Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows
fix(ci): restore CI poll loop with tradeoff note in running-in-ci skill (#1314)
worktrunk-botb1ee4dae4eb7
diff --git a/.claude/skills/running-in-ci/SKILL.md b/.claude/skills/running-in-ci/SKILL.mdindex b86f01b3a..8e4be8cb7 100644--- a/.claude/skills/running-in-ci/SKILL.md+++ b/.claude/skills/running-in-ci/SKILL.md@@ -46,16 +46,23 @@ After pushing changes to a PR branch, you **must** wait for CI before saying"done" or reporting completion. A push without green CI is not finished work.1. Push your changes-2. Wait for CI completion with `gh run watch` or poll `gh pr checks <number>`-3. If CI fails, diagnose with `gh run view <run-id> --log-failed`-4. Fix issues, commit, push, and repeat from step 2-5. Only after all checks pass, report completion+2. Run `gh pr checks <number>` once+3. If all checks passed, report completion+4. If checks are still running, poll with `gh pr checks <number>` every 60+ seconds until all checks complete (this may take up to 10 minutes — that's an+ acceptable tradeoff to ensure the bot reports accurate CI status)+5. If CI fails, diagnose with `gh run view <run-id> --log-failed`, fix issues,+ commit, push, and repeat from step 2+6. Only after all checks pass, report completion**Never** post a "done" or "fixed" comment before CI passes. Local tests aloneare not sufficient — CI runs on Linux, Windows, and macOS. If you reportcompletion and CI later fails, the user has to come back and ask you to fix itagain.+Avoid `gh run watch` — it can hang indefinitely. Use the poll loop above+instead, which has a natural bound on CI completion time.+## Replying to CommentsPrefer replying in context rather than creating a new top-level comment: