agentleFS
Starlight-IntelligenceStarlight-Intelligence/starlight-agent-skills/skills/education/simulation-lab-builder/SKILL.md

simulation-lab-builder

Skill1 starsChanged 4 months agoMITView on GitHub

Design an interactive simulation lab — a self-contained HTML/JS (or p5.js) sim with tunable parameters, a learning goal, and guided experiments. Use when building an interactive demo, a physics/astronomy sandbox, or a 'simulation' / 'interactive lab' for teaching.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Simulation Lab Builder

A learning goal → a runnable interactive simulation with guided experiments.

Purpose

Some concepts only click when you can play with them (orbits, gravity, wave interference, scale). This skill produces a self-contained interactive simulation — parameters the learner can tune, plus a short set of guided experiments that lead to the intended insight — runnable from a single HTML file.

When it fires

  • Keyword triggers: simulation, interactive lab, sandbox, interactive demo, visualize this
  • File triggers: sims/**, *.sim.html
  • Command triggers: /simulation-lab-builder

Inputs

InputRequiredNotes
goalyesThe insight the sim should produce.
paramsnoVariables to expose as sliders/inputs.
stacknop5js (default) or vanilla HTML/Canvas.

Workflow

  1. State the insight — the one thing a learner should walk away understanding. ✅ Check: the sim can actually demonstrate it.
  2. Model — the minimal correct model (equations/rules) that produces the behavior. Keep physics honest within stated simplifications.
  3. Build the sim — single-file HTML/JS (or p5.js sketch) with tunable controls and clear rendering.
  4. Guided experiments — 2–4 prompts ("set gravity to 0 — what happens?") that surface the insight.
  5. Self-check — the sim runs without errors; controls visibly affect behavior.

Output contract

{
  "goal": "string",
  "model_notes": "string — equations/rules + simplifications",
  "code": "string — single-file HTML/JS or p5.js sketch",
  "experiments": ["string — guided prompts"],
  "stack": "p5js | vanilla"
}

Tools & MCP

  • Tools: Write, Bash/browser to smoke-test. MCP: none required.

Quality bar

  • Runs from a single file without external build steps.
  • Model is physically honest within its stated simplifications.
  • Controls measurably change the simulation.
  • Experiments lead to the stated insight.

Example

Input: goal "show how orbital speed changes with distance" → a p5.js two-body sim with a distance slider and three guided experiments.


Built on SIP — Starlight Intelligence Protocol Substrate: starlightintelligence.org/protocol v1.1.0 Layers used: [file-contract, attestation, sovereignty] Vertical: starlight-agent-skills · portable capability layer

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.