Back to guide/Developer Tools

CI Pipeline Debugger

Claude Code is uniquely powerful here — it can read CI configs, check git history, run tests locally, and make fixes. In Cursor, paste the error output and use @file to reference the CI config. The categorization framework prevents treating symptoms.

cursor-vs-claude-codeci_systemerror_outputconfig_file_path
Edit View
Prompt
The CI pipeline is failing. Help me diagnose and fix it.

CI system: {{ci_system}}
Error output:
{{error_output}}

Pipeline config file: {{config_file_path}}

Investigation steps:
1. Read the CI config file and understand the pipeline stages
2. Parse the error output to identify the failing step and root cause
3. Check if the failure is:
   - A code issue (test failure, build error, lint error)
   - An environment issue (missing env var, wrong Node version, dependency conflict)
   - A flaky test (check if this test has failed before in git history)
   - A config issue (changed pipeline config, new required step)
4. Propose a fix:
   - If code issue: fix the code and explain what broke
   - If environment issue: update the CI config with the correct values
   - If flaky test: fix the test or add retry logic with a TODO to investigate root cause
   - If config issue: update the config and note what changed

Also check: Are there any deprecated actions/orbs/steps that should be updated? Any security warnings in the output?

Variables to customize

{{ci_system}}{{error_output}}{{config_file_path}}

Why this prompt works

Claude Code is uniquely powerful here — it can read CI configs, check git history, run tests locally, and make fixes. In Cursor, paste the error output and use @file to reference the CI config. The categorization framework prevents treating symptoms.

Save this prompt to your library

Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.

Related prompts

Code Review Assistant

Get thorough code reviews with actionable feedback tailored to your language, framework, and standards.

Context-Aware Code Completion

Providing the surrounding code and project context lets the model match existing patterns exactly. The constraint against modifying existing code prevents unwanted side effects.

Inline Code Suggestion

Constraining suggestions to match existing style and scope produces insertions that feel native to the codebase. The 'no explanation' rule mimics real inline completion behavior.

Code Explanation

The audience level parameter adjusts complexity automatically. Requiring a usage example ensures the explanation is practical, not just theoretical.