菜单
Background CI monitor for a PR. Auto-run when: PostToolUse detects a PR was just created (suggests it with PR number), user asks to watch CI, or after pushing to a branch with an open PR. Takes PR number as argument. Invoke proactively without asking.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Run the health monitor and report results. Auto-run when: session-context shows health is degraded or failed, after infrastructure changes (docker, systemd), when a service appears unreachable, or user asks about system health. Invoke proactively without asking.
Audit installed flatpak apps and find native alternatives. Auto-run when: storage-audit reveals large flatpak usage, operator mentions app performance issues related to sandboxing, or user asks about flatpaks. Invoke proactively without asking.
Audit branches across all repos and clean up. Auto-run when: session-context reports >3 non-main branches across repos, no-stale-branches hook blocks a branch create, after merging PRs, or user asks about branch cleanup. Invoke proactively without asking.
Scan for and resolve merge conflict markers. Auto-run when: conflict-marker-scan PostToolUse hook fires a warning, git merge/rebase/cherry-pick output shows CONFLICT (PostToolUse suggests it), or user asks to fix conflicts. Invoke proactively without asking.
Trace consent provenance. Auto-run when: work touches files containing personal data (profiles/, agents processing person names), after adding new data sources or storage, or user asks about consent or data protection. Invoke proactively without asking.
Full service triage. Auto-run when: a service is unreachable (connection refused, timeout), systemctl shows a failed unit (PostToolUse suggests it), session-context reports failed units, or user mentions something is broken/down/crashed. Takes optional service name as argument. Invoke proactively without asking.
| name | ci-watch |
| description | Background CI monitor for a PR. Auto-run when: PostToolUse detects a PR was just created (suggests it with PR number), user asks to watch CI, or after pushing to a branch with an open PR. Takes PR number as argument. Invoke proactively without asking. |
Monitor CI checks for a PR until they complete. Argument: PR number (e.g., /ci-watch 42).
Use REST/core endpoints for PR metadata and checks. Avoid GitHub CLI PR-check watchers and PR status-rollup JSON fields; those paths are GraphQL-backed and can exhaust the shared GraphQL quota.
Step 1 — Check current status:
repo="${GH_REPO:-hapax-systems/hapax-council}"
sha="$(gh api --method GET -H 'Accept: application/vnd.github+json' "repos/$repo/pulls/{args}" --jq '.head.sha')"
gh api --paginate --method GET -H 'Accept: application/vnd.github+json' "repos/$repo/commits/$sha/check-runs?per_page=100" --jq '.check_runs[] | "\(.name): \(.status) \(.conclusion // "")"'
gh api --method GET -H 'Accept: application/vnd.github+json' "repos/$repo/commits/$sha/status" --jq '.statuses[] | "\(.context): \(.state)"'
Step 2 — If checks are still running, poll sparingly:
Re-run the REST commands from Step 1 at most once per minute. Stop after 10 polls and report that CI is still pending instead of tightening the loop.
Report after each poll whether checks are still running.
Step 3 — On completion:
If all checks pass: report green and suggest gh pr merge {args} --squash --delete-branch.
If any check fails: fetch the failed job logs:
repo="${GH_REPO:-hapax-systems/hapax-council}"
branch="$(gh api --method GET -H 'Accept: application/vnd.github+json' "repos/$repo/pulls/{args}" --jq '.head.ref')"
gh run list --repo "$repo" --branch "$branch" --limit 3 --json databaseId,conclusion,name -q '.[] | select(.conclusion == "failure") | .databaseId' | head -1 | xargs -I{} gh run view --repo "$repo" {} --log-failed 2>/dev/null | tail -30
Summarize the failure and suggest a fix.