Data Scientist — expert analytics, ML and statistics copilot
A senior-level data scientist persona for agents: statistics and experimental design, ML pipelines, Python/R/SQL tooling, visualization, and business analytics across marketing, finance and operations
- What
- A senior-level data scientist persona for agents: statistics and experimental design, ML pipelines, Python/R/SQL tooling, visualization, and business analytics across marketing, finance and operations
- Cost
- Free
- Needs
- Python data stack (pandas, NumPy, scikit-learn, matplotlib/plotly) and your own datasets; a Jupyter-capable environment helps
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @rmyndharis's data-scientist skill, listed here with credit to its creator: a senior-level data scientist persona that equips an agent with the full analytics playbook — statistical analysis and methodology (hypothesis testing, A/B testing and experimental design, causal inference, ARIMA/Prophet time series, survival analysis, Bayesian stats), machine learning (supervised/unsupervised models, deep learning with PyTorch/TensorFlow, ensembles, hyperparameter tuning with Optuna, feature engineering, SHAP/LIME interpretability), data manipulation (pandas, NumPy, scikit-learn, R/tidyverse, SQL window functions and CTEs, PySpark/Dask), visualization (matplotlib, seaborn, plotly, Streamlit/Dash dashboards), and applied business analytics for marketing (CLV, attribution, MMM, churn), finance (credit risk, fraud detection, portfolio optimization) and operations (demand planning, predictive maintenance). Honest caveats: it's a persona and knowledge pack, not executable code — the agent still needs the actual data, compute and libraries on your side; it invokes the skill "proactively" by default, which you may want to narrow; fraud-detection and risk-modeling capabilities assume authorized, lawful use on data you're entitled to analyze. MIT licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: Python data stack (pandas, NumPy, scikit-learn, matplotlib/plotly) and your own datasets; a Jupyter-capable environment helps Install "Data Scientist — expert analytics, ML and statistics copilot" for me. It gives my agent @rmyndharis's senior data-scientist persona: the full analytics playbook — statistics and experimental design (A/B testing, causal inference, time series, Bayesian), ML (classical and deep learning, Optuna tuning, SHAP/LIME), data manipulation (Python/R/SQL, PySpark/Dask), visualization and dashboards, plus applied playbooks for marketing, finance and operations analytics. MIT licensed. Repository: https://github.com/rmyndharis/antigravity-skills/blob/main/skills/data-scientist/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This is a persona/knowledge skill — any executable side beyond normal examples is a red flag. This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "data-scientist". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. install the Python data stack, point the agent at my datasets, decide whether to keep the "proactive" invocation behavior, and confirm any analysis stays within authorized, lawful use of my data). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.