Skip to content

Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows

skills(running-tend): replace retired CI fix guidance (#4600)

Worktrunk Botd9257e7a0eec
diff --git a/.claude/skills/running-tend/SKILL.md b/.claude/skills/running-tend/SKILL.md
index 251efec01..c68c1df9d 100644
--- a/.claude/skills/running-tend/SKILL.md
+++ b/.claude/skills/running-tend/SKILL.md
@@ -93,12 +93,12 @@ shape is one `<session-id>.jsonl` under a single slugified directory.
## Labels
-- `automated-fix` — fix PRs from triage and ci-fix workflows
+- `automated-fix` — fix PRs from triage
- `nightly-cleanup` — nightly sweep issues and PRs
-## CI Fix: Prefer Rerun for Transient Infrastructure Failures
+## CI Failure Triage: Prefer Rerun for Transient Infrastructure Failures
-Before opening a `fix/ci-*` PR, classify the failure:
+Before opening a PR for a CI failure, classify it:
- **Transient infrastructure** (link-check timeouts, apt-get flakes, GitHub
outages, runner disk issues, codecov upload blips) — do **not** create a
@@ -121,18 +121,7 @@ failure, not a broken link:
- Only `[TIMEOUT]` is reported (not `404`/`403`/`410`).
- The URL is reachable from a local `curl`.
-When in doubt, post a comment on the failed run summarizing the diagnosis and
-wait — don't open a PR.
-
-## CI Fix: A Failed Scheduled Nightly Already Has Its Issue
-
-When a scheduled `nightly` run fails, its `create-issue-on-nightly-failure` job opens (or updates) an open `Nightly tests failed` issue labelled `ci`, and `tend-triage` diagnoses it there. That issue is the tracker for the failure. The `ci-fix:` title search in `/tend-ci-runner:ci-fix` cannot find it, so look it up by title before filing anything:
-
-```bash
-gh issue list --state open --label ci --search '"Nightly tests failed" in:title' --json number,title
-```
-
-Post a durable diagnosis on that issue, unless a comment there already covers it, instead of opening a `ci-fix:` tracking issue. A fix PR closes it with `Fixes #<n>`. A transient diagnosis still files its closed `tend-outage` tracker, since the repeat-occurrence escalation in `/tend-ci-runner:ci-fix` counts only those.
+When in doubt, post the diagnosis on the failure cause issue and wait — don't open a PR.
## Applying GitHub Suggestions
diff --git a/.claude/skills/running-tend/references/nightly-cleaner.md b/.claude/skills/running-tend/references/nightly-cleaner.md
index 09e8bb402..c2a766dc9 100644
--- a/.claude/skills/running-tend/references/nightly-cleaner.md
+++ b/.claude/skills/running-tend/references/nightly-cleaner.md
@@ -12,4 +12,4 @@ For each `.rs` file in the survey, also check:
## Repo-Wide CI Breakage
-A failure that reproduces identically on `main` and every PR (a broken system-package install in `code-coverage`, say) belongs to `tend-ci-fix`, which fires on any watched-workflow failure on `main` — the list lives in `.config/tend.yaml` under `ci-fix.watched_workflows`; a non-required job failing is enough to trigger it. A cancelled run does not trigger it, so record a breakage that shows up only as cancellations in the summary rather than assuming a handoff.
+A failure that reproduces identically on `main` and every PR (a broken system-package install in `code-coverage`, say) is reported by `tend-ci-failures` and dispatched to triage — the watched workflows are listed under `ci-failures.watched_workflows` in `.config/tend.yaml`; a non-required job failing is enough to report it. A cancelled run does not trigger it, so record a breakage that shows up only as cancellations in the summary rather than assuming a handoff.