Address PR review feedback by systematically working through every unresolved PR review thread on the current branch's PR - analyze each comment, make the requested code changes (with tests where useful), commit, and optionally reply and resolve.
The English summary is being prepared. Showing the original description.
Review the instructions the agent will receive before you install.
Before using this command, check if the gh pr-review extension is installed:
gh extension list | grep -q pr-review || gh extension install agynio/gh-pr-review
Every gh pr-review subcommand requires both --pr <number> and --repo <owner/repo> — do not omit either. Look the values up once at the start of the workflow and substitute the literal numbers and slugs into every later command.
Get the PR number for the current branch:
gh pr view --json number -q .number
Get the repository slug:
gh repo view --json nameWithOwner -q .nameWithOwner
Then pass the resulting values directly — e.g. --pr 42 --repo posit-dev/skills — on every subsequent gh pr-review call in this workflow (review view, comments reply, threads resolve, etc.).
Display all reviews, inline comments, and replies for a pull request:
gh pr-review review view --pr <number> --repo <owner/repo>
Common filters:
--reviewer <login> — Filter by specific reviewer--states <list> — Comma-separated review states (APPROVED, CHANGES_REQUESTED, COMMENTED, DISMISSED)--unresolved — Show only unresolved threads--tail <n> — Show only the last n replies per thread--include-comment-node-id — Include GraphQL node IDs for repliesgh pr-review comments reply --thread-id <PRRT_...> --body "<reply-text>" --repo <owner/repo> --pr <number>
For multi-line replies, pass --body "$(cat <<'EOF' ... EOF\n)" heredoc syntax.
gh pr-review threads resolve --thread-id <PRRT_...> --pr <number> --repo <owner/repo>
Thread IDs (format PRRT_...) come from review view --include-comment-node-id.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Generate and improve accessible alt text for data visualizations and images in R packages and Quarto documents. Use when the user wants to add, improve, or audit alt text for figures in a pkgdown site or .qmd files. Activate for requests that mention fig-alt, fig.alt, figure descriptions, or alt text in the context of an R package or Quarto document.
The English summary is being prepared. Showing the original description.
Create and use brand.yml files for consistent branding across Shiny apps and Quarto documents. Covers: (1) Creating new _brand.yml files, (2) Applying to Shiny (R and Python), (3) Using in Quarto, (4) Modifying existing files, and (5) Troubleshooting. Includes complete specifications and integration guides.
The English summary is being prepared. Showing the original description.
Create a release checklist and GitHub issue for an R package. Use when the user asks to "create a release checklist" or "start a release" for an R package.
The English summary is being prepared. Showing the original description.
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
The English summary is being prepared. Showing the original description.
Deploy or publish Python and R content to a Posit Connect server using rsconnect-python or the R rsconnect package. Handles interactive apps and dashboards, web APIs, rendered documents, and prepared bundles/manifests. Use whenever the user asks to deploy, publish, or redeploy content to Posit Connect, or mentions rsconnect. Consult this skill instead of guessing flags or commands.
The English summary is being prepared. Showing the original description.
Research a codebase and create architectural documentation describing how features or systems work. Use when the user asks to: (1) Document how a feature works, (2) Create an architecture overview, (3) Explain code structure for onboarding or knowledge transfer, (4) Research and describe a system's design. Produces markdown documents with Mermaid diagrams and stable code references suitable for humans and AI agents.
The English summary is being prepared. Showing the original description.