Agent skill

Check PR CI Status

by openshift-eng in openshift-eng/ai-helpers

Check CI status on a GitHub PR and detect new failures. An agent skill from openshift-eng/ai-helpers.

Apache-2.0Auto-check passedTesting & QA

Install Check PR CI Status

skills CLI
$ npx skills add openshift-eng/ai-helpers --skill check-pr-ci-status -a claude-code

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

GitHub CLI
$ gh skill install openshift-eng/ai-helpers check-pr-ci-status --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/openshift-eng/ai-helpers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/github/skills/check-pr-ci-status .claude/skills/check-pr-ci-status && 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
check-pr-ci-status
GitHub stars
120
Token cost
~885 tokens
SKILL.md length
317 words
Files
2
Skills in repo
118
Repo updated
First seen
Licence
Apache-2.0

At a glance

Check CI status on a GitHub PR and detect new failures. An agent skill from openshift-eng/ai-helpers.

  • Works in 2 steps: gh CLI: Authenticated with gh auth login → Repository read access: The token must…
  • Monitoring a PR for CI regressions
  • SKILL.md covers When to Use This Skill, Prerequisites, Implementation and How It Works, plus 2 more sections
  • Runs Shell scripts from its folder; calls bash, jq and gh

What it does

Check PR CI Status is an agent skill from openshift-eng/ai-helpers. Check CI status on a GitHub PR and detect new failures. Use when monitoring a PR for CI regressions, deciding if CI failures need attention, or building a review-response loop.

Its SKILL.md is about 890 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `check_pr_ci_status.sh`).

It sits in Testing & QA, covering Failing and flaky tests. It works with GitHub. The repository describes itself as: Developer productivity tools for Claude Code & other AI assistants. The licence is Apache-2.0.

When your agent uses it

  • Monitoring a PR for CI regressions
  • Deciding if CI failures need attention
  • Building a review-response loop

Example prompts

  • “/check-pr-ci-status”

Requirements

  • A Bash shell

Workflow steps

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

  1. gh CLI: Authenticated with gh auth login
  2. Repository read access: The token must have permission to view PR check status

What it can do on your machine

Read from SKILL.md and the folder at commit a627176. 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

    Ships script files (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • bash
    • jq
    • gh

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

  • Network

    No URLs in SKILL.md. Its commands use gh, 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

Check PR CI Status loads about 885 tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 317 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~885

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 openshift-eng/ai-helpers at commit a627176, republished under its Apache-2.0 licence (© openshift-eng). 317 words, ~885 tokens.

Download SKILL.mdSave it as .claude/skills/check-pr-ci-status/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
check-pr-ci-status
description
Check CI status on a GitHub PR and detect new failures. Use when monitoring a PR for CI regressions, deciding if CI failures need attention, or building a review-response loop.

Check PR CI Status

Check the CI check status on a GitHub pull request and detect whether any failures are new since the last check. This enables efficient CI monitoring — only act on new failures, not stale ones that were already addressed.

When to Use This Skill

Use this skill when you need to:

  • Check if a PR has any failing CI checks
  • Detect new CI failures that appeared since your last check
  • Decide whether CI failures need attention in an agentic workflow
  • Build a polling loop that reacts to CI status changes

Prerequisites

  1. gh CLI: Authenticated with gh auth login
  2. Repository read access: The token must have permission to view PR check status

Implementation

Basic usage
bash
result=$(bash "${CLAUDE_PLUGIN_ROOT}/skills/check-pr-ci-status/check_pr_ci_status.sh" \
  --repo owner/repo \
  --pr 123)
With previous failure tracking
bash
result=$(bash "${CLAUDE_PLUGIN_ROOT}/skills/check-pr-ci-status/check_pr_ci_status.sh" \
  --repo owner/repo \
  --pr 123 \
  --previous-failures "ci/prow/e2e-aws ci/prow/unit")
Parameters
ParameterRequiredDescription
--repoYesGitHub repository in owner/repo format
--prYesPull request number
--previous-failuresNoSpace-separated check names that were failing on the last check
Output

JSON on stdout:

json
{
  "failing_checks": [
    {"name": "ci/prow/e2e-aws", "state": "FAILURE"},
    {"name": "ci/prow/unit", "state": "FAILURE"}
  ],
  "failing_count": 2,
  "failing_names": "ci/prow/e2e-aws ci/prow/unit",
  "has_new_failures": true,
  "formatted": "- ci/prow/e2e-aws (FAILURE)\n- ci/prow/unit (FAILURE)"
}
Using in a polling loop

The failing_names field is designed to be passed back as --previous-failures on the next call:

bash
LAST_FAILURES=""

while true; do
  sleep 300

  result=$(bash "${CLAUDE_PLUGIN_ROOT}/skills/check-pr-ci-status/check_pr_ci_status.sh" \
    --repo owner/repo --pr 123 --previous-failures "$LAST_FAILURES")

  has_new=$(echo "$result" | jq -r '.has_new_failures')
  if [[ "$has_new" == "true" ]]; then
    formatted=$(echo "$result" | jq -r '.formatted')
    echo "New CI failures detected:"
    echo "$formatted"
    # Address failures...
  fi

  LAST_FAILURES=$(echo "$result" | jq -r '.failing_names')
done

How It Works

  1. Runs gh pr checks to get all check statuses
  2. Filters to checks with state FAIL or FAILURE
  3. Compares current failing check names against --previous-failures
  4. Reports has_new_failures: true if the set of failing checks has changed
  5. Returns both structured data and pre-formatted text

New Failure Detection

A failure is considered "new" when the set of failing check names differs from --previous-failures. This means:

  • A check that was passing and is now failing triggers has_new_failures
  • A check that was already failing stays in the list but doesn't trigger by itself
  • A check that was failing and is now passing changes the set and triggers too

If --previous-failures is not provided, any failing check is considered new.

See Also

  • Related Skill: fetch-pr-comments — Fetch trusted PR review comments
  • Related Skill: upload-screenshot — Upload images to GitHub for PR comments

© openshift-eng, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in plugins/github/skills/check-pr-ci-status of openshift-eng/ai-helpers.

  • SKILL.md
  • check_pr_ci_status.sh

Open the folder on GitHubat commit a627176

Compare with similar skills

Check PR CI Status 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.

Check PR CI Status compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Check PR CI Status this skillopenshift-eng/ai-helpers120—~885Automated safety check: PassApache-2.0
Triage CI Flakepayloadcms/payload45k—~4.4kAutomated safety check: PassMIT
GreptimeDB Fuzz CI Failure InvestigationGreptimeTeam/greptimedb6.7k—~4.4kAutomated safety check: PassApache-2.0
Fix Issueremix-run/remix33k—~1.8kAutomated safety check: PassMIT
Issue To Regression Testbrunosabot/streamline-card269—~529Automated safety check: PassMIT
Detect Flaky Testsagent-substrate/substrate4.7k—~3kAutomated safety check: PassApache-2.0

Similar skills

  • Triage CI Flake

    payloadcms/payload

    A skill your agent uses when CI tests fail on main branch after PR merge, when investigating flaky test failures, or when user provides a PR URL/number to aggregate all failing tests

    45k GitHub stars~4.4k tokensUpdated today
    Testing & QAAuto-check passed
  • Diagnoses a failed GreptimeDB fuzz CI job by pulling its GitHub Actions logs and fuzz artifacts, then matching the evidence to the local source code.

    6.7k GitHub stars~4.4k tokensUpdated today
    Testing & QAAuto-check passed
  • Fix Issue

    remix-run/remix

    Fix a reported issue in Remix from a GitHub issue. An agent skill from remix-run/remix.

    33k GitHub stars~1.8k tokensUpdated today
    Testing & QAAuto-check passed
  • Issue To Regression Test

    brunosabot/streamline-card

    A skill your agent uses when the user asks to fix a bug, references a GitHub issue number, or describes an issue and wants a fix.

    269 GitHub stars~529 tokensUpdated 4 mo ago
    Testing & QAAuto-check passed
  • Detect Flaky Tests

    agent-substrate/substrate

    Detects flaky Go tests by analyzing GitHub Actions workflow runs across the last 7 days and all PRs — covering both the run-tests job (unit/integration) and the e2e-test job (gVisor and microVM…

    4.7k GitHub stars~3k tokensUpdated today
    Testing & QAAuto-check passed
  • Official

    Investigate and fix flaky/random CI test failures in dotnet/macios.

    2.9k GitHub stars~1.3k tokensUpdated yesterday
    Testing & QAAuto-check passed

More from openshift-eng/ai-helpers

All 118 skills in this repo
  • Investigate CI Reliability

    openshift-eng/ai-helpers

    Find and independently validate actionable reliability defects across OpenShift release jobs and presubmits, then export portable issue handoffs.

    120 GitHub stars~1.9k tokensUpdated 3 days ago
    Auto-check passed
  • Address Review PR

    openshift-eng/ai-helpers

    Fetch and address all PR review comments — categorize by priority, make code changes, post replies, and push.

    120 GitHub stars~2.9k tokensUpdated 3 days ago
    Auto-check passed
  • Categorize Activity Types

    openshift-eng/ai-helpers

    Categorize Jira issues into Red Hat Sankey Activity Type categories using MCP Jira tools.

    120 GitHub stars~2.4k tokensUpdated 3 days ago
    Auto-check passed
  • Has Review Work

    openshift-eng/ai-helpers

    Decide whether a GitHub PR has unanswered authorized review comments or new required CI failures worth a follow-up agent.

    120 GitHub stars~1.9k tokensUpdated 3 days ago
    Auto-check passed
  • Must Gather Analyzer

    openshift-eng/ai-helpers

    Analyze OpenShift must-gather diagnostic data including cluster operators, pods, nodes, and network components.

    120 GitHub stars~2.3k tokensUpdated 3 days ago
    Auto-check passed
  • Payload Autodl JSON

    openshift-eng/ai-helpers

    Schema for the autodl JSON data file produced by payload-analysis for database ingestion — you must use this skill whenever generating the autodl JSON file

    120 GitHub stars~2.6k tokensUpdated 3 days ago
    Auto-check passed

Works with

Categories

Questions about Check PR CI Status

What does Check PR CI Status do?

Check CI status on a GitHub PR and detect new failures. An agent skill from openshift-eng/ai-helpers. Check PR CI Status is an agent skill from openshift-eng/ai-helpers. Check CI status on a GitHub PR and detect new failures.

When should I use Check PR CI Status?

Check PR CI Status fits situations like: monitoring a PR for CI regressions; deciding if CI failures need attention; building a review-response loop.

How do I install Check PR CI Status in Claude Code?

Run `npx skills add openshift-eng/ai-helpers --skill check-pr-ci-status -a claude-code`. Or copy the skill folder (plugins/github/skills/check-pr-ci-status in openshift-eng/ai-helpers) into .claude/skills/check-pr-ci-status in your project. Claude Code loads it when a task matches its description.

How do I install Check PR CI Status in Codex?

Run `npx skills add openshift-eng/ai-helpers --skill check-pr-ci-status -a codex`. Or copy the skill folder (plugins/github/skills/check-pr-ci-status in openshift-eng/ai-helpers) into .agents/skills/check-pr-ci-status in your project. Codex loads it when a task matches its description.

Can I use Check PR CI Status 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 openshift-eng/ai-helpers --skill check-pr-ci-status -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/check-pr-ci-status, .gemini/skills/check-pr-ci-status, .github/skills/check-pr-ci-status and .opencode/skills/check-pr-ci-status in your project.

What does Check PR CI Status need to run?

Going by SKILL.md and its folder, Check PR CI Status needs a shell for the scripts in its folder and the command-line tools its instructions call (bash, jq and gh). Our summary lists: A Bash shell.

Does Check PR CI Status access the network?

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

Is Check PR CI Status 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 Check PR CI Status use?

Check PR CI Status is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Check PR CI Status use?

About 885 tokens (SKILL.md is roughly 3.5k 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 Check PR CI Status?

Skills that share tags, products or a category with Check PR CI Status: Triage CI Flake (payloadcms/payload, 45k stars), GreptimeDB Fuzz CI Failure Investigation (GreptimeTeam/greptimedb, 6.7k stars), Fix Issue (remix-run/remix, 33k stars) and Issue To Regression Test (brunosabot/streamline-card, 269 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Check PR CI Status?

openshift-eng (a GitHub organization) maintains it in openshift-eng/ai-helpers, which has 120 GitHub stars. The repository holds 118 skills in this directory. The repository was last updated on October 6, 2026.

Source: openshift-eng/ai-helpers on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.