Python Executor
cortega26/chile-hub
Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh).
3Dmol.js WebGL molecular visualization emitted as self-contained HTML.
$ npx skills add jaechang-hits/SciAgent-Skills --skill molecular-visualization-3dmol -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jaechang-hits/SciAgent-Skills molecular-visualization-3dmol --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/data-visualization/molecular-visualization-3dmol .claude/skills/molecular-visualization-3dmol && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "molecular-visualization-3dmol" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/data-visualization/molecular-visualization-3dmol into .claude/skills/molecular-visualization-3dmol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "molecular-visualization-3dmol", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/data-visualization/molecular-visualization-3dmolType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jaechang-hits/SciAgent-Skills --skill molecular-visualization-3dmol -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jaechang-hits/SciAgent-Skills molecular-visualization-3dmol --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/data-visualization/molecular-visualization-3dmol .agents/skills/molecular-visualization-3dmol && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "molecular-visualization-3dmol" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/data-visualization/molecular-visualization-3dmol into .agents/skills/molecular-visualization-3dmol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "molecular-visualization-3dmol", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jaechang-hits/SciAgent-Skills --skill molecular-visualization-3dmol -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jaechang-hits/SciAgent-Skills molecular-visualization-3dmol --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/data-visualization/molecular-visualization-3dmol .cursor/skills/molecular-visualization-3dmol && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "molecular-visualization-3dmol" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/data-visualization/molecular-visualization-3dmol into .cursor/skills/molecular-visualization-3dmol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "molecular-visualization-3dmol", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jaechang-hits/SciAgent-Skills.git --path skills/data-visualization/molecular-visualization-3dmol--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jaechang-hits/SciAgent-Skills --skill molecular-visualization-3dmol -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jaechang-hits/SciAgent-Skills molecular-visualization-3dmol --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/data-visualization/molecular-visualization-3dmol .gemini/skills/molecular-visualization-3dmol && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "molecular-visualization-3dmol" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/data-visualization/molecular-visualization-3dmol into .gemini/skills/molecular-visualization-3dmol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "molecular-visualization-3dmol", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jaechang-hits/SciAgent-Skills molecular-visualization-3dmolInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jaechang-hits/SciAgent-Skills --skill molecular-visualization-3dmol -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/data-visualization/molecular-visualization-3dmol .github/skills/molecular-visualization-3dmol && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "molecular-visualization-3dmol" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/data-visualization/molecular-visualization-3dmol into .github/skills/molecular-visualization-3dmol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "molecular-visualization-3dmol", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jaechang-hits/SciAgent-Skills --skill molecular-visualization-3dmol -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jaechang-hits/SciAgent-Skills molecular-visualization-3dmol --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jaechang-hits/SciAgent-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/data-visualization/molecular-visualization-3dmol .opencode/skills/molecular-visualization-3dmol && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "molecular-visualization-3dmol" agent skill from https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/data-visualization/molecular-visualization-3dmol into .opencode/skills/molecular-visualization-3dmol/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "molecular-visualization-3dmol", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
molecular-visualization-3dmol3Dmol.js WebGL molecular visualization emitted as self-contained HTML.
Molecular Visualization 3dmol is an agent skill from jaechang-hits/SciAgent-Skills. 3Dmol.js WebGL molecular visualization emitted as self-contained HTML. Render structures (PDB/SDF/XYZ/MOL2/cube) with stick, sphere, cartoon, line, and surface styles; animate trajectories with a frame-delay (interval, ms) control; and animate vibrational normal modes via vibrate() from per-atom dx/dy/dz displacements or from precomputed frames. Output standalone HTML that loads 3Dmol from a CDN, with optional play/pause and speed controls. Use for transition-state imaginary-mode animations, MD or reaction-path…
Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/mol_viewer.py`).
