monitor-ci-results

スター678

フォーク705

更新日2026年6月14日 03:26

Monitor remote CI results for a PR and autonomously trigger log analysis upon failures

インストール

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。

Manusで実行

ソース

bazel-contrib

bazel-contrib/rules_python

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

✨ Autonomous Failure Orchestration

When any CI job completes with errors or returns a non-zero exit code:

It automatically downloads the raw CI log file to ci_logs/.
It launches an independent background analyzer script (analyze_ci_failure.py).
It authors a beautifully structured Markdown suggested plan for how to fix the failure.
It natively dispatches a high-priority notification message back to your active agent conversation (containing the downloaded log path and fix plan) using agentapi send-message!

Example Invocation

./scripts/monitor_remote_ci.py 3812 "0be435bd-96aa-4e1b-9c6f-727b31e80fa0" &

このリポジトリの他の Skills

同じリポジトリ

review-pr

bazel-contrib/rules_python

Perform a read-only code review on a pull request.

2026-07-12678

rule-creator

bazel-contrib/rules_python

Create and format agent rules with proper front matter in the workspace

2026-06-28678

analyze-ci-failure

bazel-contrib/rules_python

Download and analyze a CI failure log to construct an actionable suggested fix plan and report back

2026-06-14678

buildkite-get-results

bazel-contrib/rules_python

Gets buildkite build results

2026-06-14678

buildkite-retry-job

bazel-contrib/rules_python

Retry a failed build kite job

2026-06-14678

name	monitor-ci-results
description	Monitor remote CI results for a PR and autonomously trigger log analysis upon failures

When the user requests to monitor remote CI results or watch a pull request, invoke scripts/monitor_remote_ci.py <pr_number> <your_conversation_id>.

This long-running monitoring service runs in the background and continuously polls both GitHub PR checks and Buildkite workflow executions.

✨ Autonomous Failure Orchestration

When any CI job completes with errors or returns a non-zero exit code:

It automatically downloads the raw CI log file to ci_logs/.
It launches an independent background analyzer script (analyze_ci_failure.py).
It authors a beautifully structured Markdown suggested plan for how to fix the failure.
It natively dispatches a high-priority notification message back to your active agent conversation (containing the downloaded log path and fix plan) using agentapi send-message!

Example Invocation

./scripts/monitor_remote_ci.py 3812 "0be435bd-96aa-4e1b-9c6f-727b31e80fa0" &