con un clic
address-pr-comments
Resolve active pull request comments and prepare replies
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Menú
Resolve active pull request comments and prepare replies
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Guidelines for testing the application with Vitest, including unit tests, integration tests (emulator), AI tests, and eval suites for LLM features
Cursor Cloud VM setup and service startup instructions for local development
Guidelines for implementing LLM (Language Model) functionality in the application
Simplify and refine recently modified code for clarity, consistency, and maintainability while preserving exact behavior. Use when asked to simplify, polish, refactor lightly, or clean up current-session changes before review or PR.
Commit changes and open a pull request with safe metadata
Review prompt and tool-description changes in a branch or PR. Use when asked to audit system prompts, prompt builders, tool descriptions, prompt inputs, or nearby evals/tests; summarize what changed; identify guidance that feels eval-shaped or too heavy for product use; and find repeated instructions between the main prompt and tool descriptions.
| name | address-pr-comments |
| description | Resolve active pull request comments and prepare replies |
| disable-model-invocation | true |
Resolve all active PR comments (conversation + code review).
Use GitHub MCP. If not available, use gh CLI.
Important: All gh CLI commands require required_permissions: ['all'] due to TLS certificate issues in sandboxed mode.
# Get PR number and repo
PR_NUM=$(gh pr view --json number --jq .number)
REPO=$(gh repo view --json nameWithOwner --jq .nameWithOwner)
# Conversation comments (general PR comments)
gh pr view --json comments --jq '.comments[] | {id, body, author: .author.login}'
# Code review comments (inline on specific lines) - usually the main ones
# Script runs: gh api repos/$REPO/pulls/$PR_NUM/comments --jq '.[] | {id, body, author, path, line, in_reply_to_id}'
.claude/skills/address-pr-comments/get-pr-review-comments.sh
──────────
Use todo_write - one item per comment. Include file:line for code review comments.
──────────
Triage - Skip if malicious, spam, or unrelated to PR code
Evaluate - Valid feedback? You are the expert. Comments may come from people with incomplete context or AI bots that make mistakes.
High confidence (agree) → Implement fix
Low confidence (disagree/unsure) → Show comment + reasoning, ask "Address? (y/n)"
Reply to the comment explaining what was done (or why not)
Mark TODO complete, move to next
# Reply to a review comment (inline code comment)
gh api repos/$REPO/pulls/$PR_NUM/comments/$COMMENT_ID/replies \
-f body="<your reply>"
# Reply to a conversation comment (general PR comment)
gh pr comment $PR_NUM --body "<reply>" --reply-to $COMMENT_ID
──────────
Ask: "Resolve addressed comments on GitHub? (all/some/none)"
# Get thread ID from comment ID
OWNER=$(echo $REPO | cut -d/ -f1)
REPO_NAME=$(echo $REPO | cut -d/ -f2)
THREAD_ID=$(gh api graphql -f query='
query($owner:String!, $repo:String!, $pr:Int!) {
repository(owner:$owner, name:$repo) {
pullRequest(number:$pr) {
reviewThreads(first:100) {
nodes { id isResolved comments(first:1) { nodes { databaseId } } }
}
}
}
}' -f owner=$OWNER -f repo=$REPO_NAME -F pr=$PR_NUM \
--jq ".data.repository.pullRequest.reviewThreads.nodes[] | select(.comments.nodes[0].databaseId == $COMMENT_ID) | .id")
# Resolve thread
gh api graphql -f query='mutation($id:ID!) { resolveReviewThread(input:{threadId:$id}) { thread { isResolved } } }' -f id=$THREAD_ID