It sits in Data & Analytics, covering Data visualization, Drug discovery and cheminformatics and 3D graphics and WebGL. It works with Matplotlib, Plotly, RDKit and Python. The repository describes itself as: 197 bioinformatics & life science skills for Claude Code and AI agents — BixBench 92.0% accuracy. RNA-seq, single-cell, drug discovery, proteomics, and more. Powers OmicsHorizon. The licence is BSD-3-Clause.
Read from SKILL.md and the folder at commit 82c862c. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3pipFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
3dmol.orgAlso links to:
pypi.orgFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Molecular Visualization 3dmol loads about 3.2k tokens when it runs. Until then it costs about 181 tokens; SKILL.md has 1,036 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from jaechang-hits/SciAgent-Skills at commit 82c862c, republished under its BSD-3-Clause licence (© jaechang-hits). 1,036 words, ~3,195 tokens.
.claude/skills/molecular-visualization-3dmol/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.3Dmol.js is a WebGL molecular viewer that runs entirely in the browser. This skill emits
self-contained HTML files that load 3Dmol from a CDN and render a structure, a trajectory,
or a vibrational mode — no server, no build step, no Python runtime to view. The bundled
scripts/mol_viewer.py generates that HTML from any .xyz/.trj/.pdb/.sdf/.mol2/.cube file;
the Core API below shows the underlying 3Dmol.js calls so you can hand-write or customize a
viewer.
.cube filescripts/mol_viewer.py — Python 3 standard library only, no installpip install py3Dmol for notebook use (wraps the same library)No package is needed to produce or open the HTML. The generator lives in this skill's scripts/
folder (next to this SKILL.md). It can't be run in place from the skill directory, so use your
file tools to read scripts/mol_viewer.py and save it into your working directory before running.
# animate a mode/trajectory file with play/pause + speed slider, in one call
python3 mol_viewer.py ts_imaginary_mode_000.trj --mode trajectory \
--title "TS mode" --subtitle "-621.8 cm-1" --out ts_mode.html
# static structure: python3 mol_viewer.py mol.xyz --out mol.htmlAll snippets assume <script src="https://3Dmol.org/build/3Dmol-min.js"></script> is loaded
and a <div id="v"></div> exists.
createViewer binds to a div; addModel(data, format) loads coordinates. Always zoomTo()
then render(). Supported format: xyz, pdb, sdf, mol2, cube, cif.
const viewer = $3Dmol.createViewer("v", {backgroundColor: "white"});
viewer.addModel(xyzString, "xyz"); // coordinates as a string, not a URL
viewer.setStyle({}, {stick: {radius: 0.15}, sphere: {scale: 0.28}});
viewer.zoomTo();
viewer.render();setStyle(selection, styleSpec) — empty selection {} targets all atoms. Styles: stick,
sphere, line, cross, cartoon. Color by element (default), a scheme, or a fixed color.
viewer.setStyle({}, {stick: {}, sphere: {scale: 0.25}}); // ball-and-stick
viewer.setStyle({elem: "C"}, {stick: {color: "gray"}}); // per-element override
viewer.setStyle({chain: "A"}, {cartoon: {color: "spectrum"}}); // protein ribbon
viewer.render();Load every frame with addModelsAsFrames, then animate. interval is the delay between
frames in milliseconds (larger = slower) — do not use step, which skips frames and looks
jumpy. loop: "backAndForth" makes a one-way path oscillate; reps: 0 loops forever.
viewer.addModelsAsFrames(trjString, "xyz"); // multi-frame .trj or multi-model .xyz/.pdb
viewer.setStyle({}, {stick: {radius: 0.14}, sphere: {scale: 0.28}});
viewer.zoomTo();
viewer.render();
viewer.animate({loop: "backAndForth", interval: 120, reps: 0});If a model's atoms carry displacement vectors (dx, dy, dz — extra columns on each XYZ line:
elem x y z dx dy dz), model.vibrate(numFrames, amplitude, bothWays, arrowSpec) builds the
oscillation frames. bothWays: true swings symmetrically about equilibrium; arrowSpec draws
motion arrows.
const m = viewer.addModel(modeXyz, "xyz"); // each atom line: elem x y z dx dy dz
m.vibrate(10, 1.0, true, {radius: 0.08, color: "black"}); // 10 frames, full amplitude, arrows
viewer.setStyle({}, {stick: {radius: 0.14}, sphere: {scale: 0.28}});
viewer.zoomTo();
viewer.render();
viewer.animate({loop: "backAndForth", interval: 120, reps: 0});If you only have a precomputed frame trajectory (e.g. pysisyphus ts_imaginary_mode_000.trj),
use the trajectory path above instead — no dx/dy/dz needed.
addSurface(type, style, atomsel) builds a molecular surface (VDW, SAS, SES, MS).
For an orbital/density isosurface, load the .cube and call addVolumetricData.
viewer.addSurface($3Dmol.SurfaceType.VDW, {opacity: 0.75, color: "lightblue"}, {chain: "A"});
// isosurface from a Gaussian cube (positive and negative lobes):
viewer.addVolumetricData(cubeString, "cube", {isoval: 0.02, color: "blue", opacity: 0.85});
viewer.addVolumetricData(cubeString, "cube", {isoval: -0.02, color: "red", opacity: 0.85});
viewer.render();addLabel(text, spec) annotates. For animations, a slider bound to interval (restarting via
stopAnimate() + animate()) lets the viewer set the speed — the fix for "sometimes too fast".
viewer.addLabel("TS", {position: {x: 0, y: 0, z: 0}, backgroundColor: "black", fontSize: 14});
let interval = 140;
const play = () => viewer.animate({loop: "backAndForth", interval});
document.getElementById("spd").oninput = e => { interval = +e.target.value; viewer.stopAnimate(); play(); };
play();interval vs step. interval (ms) sets playback speed; every frame is shown. step
plays every Nth frame — it skips motion and is the usual cause of a "too fast"/jumpy animation.
Control speed with interval, never step.
Coordinates are strings, not URLs. addModel/addModelsAsFrames take the file contents.
Embed them in the HTML as a JSON-encoded string so quotes and newlines survive
(scripts/mol_viewer.py uses json.dumps; a raw backtick template breaks on backticks in data).
CDN and CSP. The page fetches 3Dmol.js from a CDN, so it needs network access when opened, and a strict Content-Security-Policy (e.g. inside some artifact sandboxes) will blank it. Open it as a normal local/hosted file.
End-to-end HTML from a precomputed mode trajectory, with play/pause and a speed slider — the
deliverable the neb-irc-activation-energy skill hands off.
python3 mol_viewer.py ts_imaginary_mode_000.trj --mode trajectory \
--title "Transition-state mode" --subtitle "-621.8 cm-1" --out ts_mode.html
# open ts_mode.html; drag the slider if the oscillation is too fastpython3 mol_viewer.py trajectory.pdb --mode trajectory --style ballstick --out md.html
# any multi-model .xyz/.pdb works; backAndForth loop + interval control are built inconst viewer = $3Dmol.createViewer("v", {backgroundColor: "white"});
viewer.addModel(complexPdb, "pdb");
viewer.setStyle({}, {cartoon: {color: "spectrum"}}); // protein
viewer.setStyle({resn: "LIG"}, {stick: {radius: 0.2}}); // ligand
viewer.addSurface($3Dmol.SurfaceType.VDW, {opacity: 0.6}, {resn: "LIG", byres: true, expand: 5});
viewer.zoomTo({resn: "LIG"});
viewer.render();| Parameter | Method | Default | Range / Options | Effect |
|---|---|---|---|---|
interval | animate | 50 | 40–400 ms | Frame delay; larger = slower playback |
loop | animate | forward | forward/backward/backAndForth | backAndForth oscillates a one-way path |
reps | animate | 0 | 0=∞, n | Number of loops |
radius | stick | 0.3 | 0.1–0.3 | Bond cylinder thickness |
scale | sphere | 1.0 (vdW) | 0.2–0.4 for ball-and-stick | Atom sphere size |
