dataverse-upload-zip

1

letitbk

Upload files to Harvard Dataverse via ZIP archive to bypass WAF restrictions. Use when direct uploads of R, Stata, or other code files fail with 403 Forbidden.

irb-protocol

1

letitbk

Draft IRB protocol documents from research descriptions. Covers study purpose, procedures, risks/benefits, informed consent, data security, and participant selection. Templates for survey, interview, and secondary data studies.

brainstorming

1

letitbk

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation. Also use when user says 'ask me questions', 'interview me', or needs help clarifying requirements.

marginal-effects-plot

1

letitbk

Visualize marginal effects from regression models with factor level parsing, reference category labeling, and multi-panel layouts using R ggplot2. Use when plotting AMEs from Stata margins or R marginaleffects output.

stop-slop

1

letitbk

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.

survey-regression-stata

1

letitbk

Run survey-weighted regression in Stata with svyset, margins for average marginal effects (AMEs), and esttab export. Use for complex survey analysis with sampling weights in Stata.

survey-analysis

1

letitbk

Design-based survey analysis in R using the survey package. Use for survey design setup, weighted descriptives, svyglm regression, raking, and calibration. NOT for IPW/propensity scores (use /compute-survey-weights).

codex

1

letitbk

Get code reviews and second opinions using OpenAI Codex CLI (GPT-5.3). Use for reviewing code changes, getting alternative perspectives on implementations, or validating approaches with another AI model.

doc

1

letitbk

Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.

setup-snakemake-pipeline

1

letitbk

Initialize Snakemake workflows with R and Stata integration for reproducible research pipelines. Use when setting up multi-language data processing and analysis workflows.

qualtrics-survey

1

letitbk

Manage Qualtrics surveys via API - list blocks/questions, create/update questions, add JavaScript, manage embedded data and display logic. Use for modifying existing surveys with LLM-powered features.

skill-creator

1

letitbk

Use when creating new skills, editing existing skills, scaffolding skill directories, packaging skills for distribution, or verifying skills work before deployment. Combines Anthropic's official skill authoring guide with TDD methodology.

datacheck

1

letitbk

Use when starting work with a new data file, before any analysis or visualization. Also use when encountering parsing errors, unexpected values, or when the user says "check this data" or "what's in this file".

imagegen

1

letitbk

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.

clean-survey-data

1

letitbk

Clean survey data with missing value handling, variable recoding, and Stata label conversion to R factors. Use when processing raw survey/health study data, handling coded missing values (91/92/97/98), or converting Stata labels in R.

screenshot

1

letitbk

Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.

analyze-ego-network

1

letitbk

Analyze ego-centric social networks to extract network size, composition, tie strength, and multiplexity using R egor package. Use for personal network data, social support analysis, or network health research.

napkin

1

letitbk

Maintain a per-repo napkin file that tracks mistakes, corrections, and what works. Activates EVERY session, unconditionally. Read the napkin before doing anything. Write to it continuously as you work — not just at session boundaries. Log your own mistakes, not just user corrections. The napkin lives in the repo at `.claude/napkin.md`.

research-ideation

1

letitbk

Structured hypothesis generation from literature gaps. Maps existing research, identifies unanswered questions, generates citation-backed hypotheses, and assesses feasibility using a rubric (data, timeline, funding, methods).

marginaleffects

1

letitbk

Computation of marginal effects, comparisons, and predictions using the marginaleffects R package. Use when computing AMEs, factor contrasts, continuous contrasts, or predicted values from regression models. NOT for plotting (use /marginal-effects-plot or /coefficient-plot).

draft-paper

1

letitbk

Use when writing a research paper draft from completed analysis results, or when the user says "write paper", "draft manuscript", "start writing", or wants to turn analysis outputs into a publication-ready document with literature review.

compute-survey-weights

1

letitbk

Calculate participation-adjusted survey weights using logistic regression. Use when you need to adjust sampling weights for selection bias, non-response, or create IPW (inverse probability weights) for survey data.

lit-review

1

letitbk

Conduct structured literature reviews using Zotero MCP and paper-search-mcp. Search academic databases, screen abstracts, extract findings, and synthesize into thematic reviews with citation keys and evidence tables.

finalize-analysis

1

letitbk

Use when organizing exploratory analyses into a clean reproducible project with publication-ready outputs, or when the user says "clean up", "finalize", "make reproducible", "prepare for publication", or has messy scripts needing structure.

marp-slide

1

letitbk

Create professional Marp presentation slides with 7 beautiful themes (default, minimal, colorful, dark, gradient, tech, business). Use when users request slide creation, presentations, or Marp documents. Supports custom themes, image layouts, and "make it look good" requests with automatic quality improvements.

humanizer

1

letitbk

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

heterogeneity-analysis

1

letitbk

Subgroup and heterogeneity analysis in Stata using interaction models and stratified regression. Use when examining if treatment effects vary across groups (age, gender, race, etc.).

viz

1

letitbk

Use when creating any data visualization, chart, figure, or plot. Also use when the user asks to "plot", "graph", "visualize", "make a figure", or refine an existing chart.

distribution-boxplot

1

letitbk

Create boxplots with custom statistics by group using R ggplot2. Use for comparing distributions across categories, showing median, quartiles, and range with reference lines.

discuss-claims

1

letitbk

Use when the user wants to create GitHub issues for internal team discussion of core empirical claims in a research paper, or when the user says "post issues", "create claim issues", "set up GitHub discussion", or "discuss findings on GitHub".

citation-verification

1

letitbk

Cross-check citations in a manuscript against Zotero library and Crossref. Verify author names, years, titles, journals, DOIs. Flag mismatches, missing citations, orphaned references, and formatting inconsistencies.