Posit Claude Skills
A collection of Claude Skills from Posit!
Claude Skills extend Claude's capabilities with specialized knowledge and workflows. Skills are automatically activated by Claude based on your task and can be used in Claude.ai, Claude Code, or via the Claude API. Learn more at the Claude Skills documentation.
Available Skills
Posit Developer
General-purpose developer skills useful across any language, project type, or context.
- critical-code-reviewer - Conduct rigorous, adversarial code reviews identifying security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code
- describe-design - Research a codebase and create architectural documentation describing how features or systems work, with Mermaid diagrams and stable code references suitable for humans and AI agents
- new-work - Create a todo tracking document for a new feature, bug, or task; keeps it updated with decisions, plans, and progress for the rest of the session
- review-testing - Review test code for quality, design, and completeness after implementing a feature or fixing a bug, covering assertion completeness, mocking boundaries, fixture design, test smells, and coverage gaps
- working-on - Set an existing tracking document as the source of truth for the current session, keeping it updated with decisions and progress
GitHub
Skills for GitHub pull request workflows — creating PRs, addressing review feedback, and resolving threads.
- pr-create - Creates a pull request from current changes, monitors GitHub CI, and debugs any failures until CI passes
- pr-threads-address - Review all unresolved PR review threads, address them by making necessary code changes, and commit the changes appropriately
- pr-threads-resolve - Bulk resolve unresolved PR review threads
Open Source
Skills for open-source R and Python package developers, streamlining common workflows like releases, changelogs, and contributor acknowledgments.
- create-release-checklist - Create a release checklist and GitHub issue for an R package, with automatic version calculation and customizable checklist generation
- release-post - Create professional package release blog posts following Tidyverse or Shiny blog conventions, with support for both R and Python packages
R Package Development
R package development skills for working with the r-lib ecosystem and modern R package workflows.
- testing-r-packages - Best practices for writing R package tests using testthat 3+, including test structure, expectations, fixtures, snapshots, mocking, and BDD-style testing
- cli - Comprehensive guidance for using the cli R package for command-line interface styling, semantic messaging, and user communication with inline markup, progress indicators, and theming
- cran-extrachecks - Prepare R packages for CRAN submission by checking for common ad-hoc requirements not caught by
devtools::check(), including documentation standards, DESCRIPTION field formatting, and URL validation
- lifecycle - Manage R package lifecycle according to tidyverse principles using the lifecycle package, covering deprecation workflows, function/argument renaming, superseding, and experimental stages
- r-package-development - R package development with devtools, testthat, and roxygen2, covering key commands, coding conventions, testing, documentation, and NEWS.md practices
- mirai - Async, parallel, and distributed computing in R using mirai, covering explicit dependency passing, daemon setup, parallel mapping with
mirai_map(), Shiny integration, remote/HPC launchers, and migration from future/parallel
- alt-text - Generate and improve accessible alt text for data visualizations and images in pkgdown sites and Quarto documents, covering vignette code chunks (
fig.alt), static markdown images, and multi-plot chunks
ggsql
Skills for writing ggsql queries — a grammar of graphics for SQL.
- ggsql - Write ggsql queries — a grammar of graphics for SQL. Use when the user wants to create, modify, or understand a ggsql visualization query
Shiny
Skills for Shiny app development in both R and Python.
