菜单
Read, search, create, and update GitLab merge requests, pipelines, issues, and releases via the glab CLI. Use when viewing or creating an MR, checking CI pipeline status, reading or filing issues, or managing releases on GitLab.
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
| name | gitlab |
| description | Read, search, create, and update GitLab merge requests, pipelines, issues, and releases via the glab CLI. Use when viewing or creating an MR, checking CI pipeline status, reading or filing issues, or managing releases on GitLab. |
| version | 1.0.0 |
| tags | ["gitlab","glab","merge-requests","pipelines","ci","issues"] |
| metadata | {"related-skills":"jira"} |
Read and write GitLab using the glab CLI. No REST API
tokens or browser automation — glab reuses its own
authenticated config.
glab installed (via nix devPackages).glab auth login completed once by the user. If a command
reports "not authenticated", stop and ask the user to run
! glab auth login — never run it yourself.glab resolves the host and project from the git
remote.glab resolves the target host itself, in order:
GITLAB_HOST environment variable (fallback for
out-of-repo use).glab multi-host config in ~/.config/glab-cli/config.yml.Never hardcode a host — this repo is public. If host resolution fails, report it and ask which host/repo to target.
Accepts a command plus arguments. If no command is given, infer from context or ask. If a command needs an MR, issue, or pipeline reference and none is given, ask.
| Command | Reference | Load When |
|---|---|---|
| mr | references/merge-requests.md | Any merge request operation |
| ci | references/pipelines.md | Pipeline/job status, logs, retry |
| issue | references/issues.md | Issue read/search/create/update |
| repo | references/repo-releases.md | Clone, browse, release, variables |
| setup | references/setup.md | Auth or host troubleshooting |
Drafting an MR description: see references/templates.md.
create, merge, approve, close, and variable set
change shared state visible to others. Always show the exact
glab command and get explicit user confirmation before
running a state-changing command. Never merge or push
without instruction. No retry loops.
Report clearly and stop.
| Condition | Action |
|---|---|
| Not authenticated | Ask user to run glab auth login |
| Host not resolved | Report; ask which host/repo |
| Not inside a repo | Ask for repo, or use -R host/group/project |
| MR / issue / pipeline 404 | Report stale or wrong reference |
| Permission denied | Report the missing scope/role |
glab non-zero exit | Print stderr verbatim, stop |
| No results (list/search) | Report empty result set |
Shape answers so they are immediately actionable instead of long. Use on any response that would otherwise run long — multi-step tasks, explanations, plans, reviews with many findings, or answers that hand back commands, paths, or snippets to run. Leads with the next action, numbers steps, restates progress, caps lists, and gives concrete time estimates. Complements caveman (which handles tone); this handles shape.
Senior software architect for system design, ADRs, microservices evaluation, technology trade-off analysis. Use when designing system architecture, evaluating patterns, creating ADRs, analyzing technology choices, or planning migrations.
Go CLI development with Cobra command hierarchy, Bubbletea interactive TUI, Lipgloss terminal styling, Charmbracelet ecosystem (Bubbles, Huh forms, Glamour markdown rendering), and shell completions. Use when building CLI tools, adding subcommands, creating interactive TUI, styling terminal output, or implementing shell completions.
Cloud architecture design, migration, optimization, and disaster recovery across AWS and Azure. Use when designing VPCs/VNets, IAM/RBAC, compute/storage architectures, cost optimization, multi-cloud patterns, or planning migrations. Both Terraform and CLI approaches.
Datadog monitoring strategy, alert design, tagging governance, dashboard patterns, SLO strategy, log management, cost optimization, and cross-pillar correlation workflows. Use when making architectural decisions about what to monitor, how to alert, how to tag, or how to structure Datadog for a service or platform. Delegates execution to pup CLI and infrastructure-as-code to sre-engineer.
Kubernetes workload management, Helm chart development, cluster troubleshooting, custom operators, configuration management, and multi-cluster administration. Use when deploying workloads, writing Helm charts, debugging pods, creating operators, managing ConfigMaps/Secrets/RBAC, or working with multi-cluster setups.