메뉴
Commit, push, then monitor Vercel deployment and GitHub Actions until green. Auto-fixes failures and retries. Use when committing code that needs deployment verification, or when you want to ship and verify in one command.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | commit-and-monitor |
| description | Commit, push, then monitor Vercel deployment and GitHub Actions until green. Auto-fixes failures and retries. Use when committing code that needs deployment verification, or when you want to ship and verify in one command. |
| argument-hint | [commit message] |
| allowed-tools | Bash(git :*), Bash(gh :*), Bash(vercel :*), Bash(npm :*), Bash(pnpm :*), Bash(bun :*), Bash(npx :*), Bash(sleep :*) |
| disable-model-invocation | true |
| allow_implicit_invocation | false |
Commit, push, then watch Vercel + GitHub Actions until everything is green. Fix and retry if anything fails.
git status --shortgit diff --cached --statgit diff --statgit log --oneline -5git branch --show-currentAnalyze git state
git add .$ARGUMENTS provided, use it as commit messagetype(scope): brief description (under 72 chars, imperative mood)Commit: git commit -m "message"
Push: git push (set upstream if needed with git push -u origin $(git branch --show-current))
Get latest deployment for current branch:
vercel list --limit 5 2>/dev/null
Wait for deployment to complete using vercel inspect --wait:
vercel inspect <deployment-url> --wait --timeout 10m
This blocks until the deployment reaches Ready or Error state. No polling needed.
On build error: Fetch logs with vercel inspect <url> --logs, analyze the error, fix locally, then go back to Phase 1.
On success: Note the preview URL and continue to Phase 3.
Check for running workflows:
gh run list --branch $(git branch --show-current) --limit 5
Watch the latest run:
gh run watch <run-id> --exit-status
This blocks until the run completes. If it exits non-zero, the run failed.
On failure: Get logs with gh run view <run-id> --log-failed, analyze error, fix locally, then go back to Phase 1.
On success: Continue to Phase 4.
gh pr view --json state,url,checks 2>/dev/null@ts-ignore, eslint-disable, skipping tests, --no-verifyfix(ci): resolve build error in Xvercel inspect --wait --timeout 10m to block until deployment completesExpert guidance for creating, building, and using Claude Code agents and the Task tool. Use when working with agents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.
Complete SaaS ideation to implementation workflow - from idea discovery to task breakdown
Run structured APEX implementation (Analyze, Plan, Execute, eXamine) with parallel agents, tests, adversarial review, and proof-backed verification. Use for features, bug fixes, or code changes that need disciplined execution and real-flow evidence.
Deep iterative research using progressive flow psychology (diverge-analyze-converge-execute) with parallel agents, skeptical analysis, and multi-perspective synthesis. Use for thorough topic exploration, decision-making research, or when you need battle-tested conclusions.
Automated CI/CD pipeline fixer - watches CI, fixes errors locally, commits, and loops until green. Use when CI is failing and you want to automatically fix and verify changes.
Improve unclear UX copy, error messages, microcopy, labels, and instructions. Makes interfaces easier to understand and use.