Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add garroshub/ai-economist-skill --skill economics-mlgit clone --depth 1 https://github.com/garroshub/ai-economist-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/garroshub/ai-economist-skill/economics-ml)<a href="https://agentmods.dev/skills/garroshub/ai-economist-skill/economics-ml"><img src="https://agentmods.dev/badge/skills/garroshub/ai-economist-skill/economics-ml/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/garroshub/ai-economist-skill/economics-ml"><img src="https://agentmods.dev/badge/skills/garroshub/ai-economist-skill/economics-ml.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01263 |
| Opus 5.5 | $0.00000 | $0.00505 |
| Sonnet 5.5 | $0.00000 | $0.00253 |
| Haiku 4.5 | $0.00000 | $0.00126 |
Grade A, and why
economics-ml scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Economics ML Skill
Use this skill for macroeconomic nowcasting, central-bank policy diagnostics, economics-oriented ML calibration, and validation reports.
Interface
Treat this as an agent skill first. A runtime installation should include this
file, requirements.txt, main.py, backtest_engine.py, and src/. Use the
bundled Python scripts when the user asks for a live run, fresh backtest,
regenerated dashboard snapshot, or reproducible artifact. For interpretive
questions, answer from the latest available report, snapshot, user-supplied
numbers, or cited public data.
Operating Principles
- Do not expose private keys, local machine identifiers, personal names, or unpublished private data in generated reports or dashboard text.
- Keep the structural economics model as the primary estimate.
- Use ML as an auxiliary calibration, measurement, nuisance-estimation, heterogeneity, or validation layer.
- Do not describe ML calibration as the main forecast.
- Keep causal language conservative. Separate measurement, prediction, association, identification, and policy evaluation.
- Treat boundary and discontinuity designs as nonparametric econometrics unless a specific ML method is actually used.
Default Agent Behavior
When answering a user request, produce an economist-style readout rather than a raw script result. Include:
- Forecast or policy target period.
- Data-through date and release-lag assumptions.
- Sources used and sources missing.
- Structural baseline result.
- Data-enhanced result when available, shown separately.
- Driven-factor decomposition.
- Directional interpretation of the largest positive and negative factors.
- Backtest window, observations, R2/RMSE where available.
- Leakage and overfit checks.
- Limitation note for revised-data, pseudo-real-time, or non-causal results.
Non-Script Analysis Mode
Use this mode when the user asks what the results mean, why a country changed, whether an enhancement is credible, or which factors are driving a forecast. Do not simply tell the user to run a command.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- backtest_engine.py 22 KB runs code
- main.py 1.2 KB runs code
- requirements.txt 65 B
- src/__init__.py 0 B runs code
- src/core/__init__.py 0 B runs code
- src/core/modeling_core.py 2.6 KB runs code
- src/core/visual_oracle.py 2.4 KB runs code
- src/data_utils/__init__.py 0 B runs code
- src/data_utils/macro_data_fetcher.py 5.3 KB runs code
- src/data_utils/statcan_fetcher.py 1.2 KB runs code
- src/engine/__init__.py 0 B runs code
- src/engine/gdp_nowcast_engine.py 13 KB runs code
- src/engine/policy_rate_engine.py 22 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 210 lines · 0 tokens per session scan A 38b2c1f6a9f9
economics-ml is a skill published in the GitHub repository garroshub/ai-economist-skill (35 stars, last pushed 20d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,263 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
bio-applied-cancer-transcriptomics
Classify tumor RNA-seq into subtypes (melanoma Tirosh/Harbst on TCGA-SKCM): log1p/z-score, PCA/t-SNE, hierarchical clustering, random forest, Kaplan-Meier survival. Use when subtyping cBioPortal expression data.
bio-applied-data-harmonization
Harmonize multi-omics data (RNA-seq, proteomics, methylation, metabolomics) before integration — per-layer normalization, KNN/half-minimum missing-value imputation, PCA/PVCA batch-effect detection, and ComBat correction with pandas/scikit-learn. Use when prepping matrices for MOFA2/DIABLO/mixOmics, fixing missing…
bio-applied-deep-learning-for-biology
Train PyTorch CNN/LSTM/Transformer/VAE on DNA/protein sequences: one-hot encoding, motif filters, saliency. Use when classifying sequences, predicting TF binding sites, denoising scRNA-seq, or choosing DL vs ML.
bio-applied-gene-regulatory-networks
Infer TF-target regulatory networks via correlation, ARACNE mutual information, and GENIE3 random-forest importance; find feed-forward loops; validate against TRRUST. Use when building a GRN or asked about GENIE3, ARACNE, or regulons.
bio-applied-machine-learning-for-biology
Engineer k-mer/GC/CpG DNA features, train scikit-learn classifiers (LogisticRegression, RandomForest, SVC), evaluate with CV/ROC-AUC. Use for promoter/variant classifiers or model comparison on omics features.
bio-applied-molecular-gnn
Train PyTorch Geometric GCN/MPNN on SMILES-derived molecular graphs to predict properties (BBBP, solubility, toxicity); compare vs Morgan-fingerprint RF. Use for GNN property prediction or SMILES-to-graph pipelines.