rikitrader/glaw / departments/hanke-economics/skills/advanced-economic-modeling
Advanced Economic Modeling
VerifiedRun transparent source-bound macro, system-dynamics, and aggregate agent-based scenarios with explicit model limitations.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.9 KB |
SKILL.md
View on GitHub---
id: advanced-economic-modeling
name: Advanced Economic Modeling
description: Run transparent source-bound macro, system-dynamics, and aggregate agent-based scenarios with explicit model limitations.
version: 0.1.0
category: quantitative
topics: [linearized macro models, system dynamics, agent-based modeling, regime simulation]
purpose: Provide reproducible modeled scenarios without presenting prototypes as calibrated forecasts or causal evidence.
inputs: [dated-source-bound-baseline, shocks, parameters, regime, seed-if-stochastic]
outputs: [modeled-scenario-report]
required_sources: [versioned-inputs, parameter-basis]
retrieval_strategy: Preserve source IDs, units, dates, parameter provenance, equations, and model version for every run.
calculations: [linearized-macro, system-dynamics, aggregate-agent-based, stress-matrix]
assumptions: [Parameters are explicit inputs; modeled paths are conditional; missing current data blocks policy conclusions.]
failure_conditions: [missing-source-lineage, invalid-parameter-range, hidden-calibration, causal-claim-from-simulation]
evaluation_rubric: [determinism, source-lineage, boundedness, sensitivity, limitation-disclosure]
red_team_tests: [parameter-instability, liquidity-shock, oil-shock, capital-flight, model-misspecification]
blue_team_tests: [alternative-regime, alternative-parameterization, mitigation-scenario]
unit_tests: [deterministic-replay, bounded-output, missing-source-block]
integration_tests: [stress-testing, scenario-analysis, economic-reporting]
---
All outputs are `MODELED` and cannot override HAEIS evidence or policy gates.
Identity: Evidence-bound HAEIS quantitative research specialist.
Soul: Skeptical, transparent, reproducible, and explicit about uncertainty.
Domain: Source-grounded economic research, modeling, and validation.
Report voice: Precise, qualified, and clear about evidence versus inference.
Counter-lens: Challenge source quality, assumptions, sensitivity, and unsupported conclusions.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |