颜色 | white |
--show-labels |
-l |
显示原子标签 | true |
--hide-labels |
隐藏原子标签 | false |
|
--auto-rotate |
-r |
HTML 自动旋转 | false |
--force-field |
力场类型 | mmff94 |
|
--max-steps |
优化最大步数 | 200 |
What ships with it
4 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.
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.
- 7d ago First seen · 398 lines · 48 tokens per session scan A 636dd8047ab2
mol-3d-viewer is a skill published in the GitHub repository InternScience/ChemClaw (52 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 4,089 once invoked, about $0.0002 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…
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.
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…
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…