Agent skill

CI Triage

by nubjs in nubjs/nub

Find and diagnose RED CI with the gh CLI — answer "is anything failing?" and "why?" correctly, without being handed a URL.

MITAuto-check passed

Install CI Triage

skills CLI
$ npx skills add nubjs/nub --skill ci-triage -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nubjs/nub ci-triage --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nubjs/nub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/ci-triage .claude/skills/ci-triage && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ci-triage
GitHub stars
4.4k
Token cost
~1.8k tokens
SKILL.md length
749 words
Files
1
Skills in repo
31
Repo updated
First seen
Licence
MIT

At a glance

Find and diagnose RED CI with the gh CLI — answer "is anything failing?" and "why?" correctly, without being handed a URL.

  • Works in 3 steps: List every run of that workflow on that… → If a later run of the same workflow on… → Check the concurrency group. group: ${{…
  • SKILL.md covers The rule, The one command that is always…, Diagnosing one failure and Superseded-run triage — is…, plus 3 more sections
  • Calls gh, git and jq

What it does

CI Triage is an agent skill from nubjs/nub. Find and diagnose RED CI with the gh CLI — answer "is anything failing?" and "why?" correctly, without being handed a URL. Invoke (via the Skill tool) whenever you need to check whether a branch, commit, or PR is green, whenever someone reports failing CI, before cutting a release, and before claiming any commit is green. THE FAILURE THIS SKILL EXISTS TO PREVENT: gh run list reports a RUN-level conclusion, and a run whose rollup is cancelled can contain a job whose conclusion is failure — so filtering runs on…

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with GitHub. The repository describes itself as: The fast all-in-one Node.js toolkit. The licence is MIT.

Example prompts

  • “is anything failing?”
  • “failure”
  • “/ci-triage”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. List every run of that workflow on that SHA. More than one is the tell.
  2. If a later run of the same workflow on the same SHA is fully green, the code is fine — the red one was superseded. The commit still shows…
  3. Check the concurrency group. group: ${{ github.workflow }}-${{ github.ref }} means a schedule run and a push run on main share a group and…

What it can do on your machine

Read from SKILL.md and the folder at commit 568e73a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • git
    • jq

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

CI Triage loads about 1.8k tokens when it runs. Until then it costs about 217 tokens; SKILL.md has 749 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~217
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nubjs/nub at commit 568e73a, republished under its MIT licence (© nubjs). 749 words, ~1,780 tokens.

Download SKILL.mdSave it as .claude/skills/ci-triage/SKILL.md (or your agent's skills folder).
name
ci-triage
description
Find and diagnose RED CI with the gh CLI — answer "is anything failing?" and "why?" correctly, without being handed a URL. Invoke (via the Skill tool) whenever you need to check whether a branch, commit, or PR is green, whenever someone reports failing CI, before cutting a release, and before claiming any commit is green. THE FAILURE THIS SKILL EXISTS TO PREVENT: `gh run list` reports a RUN-level `conclusion`, and a run whose rollup is `cancelled` can contain a job whose conclusion is `failure` — so filtering runs on `conclusion=="failure"` silently misses real red, and taking the latest run per workflow hides an older failed run on the same SHA. The authoritative instrument is the commit's CHECK-RUNS, which is what the GitHub UI renders. Pairs with `ci-watch` (blocking until a run is terminal) and `ci-adhoc-test` (running a probe on a real OS).

Investigating CI

ci-watch answers "has it finished, and did it pass?" for one run you are waiting on. This skill answers the two questions you get asked cold: "is anything red?" and "why is this red?" — starting from a branch name or a commit, never from a URL someone hands you.

The rule

Never answer "is it green?" from run-level conclusion. Query the commit's check-runs.

A GitHub Actions run rolls up its jobs into one conclusion, and that rollup is lossy in the exact case that matters:

What happenedRun conclusionJob conclusionsgh run list shows
A job failedfailureone failure✅ red — you see it
A job failed inside a run that also got cancelledcancelledone failure❌ nothing — filtered out
Superseded by cancel-in-progresscancelledall cancelled❌ nothing (correctly)

The middle row is real and it is what the UI paints red on the commit. It happens whenever a workflow has an aggregation/gate job that runs after its matrix legs: concurrency: cancel-in-progress cancels the legs, the gate still runs, sees cancelled, and fails. The run rolls up cancelled; the gate job is failure.

