greening-ci

Watch a target repo's CI, surface failures the moment they land, and drive a fix-and-push loop until the run is green.

When to use

main is red. Don't move on with new work while the trunk is broken. Run /green-ci to lock onto the failing run, fix it, push, and confirm green before resuming.
Build-server matrix dispatched and might fail fast. Release builds (curl, lief, binsuite, node-smol) have one matrix slot that usually fails first. Use --mode=release to learn the failure ~5 minutes before the whole matrix finishes.
Verifying a just-pushed fix. Push a fix, then run the skill — it'll poll, confirm the run lands green, and exit. No more "did my fix actually work" guessing.

Three modes

Mode	Poll interval	Stop trigger	When to pick
`fast`	30s	Any job fails OR whole run completes	Default. `ci.yml` watching — surface the failure as soon as one job lands.
`release`	30s	Any job fails OR any job succeeds	Build-server matrices. Matrix slots run in parallel; one slot's outcome is enough to start reacting.
`cool`	120s	Whole run completes	After `release` reported a first success — just confirming the rest of the matrix. No fast polls.

The skill picks fast by default. After running release and getting a first success, the orchestrator (the agent invoking this skill) flips to cool for the remainder.