{"id":"52c996b7-3830-4e8c-8b30-f9c23aaa6745","slug":"ai-economist-skill","kind":"skill","name":"ai-economist-skill","summary":"An installable agent skill for macroeconomic nowcasting and monetary-policy analysis. Structural statistical baselines with ML calibration for GDP forecasts and policy-rate signals (US and Canada), wi","owner":"garroshub","repoUrl":"https://github.com/garroshub/ai-economist-skill","license":"MIT","licenseTier":"permissive","trust":"community","stars":35,"match":null,"fewStars":false,"format":"skill","createdAt":"2026-02-02T17:59:30.000Z","addedAt":"2026-10-14T06:06:20.070Z","logoUrl":"https://avatars.githubusercontent.com/u/66699813?u=6eb4143513ceea20b1b2a82fd1c3010c5a1cc7b0&v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["developer-tools","data-analytics"],"tags":["macroeconomics","ai-economist","interpretable-ml","macroeconomic-forecasting","monetary-policy","nowcasting","ai-agents","economics"],"runtime":"binary","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-17T06:43:33.681Z","sample":false,"url":"https://conduits.dev/tools/ai-economist-skill","language":"Python","transports":["stdio"],"install":{},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"

\n \"Economics\n

\n\n

\nAn installable agent skill for macroeconomic nowcasting, central-bank policy
\ndiagnostics, and economist-style interpretation. The installable skill lives in\neconomics-ml/; the dashboard and tests are project-side
\nsupporting files.\n

\n\n
\n \"Economics\n
\n\n
\n\n[![Live Dashboard](https://img.shields.io/badge/View-Live_Dashboard-emerald?style=for-the-badge)](https://garroshub.github.io/ai-economist-skill/)\n[![Discussions](https://img.shields.io/badge/Join-Discussions-0b5fff?style=for-the-badge)](https://github.com/garroshub/ai-economist-skill/discussions)\n[![License: MIT](https://img.shields.io/badge/License-MIT-white?style=for-the-badge)](LICENSE)\n\n
\n\n

