ci-diagnose

스타1

포크0

업데이트2026년 7월 16일 06:21

Evaluate the CI/CD pipeline on the PR, check for failures, and fix any issues.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

출처

andrewgari

andrewgari/starbunk-rs

다운로드

CI/CD Diagnose Workflow

When triggered, perform the following steps in order:

Check Pipeline Status: Fetch the latest CI pipeline status for the current branch or PR. You can use gh pr checks or the GitHub MCP.
Fetch Logs: If the pipeline failed, extract the error logs from the failed jobs. Do not guess the failure reason without reading the logs.
Analyze: Identify the root cause of the failure (e.g., linting error, failing test, build error, Docker issue).
Fix: Make the necessary edits to the codebase to resolve the issue. If it's a test failure, ensure the tests pass locally before proceeding.
Commit and Push: Stage, commit, and push the fix (git push).
Re-check: Verify the pipeline starts running again and monitor it until it passes, or instruct the user to check the pipeline status once it's triggered.

이 저장소의 다른 Skills

같은 저장소

Analyzes the current branch/PR and adds comprehensive, well-formatted structured logging and spans for observability.

Review PR comments, categorize them into critical/nitpicks, fix user-selected ones, and close resolved comments.

Create a PR using the current branch. Generates a PR description, commits changes, and pushes.

Mandatory rules for general git use in this repository. Follow these constraints before starting work, committing, or pushing.

Feature developer and task runner. Start a new task on a fresh branch, orchestrate worktrees, do the implementation work, and open a PR when done.

Worktree lifecycle protocol — context switching, creating, and cleaning up git worktrees for starbunk-rs.

name	ci-diagnose
description	Evaluate the CI/CD pipeline on the PR, check for failures, and fix any issues.

When triggered, perform the following steps in order:

Check Pipeline Status: Fetch the latest CI pipeline status for the current branch or PR. You can use gh pr checks or the GitHub MCP.
Fetch Logs: If the pipeline failed, extract the error logs from the failed jobs. Do not guess the failure reason without reading the logs.
Analyze: Identify the root cause of the failure (e.g., linting error, failing test, build error, Docker issue).
Fix: Make the necessary edits to the codebase to resolve the issue. If it's a test failure, ensure the tests pass locally before proceeding.
Commit and Push: Stage, commit, and push the fix (git push).
Re-check: Verify the pipeline starts running again and monitor it until it passes, or instruct the user to check the pipeline status once it's triggered.