amplitude | vibrate | 1.0 | 0.5–2.0 | Normal-mode distortion size |
numFrames | vibrate | 10 | 8–20 | Frames per half-cycle |
isoval | addVolumetricData | — | e.g. ±0.02 | Isosurface contour value (sign = lobe) |
opacity | addSurface | 1.0 | 0–1 | Surface transparency |
interval (ms), never step.json.dumps), not a raw backtick template.zoomTo() before render(), and again after adding a large model.<script> tag; only vendor the ~1 MB 3Dmol-min.js inline if offline use is required.python3 mol_viewer.py mode.xyz --mode vibrate --amplitude 1.2 --title "mode" --out mode.html
python3 mol_viewer.py mol.sdf --style stick --out mol.html # staticimport py3Dmol
view = py3Dmol.view(width=500, height=400)
view.addModel(open("mol.xyz").read(), "xyz")
view.setStyle({}, {"stick": {}, "sphere": {"scale": 0.25}})
view.zoomTo(); view.show()const viewer = $3Dmol.createViewerGrid("v", {rows: 1, cols: 2});
viewer[0][0].addModel(reactantXyz, "xyz"); viewer[0][0].setStyle({}, {stick: {}});
viewer[0][1].addModel(productXyz, "xyz"); viewer[0][1].setStyle({}, {stick: {}});
viewer[0][0].zoomTo(); viewer[0][1].zoomTo(); viewer[0][0].render(); viewer[0][1].render();| Problem | Cause | Solution |
|---|---|---|
| Blank white page | 3Dmol.js not loaded (offline / strict CSP) | Open with network access; check the CDN <script> resolves |
| Animation too fast / jumpy | Using step, or a tiny interval | Use interval (ms); raise it; never set step |
| Vibration shows no motion | Model lacks dx/dy/dz vectors | Add mode vectors as extra XYZ columns, or use a precomputed frame .trj |
| Nothing rendered | Wrong format string or bad data | Match format to the file; coordinates must be the file contents, not a path |
| JS syntax error in page | Backtick/quote in embedded data | Embed via json.dumps (the generator does this) |
| Structure loads but no bonds | XYZ without connectivity + line style | Use stick/sphere; 3Dmol infers bonds by distance |
| Surface slow or hangs | Large SES/MS on a big system | Use VDW, restrict the atomsel, or lower resolution |
scripts/mol_viewer.py — emit a standalone 3Dmol HTML (static / trajectory / vibrate) from a structure file, with built-in play/pause + speed slider for animationsinterval, loop, repsdx/dy/dz© jaechang-hits, BSD-3-Clause. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (scripts) in skills/data-visualization/molecular-visualization-3dmol of jaechang-hits/SciAgent-Skills.
Open the folder on GitHubat commit 82c862c
Molecular Visualization 3dmol next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Molecular Visualization 3dmol this skilljaechang-hits/SciAgent-Skills | 374 | — | ~3.2k | Automated safety check: Pass | BSD-3-Clause | |
| Python Executorcortega26/chile-hub | 113 | 2 repos | ~1.5k | Automated safety check: Pass | MIT | |
| CJK Font Setup for Plotsxjtulyc/MedgeClaw | 617 | 1 repos | ~1.3k | Automated safety check: Pass | None | |
| SeabornK-Dense-AI/scientific-agent-skills | 48k | 1 repos | ~3.4k | Automated safety check: Notes | BSD-3-Clause | |
| Data Visualizationw95/awesome-claude-corporate-skills | 244 | 2 repos | ~2.8k | Automated safety check: Pass | MIT | |
| Bio Data Visualization Network VisualizationGPTomics/bioSkills | 1.2k | 2 repos | ~3.7k | Automated safety check: Pass | MIT |
cortega26/chile-hub
Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh).
xjtulyc/MedgeClaw
Detects a usable Chinese, Japanese or Korean font and configures matplotlib so chart labels, titles and legends render instead of showing empty boxes.
