Index of every page on this site: llms.txt
All skills
vercel avatar

/pr-status-triage

@495cbfa official
by vercelvercel/next.js144k stars
32,812
Run it yourself

Triage CI failures and PR review comments using scripts/pr-status.js. Use when investigating failing CI jobs, flaky tests, or PR review feedback. Covers blocker-first prioritization (build > lint > types > tests), CI env var matching for local reproduction, and the Known Flaky Tests distinction.

  • 3 files
  • 6.8 KB
  • Updated last week
  • GitHub
Use this Skill: https://skilld.dev/gh/vercel/next.js/pr-status-triage

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈79 tokens for metadata: the name and description. ≈931 when used: this file. ≈704 more on demand in 2 files.

Description uses 3.9% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈315 characters, or 3.9%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

PR Status Triage

Use this skill when the user asks about PR status, CI failures, or review comments in the Next.js monorepo.

Workflow

Start by fetching data to answer the user's query:

  • For a targeted question about specific review comments, run node scripts/pr-status.js [PR] --comments-only. This skips all Actions run, job, log, and flaky-test requests.
  • For CI status or general triage, run node scripts/pr-status.js [PR] (no --wait) to snapshot the current state, then start triaging immediately from the jobs that have already finished. Re-fetch on demand as more results land instead of waiting for the whole workflow to complete.
  • Use --wait only when the final run state itself is what you need: confirming an all-green run before handing back, or picking up results after retriggering failed jobs.

Then:

  1. Read scripts/pr-status/results/index.md.
  2. For a targeted review question, inspect the relevant thread-{N}.md, review-{id}.md, or comment-{id}.md files. For full triage, also analyze each job-{id}.md and review file for failures and feedback.
  3. Prioritize blocking jobs first: build, lint, types, then test jobs.
  4. Treat failures as real until disproven; check the "Known Flaky Tests" section before calling anything flaky.
  5. Reproduce test failures locally with the same mode and environment as CI (e.g. dev or start, webpack or turbopack).
  6. After addressing review comments, reply to the thread describing what was done, then resolve it. Use reply-and-resolve-thread to do both in one step, or use reply-thread + resolve-thread separately. See scripts/pr-status/results/thread-N.md files for ready-to-use commands.
  7. When the only remaining failures are known flaky tests and no code changes are needed, retrigger the failing CI jobs with gh run rerun <run-id> --failed. Then re-run the analysis with --wait to pick up the rerun results and go back to step 1. Repeat this loop up to 5 times.
  8. Start fixing as results come in; do not wait for the whole workflow before beginning on failures that have already reported. A push, on the other hand, should wait for the workflow to complete.

CI Analysis Tips

  • Prioritize CI failures over review comments.
  • Prioritize blocking jobs first: build, lint, types, then test jobs.
  • Common fast checks:
    • rust check / build → Run cargo fmt -- --check, then cargo fmt
    • lint / build → Run pnpm prettier --write <file> for prettier errors
    • test failures → Run the specific failing test path locally

Run tests in the mode (e.g.):

# Development mode with Turbopack
pnpm test-dev-turbo test/path/to/test.ts

# Production build and start with Webpack
pnpm test-start-webpack test/path/to/test.ts

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      # waits for the run to finish, then re-analyzes (final confirmation or after reruns)
node scripts/pr-status.js [PR] --comments-only  # reviews/comments only; skips CI jobs
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

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 495cbfa. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated last week
metadata
{
  "internal": true
}

README badge

README badge for vercel/next.js/pr-status-triage