菜单
Diagnose the live remote-access layer: SSH resolution, reachability, Tailscale, login-shell PATH, service state, package-manager locks, and remote CLI auth. Use when a named remote host or service is unreachable or unhealthy; do not use for deploy planning or ordinary local repo work.
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
Autonomously audit native local Codex session JSONL for workflow quality, latency, cost shape, tool use, recurring failures, and eval candidates. Use when the user wants scheduled harness observability or evidence-driven harness improvement; do not use for ordinary task execution, application telemetry, or full transcript export.
Verify an existing build artifact itself: metadata, complete download, checksum or size, archive integrity, unpacked contents, and source or lock provenance. Use when artifact contents or completeness must be proven; do not use to trigger builds, releases, deploys, or health checks.
Establish the current repo, instruction, branch, dirty-worktree, and linked live-object facts before non-trivial work. Use once at the start of repo work when current state or scope is unclear; do not stack it onto every later workflow phase.
Carry already-scoped code changes through verification, commit, push, PR/MR, authorized merge, and authorized cleanup. Use when the requested outcome includes delivery actions; do not use for review-only work, initial repo discovery, CI diagnosis, or deploy execution.
GitLab CLI workflows with `glab` for issues, merge requests, CI/CD, and GitLab API operations. Use when the user needs GitLab command-line automation, issue or MR triage, pipeline checks, API queries, threaded discussion replies, release checks, or work item conversion and hierarchy updates. Prefer `glab api` for reliable scripted flows, while keeping direct CLI commands and local helper scripts available for common MR and pipeline tasks.
Audit and fix repository-level agent scope and permission overreach in prompt or settings files. Use when an agent can execute unrelated commands, escape its stated task, or has contradictory allow/deny rules; do not use for general security review or ordinary application authorization bugs.
| name | remote-health |
| description | Diagnose the live remote-access layer: SSH resolution, reachability, Tailscale, login-shell PATH, service state, package-manager locks, and remote CLI auth. Use when a named remote host or service is unreachable or unhealthy; do not use for deploy planning or ordinary local repo work. |
| argument-hint | [host] |
Use the smallest live check that proves the path.
ssh -G <host> | sed -n '1,40p'
ssh -o BatchMode=yes -o ConnectTimeout=8 <host> 'hostname; whoami'
On macOS remote hosts, prefer login shell:
ssh <host> 'zsh -lc "echo $PATH; command -v node npm codex rg; codex doctor --summary --ascii"'
Do not treat ICMP ping failure as final. Check TCP or Tailscale:
ssh <jump-host> 'zsh -lc "tailscale status; tailscale netcheck"'
nc -vz <host-or-ip> 22
ssh <host> 'systemctl --failed; systemctl list-timers | sed -n "1,80p"; sudo fuser -v /var/lib/dpkg/lock-frontend 2>/dev/null || true'
If Windows OpenSSH rejects a key, inspect ACL before rotating keys:
icacls C:\Users\<username>\.ssh\<key>
Private keys should not inherit broad sandbox or group read permissions.
Answer with: reachable yes/no, failing layer, evidence command, and next smallest fix.