K-Dense-AI/scientific-agent-skills
Creates Seaborn statistical visualizations with pandas integration for distributions, relationships, categorical comparisons, regression displays, pair plots, and heatmaps.
w95/awesome-claude-corporate-skills
Create effective data visualizations with Python (matplotlib, seaborn, plotly).
GPTomics/bioSkills
Visualize biological networks (PPI, gene-regulatory, co-expression, pathway) with layout algorithm choice (ForceAtlas2, Fruchterman-Reingold, Kamada-Kawai, hive plots), edge bundling…
wentorai/research-plugins
Publication-quality data visualization with matplotlib, seaborn, and plotly
jaechang-hits/SciAgent-Skills
NEB-IRC activation energy pipeline for reaction barriers using GFN2-xTB and pysisyphus.
jaechang-hits/SciAgent-Skills
Constraint-based (COBRA) analysis of genome-scale metabolic models: FBA, FVA, knockouts, flux sampling, production envelopes, gapfilling, media optimization.
jaechang-hits/SciAgent-Skills
Read, write, and edit ChemDraw CDX/CDXML files with RDKit's rdkit.Chem.rdChemDraw plus direct XML editing, always paired with a rendered PNG.
jaechang-hits/SciAgent-Skills
Programmatic PubMed access via NCBI E-utilities REST API. An agent skill from jaechang-hits/SciAgent-Skills.
jaechang-hits/SciAgent-Skills
Scaffold a new SciAgent-Skills entry. An agent skill from jaechang-hits/SciAgent-Skills.
jaechang-hits/SciAgent-Skills
Model interpretability via SHAP (Shapley values from game theory).
Works with
Categories
3Dmol.js WebGL molecular visualization emitted as self-contained HTML. Molecular Visualization 3dmol is an agent skill from jaechang-hits/SciAgent-Skills.js WebGL molecular visualization emitted as self-contained HTML.
Molecular Visualization 3dmol fits situations like: transition-state imaginary-mode animations; reaction-path playback; orbital/density isosurfaces.
Run `npx skills add jaechang-hits/SciAgent-Skills --skill molecular-visualization-3dmol -a claude-code`. Or copy the skill folder (skills/data-visualization/molecular-visualization-3dmol in jaechang-hits/SciAgent-Skills) into .claude/skills/molecular-visualization-3dmol in your project. Claude Code loads it when a task matches its description.
Run `npx skills add jaechang-hits/SciAgent-Skills --skill molecular-visualization-3dmol -a codex`. Or copy the skill folder (skills/data-visualization/molecular-visualization-3dmol in jaechang-hits/SciAgent-Skills) into .agents/skills/molecular-visualization-3dmol in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jaechang-hits/SciAgent-Skills --skill molecular-visualization-3dmol -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/molecular-visualization-3dmol, .gemini/skills/molecular-visualization-3dmol, .github/skills/molecular-visualization-3dmol and .opencode/skills/molecular-visualization-3dmol in your project.
Going by SKILL.md and its folder, Molecular Visualization 3dmol needs Python for the scripts in its folder and the command-line tools its instructions call (python3 and pip). Our summary lists: Python 3.
SKILL.md names 2 domains. In commands or code: 3dmol.org; the agent is likely to contact it when it follows the instructions. As links in the text: pypi.org. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Molecular Visualization 3dmol is published under the BSD-3-Clause licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Molecular Visualization 3dmol: Python Executor (cortega26/chile-hub, 113 stars), CJK Font Setup for Plots (xjtulyc/MedgeClaw, 617 stars), Seaborn (K-Dense-AI/scientific-agent-skills, 48k stars) and Data Visualization (w95/awesome-claude-corporate-skills, 244 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
jaechang-hits (a GitHub user) maintains it in jaechang-hits/SciAgent-Skills, which has 374 GitHub stars. The repository holds 169 skills in this directory. The repository was last updated on September 29, 2026.
Source: jaechang-hits/SciAgent-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.