release-monitor-ci

SkillMonitoring & ops

Monitor CI on main and iterate until it is successful

Available today. Use it from your connected AI after setup.

No other account needed.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the release-monitor-ci skill

What this skill tells your AI

The instructions your AI receives, as published by debuglebowski/slayzone in .agents/skills/release-monitor-ci/SKILL.md and read by ahel’s review.

Monitor the Release workflow and iterate until it succeeds. User context: $ARGUMENTS

Find the latest Release run.
- Run gh run list --workflow=release.yml --limit 1 to find the latest run.
- If no run exists, tell the user and stop.
Wait for the run to complete.
- Run gh run watch <run-id> --exit-status to stream logs and wait.
- If it succeeds, report success and stop.
On failure, diagnose.
- Run gh run view <run-id> --log-failed to get failed job logs.
- Identify the root cause from the logs.
Fix the issue.
- Make the minimal code/config change to fix the failure.
- Commit with a conventional commit message (e.g. fix(ci): ...).
- Push to main.
Loop.
- Wait for the new Release run to appear (gh run list --workflow=release.yml --limit 1).
- Go back to step 2.
- Repeat until the Release workflow is green or you've attempted 10 iterations.
If stuck after 10 iterations, report what's failing and ask for guidance.

Only fix CI-related failures — don't refactor unrelated code.
Each fix should be its own commit.
Never force-push or rewrite history.
Tags may be freely managed (deleted, recreated, moved) as needed to re-trigger the Release workflow.
If a failure looks like a flaky test (passes on retry), re-run with gh run rerun <run-id> --failed instead of changing code.

Advanced