CI Status
SkillDev toolsCheck the CI pipeline status for the current branch after pushing changes. Reports pass/fail with failure details. Use this after every push to confirm your changes are truly done — CI must be green. TRIGGER when: after git push, after committing changes, when asked to check CI, or when verifying th
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 CI Status skill
What this skill tells your AI
The instructions your AI receives, as published by mifunedev/agro in .agro/skills/ci-status/SKILL.md and read by ahel’s review.
Check the current CI status for a PR and create task items for any failures.
Context-Safe Execution (MANDATORY)
CI log output MUST go to files. gh pr checks is small and OK inline.
gh run view --log-failed and artifact downloads MUST redirect:
export LOG_DIR="${LOG_DIR:-${WORKSPACE_DIR:-/tmp}/rossoctl-ci}"
mkdir -p "$LOG_DIR"
# Small output OK inline:
gh pr checks <PR-number>
# Large output MUST redirect:
gh run view <run-id> --log-failed > $LOG_DIR/ci-run-<run-id>.log 2>&1; echo "EXIT:$?"
# Analyze in subagent: Task(subagent_type='Explore') with Grep on the log file
When to Use
- After pushing changes to a PR
- When asked "what's the CI status?"
- Before deciding whether to push more changes
- After CI completes to summarize results
Workflow
1. Get PR Status
gh pr checks <PR-number>
2. Summarize Results
Present as a table:
| Check | Status | Details |
|---|---|---|
| CodeQL | pass/fail | N alerts |
| Deploy & Test (Kind) | pass/fail | N passed, N failed |
| E2E HyperShift | pass/fail/pending | N passed, N failed |
| Build | pass | - |
| Linting | pass | - |
3. For Failures - Get Details
# Kind CI test results
gh run download <run-id> -n e2e-test-results -D /tmp/ci-results
grep -oE 'errors="[0-9]+" failures="[0-9]+" skipped="[0-9]+" tests="[0-9]+"' /tmp/ci-results/e2e-results.xml
# Failed test names
grep '<failure' /tmp/ci-results/e2e-results.xml
# HyperShift logs
gh run view <run-id> --log-failed | tail -30
# CodeQL alerts
gh api repos/<owner>/<repo>/check-runs/<check-id>/annotations --jq '.[] | {path, line: .start_line, message: .message[:100]}'
4. Create Tasks for Failures
For each distinct failure, create a task:
TaskCreate: "<worktree> | <PR> | <topic> | RCA | <failure description>"
Task Tracking
On invocation:
- TaskList - check for existing CI-related tasks
- TaskCreate for each new failure found
- Link to plan doc if failures relate to planned work
- Metadata:
plan: "ad-hoc",runner: "main-session"
Troubleshooting
CI check not appearing
- Push may not have triggered the workflow
- Check workflow trigger conditions in
.github/workflows/ - HyperShift E2E requires manual
/testcomment
Stale results
- CI runs on the commit at push time, not current HEAD
- Check
headShamatches expected commit
Related Skills
ci:monitoring- Wait for and monitor running CI jobsrca:ci- Root cause analysis of CI failurestdd:ci- TDD iteration using CI as test environment
Signals
- GitHub stars
- 38
- Forks
- 3
- Last commit
- Sep 2026
Others that do the same job
Advanced
- Catalog kind
- skill
- Gateway key
ci-status- Source
- github.com/mifunedev/agro