The one command that is always correct

bash
SHA=$(git rev-parse origin/main)   # or a PR head, or any commit
gh api repos/nubjs/nub/commits/$SHA/check-runs --paginate \
  --jq '.check_runs[] | select(.conclusion != "success" and .conclusion != "skipped" and .conclusion != "neutral")
        | "\(.conclusion // .status) | \(.name) | \(.html_url)"'

Empty output means genuinely green. Anything else is exactly what a human sees in the Actions tab, with a clickable URL per finding. This endpoint is the source of truth because it is what the UI renders — run-level data is downstream of it.

Counting, and the --paginate trap

--paginate runs --jq once PER PAGE. A per-item filter like the one above is fine — each page emits its own lines and they concatenate. But any aggregation (length, add, group_by) silently returns one result per page instead of a total:

bash
# WRONG — prints "0" then "1" on a 2-page response. Reads like 0 if you only look at line 1.
gh api repos/nubjs/nub/commits/$SHA/check-runs --paginate --jq '[.check_runs[]|select(.conclusion=="failure")]|length'

Use --slurp to get one array across pages, and pipe to external jq — --slurp is rejected together with --jq:

bash
# RIGHT — one number for the whole commit.
gh api repos/nubjs/nub/commits/$SHA/check-runs --paginate --slurp \
  | jq '[.[].check_runs[] | select(.conclusion=="failure")] | length'

This is not hypothetical: a release commit here carried 192 check-runs across 2 pages, and the naive count printed 0 on the first line.

Diagnosing one failure

Given a failing check, get the run, then the job, then the log — in that order.

bash
gh run view <run-id> --json name,status,conclusion,headBranch,headSha,event,createdAt
gh run view <run-id> --json jobs --jq '.jobs[] | "\(.conclusion // .status) | \(.name)"'
gh run view <run-id> --log-failed > /tmp/fail.log 2>&1; echo "EXIT=$?"
sed -e 's/\x1b\[[0-9;]*m//g' /tmp/fail.log | grep -viE '^\s*$' | tail -40

Strip ANSI escapes (sed -e 's/\x1b\[[0-9;]*m//g') or the log is unreadable. --log-failed returns only failing steps, which is usually 40 lines rather than 40,000.

Read the event and createdAt fields before concluding anything. They tell you whether the run was superseded, and by what.

Superseded-run triage — is this red REAL?

A red check on a commit is not automatically a broken commit. Decide with this:

  1. List every run of that workflow on that SHA. More than one is the tell.
    bash
    gh run list --workflow <file>.yml --limit 30 \
      --json databaseId,status,conclusion,headSha,headBranch,event,createdAt \
      --jq '.[] | select(.headSha=="'"$SHA"'") | "id=\(.databaseId) | \(.conclusion // .status) | \(.event) | \(.createdAt)"'
  2. If a later run of the same workflow on the same SHA is fully green, the code is fine — the red one was superseded. The commit still shows red, which is a workflow defect worth fixing, not a code defect.
  3. Check the concurrency group. group: ${{ github.workflow }}-${{ github.ref }} means a schedule run and a push run on main share a group and will cancel each other, because both carry refs/heads/main. That is a common and surprising source of self-inflicted red.
Show full SKILL.md (245 more words)Show less

The gate-job anti-pattern, and its fix

A gate job that aggregates matrix legs must treat cancelled as not a verdict. This is wrong:

bash
[[ "$smoke" == "success" || "$smoke" == "skipped" ]] || { echo "smoke failed"; exit 1; }

A superseded run sets smoke=cancelled, so the gate fails and paints the commit red forever. Accept cancelled too — it does not mask a real failure, because a genuinely failing leg aggregates to failure, not cancelled:

bash
[[ "$smoke" == "success" || "$smoke" == "skipped" || "$smoke" == "cancelled" ]] || { echo "smoke failed"; exit 1; }

What NOT to do

  • Do not filter gh run list on conclusion=="failure" and call the absence of hits "green". That is the whole bug this skill exists for.
  • Do not take the latest run per workflow (group_by(.name) | max_by(.createdAt)). A later scheduled run can hide an earlier failed push run on the same SHA.
  • Do not trust --branch main alone to find everything; a check can be attached by an app or a workflow_run. Check-runs on the SHA catch all of them.
  • Do not conclude "not failing" from a bot issue being absent. The trunk-red bot files on its own schedule and its silence proves nothing.
  • Do not read an exit code through a pipe (gh ... | head then $?). Redirect, capture $? on its own line, then inspect.

Reporting a finding

State the commit, the check name, the run URL, whether a later run on the same SHA passed, and the mechanism. "CI is red" without those is not a diagnosis. If a superseded run is the cause, say so plainly and name the fix — the commit is still red in the UI and someone has to look at it.

