skills/lsystem-executor/SKILL.md
Execute L-system and shape grammars to produce visual derivations, SVG/PNG renders, and optional STL meshes
npx skillsauth add lamm-mit/scienceclaw lsystem-executorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Execute parametric L-system grammars and render the results as images or meshes.
Takes a grammar definition (axiom + rewrite rules) and produces:
--stl flag is passed)Useful for investigations that produce symbolic growth grammars (urban evolution, microstructure growth, biological branching) and need a concrete visual artifact.
python3 {baseDir}/scripts/lsystem_render.py --grammar grammar.json --steps 4 --output output_dir/
python3 {baseDir}/scripts/lsystem_render.py \
--axiom "A" \
--rules '{"A": "A[+B]A[-B]A", "B": "BB"}' \
--angle 25 \
--steps 4 \
--output output_dir/
python3 {baseDir}/scripts/lsystem_render.py \
--grammar grammar.json \
--steps 3 \
--stl \
--output output_dir/
{
"axiom": "A",
"rules": {
"A": "A[+B]A[-B]A",
"B": "BB"
},
"angle": 25.0,
"step_length": 10.0,
"length_scale": 1.0,
"title": "Urban-Material Growth Grammar"
}
| Symbol | Meaning |
|--------|---------|
| F | Move forward, drawing a line |
| A-Z (uppercase) | Move forward, drawing a line (also rewritable) |
| f | Move forward without drawing |
| + | Turn left by angle |
| - | Turn right by angle |
| [ | Push position and heading onto stack |
| ] | Pop position and heading from stack |
| ! | Decrease line width |
| > | Multiply step length by length_scale |
The script produces in the output directory:
derivation.txt — string at each steprender.svg — vector graphics of the final structurerender.png — rasterized version (300 DPI)render_steps.png — grid showing each derivation step side by sidegrammar.json — the grammar used (for reproducibility)render.stl — 3D mesh (only if --stl flag is used)tools
Onboard and manage Paperclip AI for research-paper knowledge and agent orchestration
development
Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.
testing
Generate a structured scientific PDF report from a JSON description. Accepts a JSON file specifying title, authors, abstract, sections (headings, text, tables, figures), and inline data panels (heatmap, bar, scatter, line). Produces a publication-style A4 PDF using reportlab with no LaTeX dependency. All figures are either loaded from PNG paths or generated on-the-fly from inline data.
development
Execute arbitrary Python code and return stdout. NumPy, pandas, scipy, matplotlib, and other scientific libraries are available.