data-science
Use when "statistical modeling", "A/B testing", "experiment design", "causal inference", "predictive modeling", or asking about "hypothesis testing", "feature engineering", "data analysis", "pandas", "scikit-learn"
What this skill does
<!-- Adapted from: claude-skills/engineering-team/senior-data-scientist -->
# Data Science Guide
Statistical modeling, experimentation, and advanced analytics.
## When to Use
- Designing A/B tests and experiments
- Building predictive models
- Performing causal analysis
- Feature engineering
- Statistical hypothesis testing
## Tech Stack
| Category | Tools |
|----------|-------|
| Languages | Python, SQL, R |
| Analysis | NumPy, Pandas, SciPy |
| ML | Scikit-learn, XGBoost, LightGBM |
| Visualization | Matplotlib, Seaborn, Plotly |
| Statistics | Statsmodels, PyMC |
| Notebooks | Jupyter, VS Code |
## Experiment Design
### A/B Test Framework
```python
import scipy.stats as stats
import numpy as np
def calculate_sample_size(baseline_rate, mde, alpha=0.05, power=0.8):
"""Calculate required sample size for A/B test."""
effect_size = mde / np.sqrt(baseline_rate * (1 - baseline_rate))
analysis = stats.TTestIndPower()
return int(analysis.solve_power(
effect_size=effect_size,
alpha=alpha,
power=power,
alternative='two-sided'
))
# Example: 5% baseline, 10% relative lift
n = calculate_sample_size(0.05, 0.005)
print(f"Required sample size per group: {n}")
```
### Statistical Significance
```python
def analyze_ab_test(control, treatment):
"""Analyze A/B test results."""
# Two-proportion z-test
n1, n2 = len(control), len(treatment)
p1, p2 = control.mean(), treatment.mean()
p_pool = (control.sum() + treatment.sum()) / (n1 + n2)
se = np.sqrt(p_pool * (1 - p_pool) * (1/n1 + 1/n2))
z = (p2 - p1) / se
p_value = 2 * (1 - stats.norm.cdf(abs(z)))
return {
'control_rate': p1,
'treatment_rate': p2,
'lift': (p2 - p1) / p1,
'p_value': p_value,
'significant': p_value < 0.05
}
```
## Feature Engineering
### Common Patterns
```python
import pandas as pd
from sklearn.preprocessing import StandardScaler
def engineer_features(df):
"""Feature engineering pipeline."""
# Temporal features
df['hour'] = df['timestamp'].dt.hour
df['day_of_week'] = df['timestamp'].dt.dayofweek
df['is_weekend'] = df['day_of_week'].isin([5, 6])
# Aggregations
df['user_avg_spend'] = df.groupby('user_id')['amount'].transform('mean')
df['user_transaction_count'] = df.groupby('user_id')['amount'].transform('count')
# Ratios
df['spend_vs_avg'] = df['amount'] / df['user_avg_spend']
return df
```
### Feature Selection
```python
from sklearn.feature_selection import mutual_info_classif
def select_features(X, y, k=10):
"""Select top k features by mutual information."""
mi_scores = mutual_info_classif(X, y)
top_k = np.argsort(mi_scores)[-k:]
return X.columns[top_k].tolist()
```
## Model Evaluation
### Cross-Validation
```python
from sklearn.model_selection import cross_val_score, StratifiedKFold
def evaluate_model(model, X, y):
"""Robust model evaluation."""
cv = StratifiedKFold(n_splits=5, shuffle=True, random_state=42)
scores = {
'accuracy': cross_val_score(model, X, y, cv=cv, scoring='accuracy'),
'precision': cross_val_score(model, X, y, cv=cv, scoring='precision'),
'recall': cross_val_score(model, X, y, cv=cv, scoring='recall'),
'auc': cross_val_score(model, X, y, cv=cv, scoring='roc_auc')
}
return {k: f"{v.mean():.3f} (+/- {v.std()*2:.3f})" for k, v in scores.items()}
```
## Causal Inference
### Propensity Score Matching
```python
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import NearestNeighbors
def propensity_matching(df, treatment_col, features):
"""Match treatment and control using propensity scores."""
# Estimate propensity scores
ps_model = LogisticRegression()
ps_model.fit(df[features], df[treatment_col])
df['propensity'] = ps_model.predict_proba(df[features])[:, 1]
# Match nearest neighbors
treated = df[df[treatment_col] == 1]
control = df[df[treatment_col] == 0]
nn = NearestNeighbors(n_neighbors=1)
nn.fit(control[['propensity']])
distances, indices = nn.kneighbors(treated[['propensity']])
return treated, control.iloc[indices.flatten()]
```
## Best Practices
### Analysis Workflow
1. Define hypothesis clearly
2. Calculate required sample size
3. Design experiment (randomization)
4. Collect data with quality checks
5. Analyze with appropriate tests
6. Report with confidence intervals
### Common Pitfalls
- Multiple comparisons without correction
- Peeking at results before sample size reached
- Simpson's paradox in aggregations
- Survivorship bias in cohort analysis
- Correlation vs causation confusion
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.