\n \"Live\n

\n\n---\n\n## What It Does\n\n| Layer | Main Output | Role of ML |\n| --- | --- | --- |\n| GDP nowcast | Bridge-equation baseline by country and quarter | Bounded residual calibration, reported separately |\n| Policy diagnostics | Base Taylor and Data-Enhanced Taylor readouts | Historical residual calibration against observable macro factors |\n| Backtesting | Baseline vs calibrated OOS comparison | Prior-window calibration only, release-lag filtered |\n| Agent report | Driven factors, data-through dates, validation notes | Structured interpretation, not a hidden predictor |\n\nML is not the primary forecaster. It is an auxiliary calibration and measurement\nlayer used to explain where the structural model may be missing information.\n\n## Install As An Agent Skill\n\nInstall the `economics-ml/` folder for normal use. It contains `SKILL.md`, the\nPython runtime, and requirements. The repository-level `dashboard/`, `tests/`,\nand `assets/` folders are not part of the installed skill.\n\nmacOS/Linux:\n\n```bash\ntmpdir=\"$(mktemp -d)\"\ngit clone --depth 1 https://github.com/garroshub/ai-economist-skill.git \"$tmpdir/ai-economist-skill\"\nrm -rf ~/.codex/skills/economics-ml\ncp -R \"$tmpdir/ai-economist-skill/economics-ml\" ~/.codex/skills/economics-ml\nrm -rf \"$tmpdir\"\ncd ~/.codex/skills/economics-ml\npip install -r requirements.txt\n```\n\nWindows PowerShell:\n\n```powershell\n$skillDir = \"$env:USERPROFILE\\.codex\\skills\\economics-ml\"\n$tmpDir = Join-Path $env:TEMP \"ai-economist-skill\"\nRemove-Item -LiteralPath $tmpDir -Recurse -Force -ErrorAction SilentlyContinue\ngit clone --depth 1 https://github.com/garroshub/ai-economist-skill.git $tmpDir\nRemove-Item -LiteralPath $skillDir -Recurse -Force -ErrorAction SilentlyContinue\nCopy-Item -Recurse -LiteralPath \"$tmpDir\\economics-ml\" -Destination $skillDir\nSet-Location $skillDir\npip install -r requirements.txt\n```\n\nAfter installation, ask the agent for tasks such as:\n\n```text\nUse the Economics ML skill to explain the latest US and Canada GDP nowcast drivers.\nUse the Economics ML skill to compare Base Taylor and Data-Enhanced Taylor signals.\nUse the Economics ML skill to audit whether the backtest has forward-information leakage.\n```\n\nThe skill should answer with target period, data-through date, baseline estimate,\ndata-enhanced estimate, driven factors, validation checks, and limitations. It\nshould not merely point the user to a Python command.\n\n### Analysis-Only Install\n\nIf you only want the agent to produce structured interpretation from\nuser-provided values or existing reports, `SKILL.md` alone is enough. Live data\npulls and backtests require the runtime bundle above.\n\n### Full Repository Clone\n\nClone the full repository only for development, dashboard work, or tests:\n\n```bash\ngit clone https://github.com/garroshub/ai-economist-skill.git\n```\n\nIn a full clone, `dashboard/`, `tests/`, `src/`, and the Python entrypoints are\nproject files. Only `economics-ml/` is required for installing the agent skill.\n\n## Current Modules\n\n### GDP Nowcasting\n\n- Structural bridge model with SVD factor extraction.\n- Ragged-edge filling for missing recent monthly observations.\n- US high-frequency auxiliary variables: initial claims, housing, durable goods,\n real disposable income, financial conditions, and yield curve.\n- Canada auxiliary variables: StatCan retail sales, CPI, CAD/USD, WTI oil, and\n US demand spillover measures.\n- Baseline and ML-calibrated nowcasts shown side by side.\n\n### Policy Rate Diagnostics\n\n- Taylor 1993, Taylor 1999, and nonlinear inflation-response variants.\n- Output-gap proxies from labor slack, HP-filtered GDP, and capacity utilization.\n- Base Taylor result remains the main structural signal.\n- Data-Enhanced Taylor result learns historical residual adjustments from\n activity, inflation pressure, financial conditions, external pressure, and\n labor cooling.\n- Enhancement decomposition is reported in percentage-point contributions.\n\n### Validation\n\n- Expanding-window backtest for GDP nowcasts.\n- Release-lag-aware pseudo-real-time feature filtering.\n- Baseline R2/RMSE and ML-calibrated R2/RMSE shown on the same validation window.\n- Revised-data limitation is disclosed rather than treated as a vintage-data test.\n\n## Optional Runtime Tools\n\nThe skill can be used for analysis without running local scripts. Install the\nruntime dependencies only when you want live data pulls, regenerated reports,\nbacktests, or local dashboard builds.\n\n```bash\ncd economics-ml\npip install -r requirements.txt\nset FRED_API_KEY=your_key_here\n```\n\nRun GDP nowcasts:\n\n```bash\npython main.py gdp --country US\npython main.py gdp --country Canada\n```\n\nRun policy diagnostics:\n\n```bash\npython main.py policy --country US\npython main.py policy --country Canada\n```\n\nRun backtests:\n\n```bash\npython backtest_engine.py\n```\n\nBuild the dashboard:\n\n```bash\ncd dashboard\nnpm ci\nnpm run build\n```\n\n## Data Sources\n\n- FRED API for macro indicators.\n- BLS and Bank of Canada public data where available.\n- Statistics Canada public CSV tables for retail-sales auxiliary features.\n- Public news and outlook pages only when converted into structured measurement\n variables.\n\nNo private API key is stored in the repository. Set `FRED_API_KEY` locally before\nrunning live workflows.\n\n## Agent Output Contract\n\nReports should include the forecast target period, data-through date, source\ncoverage, structural baseline, calibrated result, driven-factor decomposition,\nbacktest window, leakage controls, and limitations. Causal claims require a\nseparate identification design.\n\n## Repository Structure\n\n```text\nai-economist-skill/\n|-- README.md\n|-- economics-ml/\n| |-- SKILL.md\n| |-- main.py\n| |-- backtest_engine.py\n| |-- requirements.txt\n| `-- src/\n|-- dashboard/\n|-- assets/\n`-- tests/\n```\n\nFor skill installation, use only `economics-ml/`. The dashboard, tests, and\nassets support the public project page and validation workflow.\n\n## Star History\n\n
\n\n[![Star History Chart](https://api.star-history.com/svg?repos=garroshub/ai-economist-skill&type=Date)](https://www.star-history.com/#garroshub/ai-economist-skill&Date)\n\n
\n"}