Next.js pr-status-triage
install
source · Clone the upstream repo
git clone https://github.com/vercel/next.js
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/vercel/next.js "$T" && mkdir -p ~/.claude/skills && cp -r "$T/.agents/skills/pr-status-triage" ~/.claude/skills/vercel-next-js-pr-status-triage && rm -rf "$T"
manifest:
.agents/skills/pr-status-triage/SKILL.mdsource content
PR Status Triage
Use this skill when the user asks about PR status, CI failures, or review comments in the Next.js monorepo.
Workflow
- Run
in the background (timeout 1 min), then readnode scripts/pr-status.js --wait
.scripts/pr-status/index.md - Analyze each
andjob-{id}.md
file for failures and review feedback.thread-{N}.md - Prioritize blocking jobs first: build, lint, types, then test jobs.
- Treat failures as real until disproven; check the "Known Flaky Tests" section before calling anything flaky.
- Reproduce locally with the same mode and env vars as CI.
- After addressing review comments, reply to the thread describing what was done, then resolve it. Use
to do both in one step, or usereply-and-resolve-thread
+reply-thread
separately. Seeresolve-thread
files for ready-to-use commands.thread-N.md - When the only remaining failures are known flaky tests and no code changes are needed, retrigger the failing CI jobs with
. Then wait 5 minutes and go back to step 1. Repeat this loop up to 5 times.gh run rerun <run-id> --failed
Quick Commands
node scripts/pr-status.js # current branch PR node scripts/pr-status.js <number> # specific PR node scripts/pr-status.js [PR] --wait # background mode, waits for CI to finish node scripts/pr-status.js --skip-flaky-check # skip flaky test detection
Thread interaction:
node scripts/pr-status.js reply-thread <threadNodeId> "<body>" # reply to a review thread node scripts/pr-status.js resolve-thread <threadNodeId> # resolve a review thread node scripts/pr-status.js reply-and-resolve-thread <threadNodeId> "<body>" # reply and resolve in one step
References
- workflow.md — prioritization, common failure patterns, resolving review threads
- local-repro.md — mode/env matching and isolation guidance