Diagnose Ci Failures

Automates the tedious work of digging through GitHub CI failures when your PR goes red. It pulls logs from failed checks using gh CLI, categorizes errors by type (formatting, clippy warnings, compilation issues, test failures), and generates a fix plan instead of immediately changing code. The workflow is thorough: verifies your PR exists, waits if checks are still running, extracts specific error locations and messages, then groups everything into actionable categories. One thing to appreciate is that it deliberately stops at the plan stage and points you to the fix-errors skill for actual remediation, which feels right when you're dealing with multiple interconnected failures and need to think through the order of fixes.

skills.sh installs: 28.6K
GitHub stars: 684
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add warpdotdev/common-skills --skill diagnose-ci-failures --agent claude-code

Installs into .claude/skills of the current project.

Files

diagnose-ci-failures

Programmatically diagnose CI failures for a PR and generate a plan to fix them.

Overview

This skill provides a deterministic workflow to check CI status for a PR, extract failure logs, analyze errors, and create a plan (not code changes) to resolve issues. The output is always a plan document that can be reviewed before execution.

Workflow

1. Verify PR exists for current branch

Get the current branch and check if a PR exists:

# Get current branch
git branch --show-current

# Check for PR
GH_PAGER=cat gh pr view <branch-name> --json number,title,url,state

If no PR exists, inform the user and offer to create one using the create-pr skill.

2. Check CI status

Fetch the status of all CI checks:

GH_PAGER=cat gh pr view <branch-name> --json statusCheckRollup

Parse the output to identify:

Completed checks vs. in-progress checks
Successful checks
Failed checks with their names and details URLs

If CI is still running, inform the user which checks have already failed or passed, highlight the checks that are still running, and suggest waiting for completion before diagnosis.