Claude skills and agent skills

sshtomarSkill

core-methodology

sshtomar/claude-code-skills-social-science/skills/core-methodology/SKILL.md

Core statistical methodology and pedagogical approach for all Inquiro analyses. Always loaded to maintain teaching quality and reproducibility standards.

sshtomarSkill

descriptive-statistics

sshtomar/claude-code-skills-social-science/skills/descriptive-statistics/SKILL.md

Summary statistics, data exploration, and descriptive analysis. Use for: summary stats, describe data, data exploration, distributions, means, medians, correlations, cross-tabs.

sshtomarSkill

difference-in-differences

sshtomar/claude-code-skills-social-science/skills/difference-in-differences/SKILL.md

Causal inference with treatment/control groups over time. Use when user mentions: treatment effects, policy evaluation, pre/post comparison, parallel trends, DID, DiD, difference in differences, natural experiment, quasi-experimental.

sshtomarSkill

lit-review

sshtomar/claude-code-skills-social-science/skills/literature-review/SKILL.md

Systematic literature review methodology for social science research. Use when conducting systematic reviews, research synthesis, meta-analyses, scoping reviews, or comprehensive literature searches across economics, political science, sociology, education, public health, and development. Produces structured notebook cells with search strategy, evidence table, thematic synthesis, and gap analysis.

sshtomarSkill

rct-core-design

sshtomar/claude-code-skills-social-science/skills/rct-core-design/SKILL.md

Design randomized controlled trials for causal inference. Use when user mentions: randomized evaluation, RCT, field experiment, randomized experiment, treatment assignment, causal impact, experimental design, control group, intervention evaluation.

sshtomarSkill

rct-data-analysis

sshtomar/claude-code-skills-social-science/skills/rct-data-analysis/SKILL.md

Analyze data from randomized controlled trials. Use when user mentions: treatment effects, ITT analysis, LATE, TOT, compliance analysis, attrition, balance checks, heterogeneous effects, RCT results, experimental analysis.

sshtomarSkill

rct-ethics-registration

sshtomar/claude-code-skills-social-science/skills/rct-ethics-registration/SKILL.md

Handle ethical requirements, IRB approval, trial registration, and pre-analysis plans for RCTs. Use when user mentions: research ethics, IRB, informed consent, trial registration, pre-analysis plan, PAP, data security, vulnerable populations, research transparency.

sshtomarSkill

rct-power-calculations

sshtomar/claude-code-skills-social-science/skills/rct-power-calculations/SKILL.md

Calculate statistical power and sample sizes for RCTs. Use when user mentions: power analysis, sample size calculation, minimum detectable effect, MDE, statistical power, effect size, clustering effects, design effect, ICC, intra-cluster correlation.

sshtomarSkill

rct-randomization

sshtomar/claude-code-skills-social-science/skills/rct-randomization/SKILL.md

Implement randomization methods for RCTs. Use when user mentions: random assignment, treatment allocation, stratification, blocking, permutation randomization, cluster randomization, randomization balance, misfit handling, re-randomization.

sshtomarSkill

regression-diagnostics

sshtomar/claude-code-skills-social-science/skills/regression-diagnostics/SKILL.md

Comprehensive regression model diagnostics and assumption checking. Use when validating regression models, checking assumptions (linearity, homoskedasticity, normality, independence), detecting outliers/influence, testing multicollinearity, or when user mentions residuals, heteroskedasticity, VIF, Cook's distance, or diagnostic plots.

sshtomarSkill

visualization

sshtomar/claude-code-skills-social-science/skills/visualization/SKILL.md

Publication-quality statistical visualization with mandatory best practices. Use when creating plots, charts, figures, or any data visualization. Enforces accessibility, uncertainty display, proper labeling, and statistical accuracy.

sshtomarSkill

agent-bricks

sshtomar/claude-skills/agent-bricks/SKILL.md

Create and manage Databricks Agent Bricks: Knowledge Assistants (KA) for document Q&A, Genie Spaces for SQL exploration, and Multi-Agent Supervisors (MAS) for multi-agent orchestration. Use when building conversational AI applications on Databricks.

sshtomarSkill

agent-evaluation

sshtomar/claude-skills/agent-evaluation/SKILL.md

Use this when you need to EVALUATE OR IMPROVE or OPTIMIZE an existing LLM agent's output quality - including improving tool selection accuracy, answer quality, reducing costs, or fixing issues where the agent gives wrong/incomplete responses. Evaluates agents systematically using MLflow evaluation with datasets, scorers, and tracing. Covers end-to-end evaluation workflow or individual components (tracing setup, dataset creation, scorer definition, evaluation execution).

sshtomarSkill

aibi-dashboards

sshtomar/claude-skills/aibi-dashboards/SKILL.md

Create AI/BI dashboards. CRITICAL: You MUST test ALL SQL queries via execute_sql BEFORE deploying. Follow guidelines strictly.

sshtomarSkill

analyze-langfuse-trace

sshtomar/claude-skills/analyze-langfuse-trace/SKILL.md

Analyzes a single Langfuse trace to answer a user query about it. Use when the user provides a trace ID and asks to debug, investigate, find issues, root-cause errors, understand behavior, or analyze quality. Triggers on "analyze this trace", "what went wrong with this trace", "debug trace", "investigate trace", "why did this trace fail", "root cause this trace", "explain this langfuse trace".

sshtomarSkill

analyzing-mlflow-session

sshtomar/claude-skills/analyze-mlflow-chat-session/SKILL.md

Analyzes an MLflow session — a sequence of traces from a multi-turn chat conversation or interaction. Use when the user asks to debug a chat conversation, review session or chat history, find where a multi-turn chat went wrong, or analyze patterns across turns. Triggers on "analyze this session", "what happened in this conversation", "debug session", "review chat history", "where did this chat go wrong", "session traces", "analyze chat", "debug this chat".

sshtomarSkill

analyzing-mlflow-trace

sshtomar/claude-skills/analyze-mlflow-trace/SKILL.md

Analyzes a single MLflow trace to answer a user query about it. Use when the user provides a trace ID and asks to debug, investigate, find issues, root-cause errors, understand behavior, or analyze quality. Triggers on "analyze this trace", "what went wrong with this trace", "debug trace", "investigate trace", "why did this trace fail", "root cause this trace".

sshtomarSkill

architecture-diagram

sshtomar/claude-skills/architecture-diagram/SKILL.md

Create and modify cloud architecture diagrams using GraphPatch operations. Use when user asks to add services, create connections, improve architecture, or modify diagrams for AWS, Azure, GCP, and Databricks.

Often used withcompetitor-news-monitor·teams-meeting-pipeline·popular-web-designs

sshtomarSkill

arxiv-digest

sshtomar/claude-skills/arxiv-digest/SKILL.md

Autonomous daily digest of relevant arxiv papers in physics and ML based on your interests

sshtomarSkill

asset-bundles

sshtomar/claude-skills/asset-bundles/SKILL.md

Create and configure Databricks Asset Bundles (DABs) with best practices for multi-environment deployments. Use when working with: (1) Creating new DAB projects, (2) Adding resources (dashboards, pipelines, jobs, alerts), (3) Configuring multi-environment deployments, (4) Setting up permissions, (5) Deploying or running bundle resources