From pair-review
Batch-opens up to 10 recent GitHub PRs with pending review requests for you in pair-review, auto-triggering AI analysis via ?analyze=true.
npx claudepluginhub in-the-loop-labs/pair-review --plugin pair-reviewThis skill uses the workspace's default tool permissions.
Batch-open outstanding GitHub review requests in pair-review with AI analysis.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Checks Next.js compilation errors using a running Turbopack dev server after code edits. Fixes actionable issues before reporting complete. Replaces `next build`.
Batch-open outstanding GitHub review requests in pair-review with AI analysis.
Call mcp__pair-review__get_server_info to get the pair-review web UI URL. If the server
is not running, inform the user and stop.
Use user-review-requested:@me (not review-requested) to find only PRs where the user
was directly requested as a reviewer, excluding team-based review requests. The gh search prs
CLI does not support this qualifier, so use the search API directly:
SINCE=$(date -v-7d +%Y-%m-%d 2>/dev/null || date -d '7 days ago' +%Y-%m-%d)
gh api "search/issues?q=is:pr+is:open+user-review-requested:@me+updated:>=${SINCE}&per_page=30" \
--jq '.items[] | {number, title, html_url, repo: (.repository_url | split("/")[-2:] | join("/"))}'
Each result provides number, title, html_url, and repo (as owner/repo).
Limit: Open at most 10 PRs. If more than 10 are found, open only the first 10 (most recently updated) and report how many were skipped.
For each PR found (up to the limit), open it in the browser with the ?analyze=true query parameter, which
automatically starts AI analysis when the page loads:
open "{server_url}/pr/{owner}/{repo}/{number}?analyze=true"
where {owner}/{repo} comes from the repo field split on /.
No MCP calls per PR are needed — the ?analyze=true parameter handles triggering analysis.
Summarize what was done: