Browse Skills

Mermaid Visualizer transforms text content into professional Mermaid diagrams for presentations and documentation. Use it when you need to visualize concepts, create flowcharts, or make diagrams from text.

Obsidian Bases creates and edits Obsidian .base files with views, filters, formulas, and summaries to turn notes into database-like tables, cards, and lists. Use it when working with .base files, creating database-like views of notes, or setting up filters, formulas, or summaries in Obsidian.

Braintrust Analysis inspects Claude Code session tracing data in Braintrust to surface tool usage, agent and skill activity, token trends, and repeated loops. Use it for post-task retrospectives, debugging stuck sessions, and weekly productivity reviews.

Shader Data Inspector retrieves detailed information from a Unity shader asset, including properties, subshaders, passes, and compilation messages. Use it after locating shaders with assets-find or assets-shader-list-all to inspect shader internals or debug compilation errors.

Graph provides interactive knowledge graph analysis, routing natural language questions to graph scripts, interpreting results in domain vocabulary, and suggesting concrete actions. Use it to check graph health, find orphans, dangling links, and synthesis opportunities.

Vault Stats shows vault statistics and knowledge graph metrics, including note counts, link density, orphans, schema compliance, and weekly growth. Use it to get a shareable snapshot of vault health, growth, and progress.

Personal CRM structures people, companies, and meetings as typed dossiers with compiled truth and append-only timelines. Use it when capturing notes about a person or company, logging meetings, prepping for meetings, or answering who someone is and what was last said.

Causal Inference Mixtape provides code templates for 10 causal inference identification strategies in Python, R, and Stata. Use it to implement DiD, event studies, IV, RDD, synthetic control, matching, and robustness checks.

Full Empirical Analysis provides a complete end-to-end workflow for applied empirical research in Python, covering data cleaning, variable construction, descriptive statistics, econometric modeling, robustness checks, and publication-ready tables and figures. It also includes specialized modes for target-trial emulation and ML causal inference, with explicit library choices and diagnostic steps.

Full Empirical Analysis R runs a complete 8-step empirical research pipeline in R using tidyverse and econometrics packages, generating publication-ready regression tables, descriptive statistics, robustness checks, and figures for applied economics, epidemiology, and ML causal inference.

Marginaleffects helps users interpret statistical models in R and Python via predictions, comparisons, slopes, and hypothesis tests, following the book Model to Meaning. Use it for marginal effects, treatment effects, causal inference, or function syntax.

PyFixest Reference provides a machine-readable API reference for the PyFixest Python package, covering feols, fepois, feglm, quantreg, clustered/robust standard errors, R-style formulas, and post-estimation. Use when writing or debugging fixed-effects regressions in Python.