reply-to-pr-conversation
This Claude Code skill drafts a single conversational reply addressing multiple GitHub PR comments, confirms the message with the user, and posts it as a new issue comment. The reply integrates tracked items (categorized as fixes, skips, answers, or clarifications) into natural prose while selectively quoting relevant passages and applying consistent voice rules. Use it when you need to respond to multiple PR conversation points in one cohesive message rather than replying individually to each comment.
git clone --depth 1 https://github.com/tobihagemann/turbo /tmp/reply-to-pr-conversation && cp -r /tmp/reply-to-pr-conversation/claude/skills/reply-to-pr-conversation ~/.claude/skills/reply-to-pr-conversationSKILL.md
# Reply to PR Conversation Draft a single reply that addresses a processed issue-comment list, confirm with the user, and post it as a new PR issue comment. ## Step 1: Run `/github-voice` Skill Run the `/github-voice` skill to load voice rules and the insider-vs-outsider detection. ## Step 2: Compose the Reply Use the processed-item list from conversation context. Each entry has: id, author, original comment body (to quote from selectively), category (`fix`, `skip`, `answer`, or `clarify`), and per-category payload. Draft one reply that addresses every item as natural conversational prose. The output is a single piece of prose with flexible length and no rigid section structure. **Use the category to interpret each payload:** - **fix**: payload is a commit SHA. Mention "fixed in `<sha>`" where it fits the flow, plus a brief note when the fix diverges from what the commenter suggested. - **skip**: payload is the skip reasoning. State it directly. - **answer**: payload is answer text prepared upstream. Integrate it as the implementer's own words. - **clarify**: payload is a user-directed question. Ask it as-is. **Quote selectively.** Use `>` blockquotes only for the phrase being responded to. A single-topic reply quotes one sentence then responds; a multi-topic reply weaves quotes and responses together. Drop quotes entirely when @mentions plus context make the reply unambiguous. **Quote handling:** - Strip leading `>` from quoted lines so nested blockquotes don't misattribute. - Replace fenced-code lines inside a quote with `> [code snippet]`. - If the author login ends in `[bot]`, omit the suffix from the `@` mention. Apply `/github-voice` rules. Match the conversation's length and tone. An acknowledgment with emoji is fine when the discussion calls for it; a multi-paragraph response is fine when the items warrant it. ## Step 3: Confirm Output the drafted reply as text for review: ``` **Draft comment** <full comment body as it will be posted> ``` Then use `AskUserQuestion` to ask whether to post. Offer: - **Post** — post the comment - **Cancel** — skip posting ## Step 4: Post the Comment Auto-detect owner, repo, and PR number from the current branch if not provided. Write the drafted body to `.turbo/pr/comment.md` with the Write tool, then post via the issue-comments REST endpoint: ```bash gh api -X POST \ "/repos/<owner>/<repo>/issues/<pr_number>/comments" \ -F body=@.turbo/pr/comment.md ``` Report the posted comment's URL. Then use the TaskList tool and proceed to any remaining task. ## Rules - Never close the PR, resolve a thread, or edit existing comments. Only post a new issue comment. - If the post fails, report the failure and leave the drafted body in the output so the user can post it manually.
For each reviewer question on a PR, recall implementation reasoning and compose a raw answer. Use when the user asks to \"answer reviewer questions\", \"draft answers to PR questions\", or \"explain reviewer questions\".
Apply findings by making the suggested code changes. Applies accepted verdicts, escalates ambiguous findings to the user, and offers to note genuine improvements for later. Use when the user asks to \"apply findings\", \"apply fixes\", \"apply suggestions\", \"apply accepted findings\", \"fix the findings\", or \"apply the review results\".
Project-wide health audit pipeline that fans out to all analysis skills in parallel, evaluates findings, and produces a unified report at .turbo/audit.md. Use when the user asks to \"audit the project\", \"run a full audit\", \"project health check\", \"audit my code\", \"codebase audit\", or \"comprehensive review\".
Shared changelog conventions and formatting rules referenced by $create-changelog and $update-changelog. Not typically invoked directly.
Enforce mirror, reuse, and symmetry principles to keep new code consistent with surrounding code. Use when writing new code in an existing codebase, adding new features, refactoring, or making any code changes.
Run autonomous task execution using the codex CLI. Use when the user asks to \"codex exec\", \"run codex exec\", \"execute a task with codex\", or \"delegate to codex\".
Run AI-powered code review using the codex CLI. Use when the user asks to \"codex review\", \"run codex review\", or \"review a commit with codex\".
Shared commit message rules and technical constraints referenced by $stage-commit and $commit-staged. Not typically invoked directly.