ワンクリックで
push-and-verify
Push to remote and wait for CI to pass. If CI fails, read logs, fix bugs, and re-push. Repeat until green.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Push to remote and wait for CI to pass. If CI fails, read logs, fix bugs, and re-push. Repeat until green.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Debug frontend vanilla JS issues - console errors, rendering bugs, SPA navigation, WebSocket
Automates the process of setting up the first admin user or adding new admins via the bootstrap endpoint. Includes a Python script for easy execution.
Use when building or debugging LangGraph multi-agent systems - eval-first execution, task decomposition, model routing by complexity, and cost discipline
Use when AI agent modifies API routes or backend logic - catch systematic blind spots where the same model writes and reviews code
Use when making or recording significant architectural decisions - capture context, alternatives, and rationale as structured ADRs
Use when you have a written implementation plan to execute with review checkpoints between tasks
| name | push-and-verify |
| description | Push to remote and wait for CI to pass. If CI fails, read logs, fix bugs, and re-push. Repeat until green. |
This skill MUST be followed after every git push. A push is NOT complete until all CI workflows pass.
git push origin <branch>
sleep 10
Poll every 30 seconds until the run completes (timeout 10 minutes):
# Get the latest run ID for the push
gh run list --limit 3 --json databaseId,headBranch,name,status,conclusion
# Check status of a specific run
gh run view <RUN_ID> --json status,conclusion
Report success to user with workflow names and conclusion.
Done.
Immediately fetch the failed logs:
gh run view <RUN_ID> --log-failed
Analyze the logs and classify the failure:
| Failure Type | Action |
|---|---|
| Lint (ruff) | Fix the reported file:line, run ruff check . locally to verify, commit, push |
| Test failure | Read the test output, reproduce locally with pytest <test_file>::<test_func> -v, fix, push |
| Install failure | Check requirements.txt or workflow pip install step, fix, push |
| Workflow syntax | Fix the .github/workflows/*.yml file, push |
| Flaky / infra | Re-run the failed job: gh run rerun <RUN_ID> --failed |
Repeat the push → poll → verify cycle until ALL workflows pass.
--log-failed not --log to reduce noise — only read what failed| Workflow | Trigger | What to check |
|---|---|---|
CI (ci.yml) | push/PR to main | lint + test + validate-json |
Test Suite (test-suite.yml) | push/PR to main | python-tests + e2e-tests |
E2E Tests (e2e.yml) | push to main | playwright e2e |
Dependency Audit (dependency-weekly-audit.yml) | weekly cron | lockfile freshness (skip for daily pushes) |
# List latest runs
gh run list --limit 5
# View specific run details
gh run view <RUN_ID>
# Get failed logs only
gh run view <RUN_ID> --log-failed
# Re-run failed jobs
gh run rerun <RUN_ID> --failed
# Watch a run in real-time
gh run watch <RUN_ID>