← ClaudeAtlas

keel-ci-checklisted

Check the latest CI run's status; on failure, locate the failing job/step, diagnose the root cause, and propose one fix — never auto-apply.
berkayturanci/voicebridge · ★ 9 · AI & Automation · score 62
Install: claude install-skill berkayturanci/voicebridge
# keel-ci-check Use this skill when the user asks to run the keel command `ci-check` (e.g. `keel ci-check ...`, `ci-check <args>`, or `/keel:ci-check`). It reads every project value from `.keel/project.yaml` via the `keel` CLI. # /keel:ci-check ## Live progress — stamp this run (required) So this run shows live on `keel-visual`'s board, record it with `keel activity` **as you go**. This command's phases are: `poll` → `report`. Pick one stable `--run-id` for the whole run (e.g. `ci-check-<issue-or-pr>`): - **Right now, before the work below**, stamp the first phase: `keel activity .keel/project.yaml --root . --write --command ci-check --run-id "$RUN" --phase poll` - Re-run with the next `--phase` (`report`, …) **as you advance** through the flow. - At the end: `keel activity .keel/project.yaml --root . --run-id "$RUN" --done` Treat this like any other contractual step — do not skip it. The one allowed exception is a core too old to ship `keel activity` (keel < 1.6.0): then skip it silently and never block the command. ## Command step evidence Every numbered step in this command is contractual. Complete the step, record the evidence it asks for, or explicitly mark it `N/A — <reason>` before moving on. If a step has an external side effect such as a GitHub comment, issue, review, report, branch, or PR, the side effect must be posted or written through the selected transport and cited in the final summary. Never silently skip a step because the runtime, agent, or prompt