Simulation Sandbox
Use this skill to turn a user-described rule system into runnable simulation artifacts. Favor small, inspectable research-toy models over opaque frameworks.
Workflow
Capture the model.
- If the user gives rules, preserve them.
- If the user gives only a domain idea, infer a minimal toy rule system and state assumptions.
- Ask only when the model's domain, outputs, or risk level is genuinely ambiguous.
Normalize rules to the JSON DSL.
- Read
references/dsl.md when designing, editing, or explaining the rule format.
- Keep units and probabilities explicit.
- Prefer deterministic seeds for reproducible runs.
Generate artifacts.
- Use the bundled generator for supported models:
- Run commands from the skill directory, or use the absolute path to
scripts/build_simulation.py.
python scripts/build_simulation.py --rules path/to/rules.json --out path/to/output
- For a quick demo, use a preset:
python scripts/build_simulation.py --preset virus --out path/to/output
- Use
--formats html,csv,notebook,json to choose outputs.
- Use
--steps and --seed for controlled experiments.
Extend when needed.
- For unsupported models, first map the idea to the closest DSL pattern.
- If the bundled script cannot represent the rules faithfully, create a scoped custom simulator using the same artifact pattern: self-contained HTML replay or canvas engine, CSV time series, notebook analysis, and rule JSON.
Validate before handoff.
- Run the generator and confirm it exits successfully.
- Inspect the CSV header and first rows.
- Open or screenshot the HTML when visual output matters.
- Check generated notebooks are valid JSON.
Output Standards
- Put final user-facing deliverables in the requested output folder.
- Return direct links to the HTML, notebook, CSV, and rule JSON when created.
- Describe assumptions and toy-model limitations plainly. Do not imply scientific validity unless the model has been validated.
- Make the first artifact runnable without external services.
- Prefer visible animation or replay over static charts when the user asks for a sandbox, simulator, or "research toy."
Resources
scripts/build_simulation.py: deterministic generator for HTML canvas replay, CSV, notebook, and JSON artifacts.assets/presets.json: starter rule systems for virus, evacuation, traffic, market, and ecosystem examples.references/dsl.md: compact DSL schema and modeling conventions.
1---2name: simulation-sandbox3description: Generate runnable simulation sandboxes from rule systems or simulation ideas. Use when Codex needs to turn agent-based or system-dynamics rules such as crowd evacuation, virus spread, city traffic, price competition, ecology, or other research-toy models into HTML canvas simulators, Python notebooks, CSV outputs, animations, or reproducible experiment artifacts.4---56# Simulation Sandbox78Use this skill to turn a user-described rule system into runnable simulation artifacts. Favor small, inspectable research-toy models over opaque frameworks.910## Workflow11121. Capture the model.13 - If the user gives rules, preserve them.14 - If the user gives only a domain idea, infer a minimal toy rule system and state assumptions.15 - Ask only when the model's domain, outputs, or risk level is genuinely ambiguous.16172. Normalize rules to the JSON DSL.18 - Read `references/dsl.md` when designing, editing, or explaining the rule format.19 - Keep units and probabilities explicit.20 - Prefer deterministic seeds for reproducible runs.21223. Generate artifacts.23 - Use the bundled generator for supported models:24 - Run commands from the skill directory, or use the absolute path to `scripts/build_simulation.py`.2526```bash27python scripts/build_simulation.py --rules path/to/rules.json --out path/to/output28```2930 - For a quick demo, use a preset:3132```bash33python scripts/build_simulation.py --preset virus --out path/to/output34```3536 - Use `--formats html,csv,notebook,json` to choose outputs.37 - Use `--steps` and `--seed` for controlled experiments.38394. Extend when needed.40 - For unsupported models, first map the idea to the closest DSL pattern.41 - If the bundled script cannot represent the rules faithfully, create a scoped custom simulator using the same artifact pattern: self-contained HTML replay or canvas engine, CSV time series, notebook analysis, and rule JSON.42435. Validate before handoff.44 - Run the generator and confirm it exits successfully.45 - Inspect the CSV header and first rows.46 - Open or screenshot the HTML when visual output matters.47 - Check generated notebooks are valid JSON.4849## Output Standards5051- Put final user-facing deliverables in the requested output folder.52- Return direct links to the HTML, notebook, CSV, and rule JSON when created.53- Describe assumptions and toy-model limitations plainly. Do not imply scientific validity unless the model has been validated.54- Make the first artifact runnable without external services.55- Prefer visible animation or replay over static charts when the user asks for a sandbox, simulator, or "research toy."5657## Resources5859- `scripts/build_simulation.py`: deterministic generator for HTML canvas replay, CSV, notebook, and JSON artifacts.60- `assets/presets.json`: starter rule systems for virus, evacuation, traffic, market, and ecosystem examples.61- `references/dsl.md`: compact DSL schema and modeling conventions.
kaiyihe699-max