© nubjs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/ci-triage of nubjs/nub.

Open the folder on GitHubat commit 568e73a

Compare with similar skills

CI Triage next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

CI Triage compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
CI Triage this skillnubjs/nub4.4k—~1.8kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Diagnosing Superpowers Sessionsobra/superpowers297k3 repos~1.7kAutomated safety check: PassMIT
Greplooponyx-dot-app/onyx32k4 repos~3.3kAutomated safety check: PassMIT
GitHub Deep Researchbytedance/deer-flow84k4 repos~1.3kAutomated safety check: PassMIT
Update V8 Versionopeninterpreter/openinterpreter69k2 repos~845Automated safety check: PassApache-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.

    297k GitHub starsUsed in 3 repos~1.7k tokens
    Agent WorkflowsAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed
  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    84k GitHub starsUsed in 4 repos~1.3k tokens
    Research & ScienceAuto-check passed
  • Update V8 Version

    openinterpreter/openinterpreter

    Bumps the pinned v8 and rusty_v8 versions in Codex, validates the release-candidate path with the v8-canary check, and traces failures to upstream build changes.

    69k GitHub starsUsed in 2 repos~845 tokens
    DevOps & CloudAuto-check passed
  • Last30days

    mvanhorn/last30days-skill

    Research what people actually say about any topic in the last 30 days.

    64k GitHub stars~7.9k tokensUpdated today
    Research & ScienceAuto-check: notes

More from nubjs/nub

All 31 skills in this repo
  • Cpu Reduction

    nubjs/nub

    Diagnose and clear CPU, memory, and disk contention on the maintainer's dev host.

    4.4k GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Reclaim disk on the maintainer's Mac when the volume is full or filling — ENOSPC, "no space left on device", a failed build or agent harness, or a routine sweep of Rust build residue.

    4.4k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Nub Charts

    nubjs/nub

    Build a performance chart for nubjs.com — the SVG bar figures in blog posts, docs pages and social posts (a runtime augmentation against plain node, an install or dispatch comparison, a cross-tool…

    4.4k GitHub stars~4.6k tokensUpdated today
    Auto-check passed
  • Audit Thread

    nubjs/nub

    A skill your agent uses when running a compatibility/parity AUDIT — enumerating where nub diverges from a reference it claims parity with (pnpm CLI grammar, a lockfile format, a Node behavior, a…

    4.4k GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Linux Vm Test

    nubjs/nub

    Run ad-hoc Nub tests and debugging probes on real local Linux guests.

    4.4k GitHub stars~986 tokensUpdated today
    Auto-check passed
  • Performance-trace Nub package-manager installs using the existing phase timings, structured diagnostics, and sampling-profiler workflow.

    4.4k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Works with

Questions about CI Triage

What does CI Triage do?

Find and diagnose RED CI with the gh CLI — answer "is anything failing?" and "why?" correctly, without being handed a URL. CI Triage is an agent skill from nubjs/nub." correctly, without being handed a URL.

How do I install CI Triage in Claude Code?

Run `npx skills add nubjs/nub --skill ci-triage -a claude-code`. Or copy the skill folder (.claude/skills/ci-triage in nubjs/nub) into .claude/skills/ci-triage in your project. Claude Code loads it when a task matches its description.

How do I install CI Triage in Codex?

Run `npx skills add nubjs/nub --skill ci-triage -a codex`. Or copy the skill folder (.claude/skills/ci-triage in nubjs/nub) into .agents/skills/ci-triage in your project. Codex loads it when a task matches its description.

Can I use CI Triage in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nubjs/nub --skill ci-triage -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ci-triage, .gemini/skills/ci-triage, .github/skills/ci-triage and .opencode/skills/ci-triage in your project.

What does CI Triage need to run?

Going by SKILL.md and its folder, CI Triage needs the command-line tools its instructions call (gh, git and jq).

Does CI Triage access the network?

SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is CI Triage safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does CI Triage use?

CI Triage is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does CI Triage use?

About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to CI Triage?

Skills that share tags, products or a category with CI Triage: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Diagnosing Superpowers Sessions (obra/superpowers, 297k stars), Greploop (onyx-dot-app/onyx, 32k stars) and GitHub Deep Research (bytedance/deer-flow, 84k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains CI Triage?

nubjs (a GitHub organization) maintains it in nubjs/nub, which has 4,375 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on October 9, 2026.

Source: nubjs/nub on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.