菜单
Executes a Linear issue end-to-end — reads the issue, creates a branch, implements the work, commits, opens a PR, and returns to main. Use when the user provides a Linear issue identifier and wants it implemented.
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。
Cuts a new release of ai-sdk — creates a Linear issue, branches, bumps version, updates changelog, runs checks, commits, opens a PR, and returns to main. Merging the PR triggers CI to auto-tag. Use when the user wants to release a new version of the ai_sdk gem.
References Semaphore's sem-ai CLI command set, output formats, safety defaults, and legacy sem replacement patterns. Use when exact sem-ai commands or flags are needed before inspecting or mutating Semaphore state.
Debugs and triages Semaphore CI pipelines and jobs with sem-ai first, falling back to legacy sem only for interactive attach/debug shells. Use when CI is failing, flaky, stuck, queued, or needs logs, reruns, stops, or deployment-state inspection.
Find an unreserved staging namespace and promote a Semaphore pipeline into it. Use when a user asks to pick a free `revNN`/`qaNN` server, trigger `Deploy to EKS staging`, or validate that promotion/deploy completed.
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
Promote an Amadeus PR to the shared `data` staging namespace using Semaphore `Deploy to Staging`, then verify the SLSA-backed artifact flow, deployed image, and live log contract through Kubernetes.
| name | ship |
| description | Executes a Linear issue end-to-end — reads the issue, creates a branch, implements the work, commits, opens a PR, and returns to main. Use when the user provides a Linear issue identifier and wants it implemented. |
Takes a Linear issue identifier, implements it, and ships a PR — all in one shot.
/ship ML-123 or "ship ML-123"A Linear issue identifier (e.g. ML-123). Passed as the argument.
Use the mcp__linear-server__get_issue tool with the provided issue identifier to fetch:
git checkout main
git pull origin main
git checkout -b <branch-name-from-linear>
Use the branchName field from the Linear issue response.
Read the issue description carefully. It contains the requirements.
This is the core work — take as much latitude as needed to do it well.
Stage and commit all changes. The commit message format is:
[<ISSUE-ID>] <issue title>
Extract both from the branch name: the issue ID is the prefix (e.g. ML-123 from feature/ml-123-add-retry-logic), and the title is the rest, un-slugified.
Example: branch feature/ml-496-add-to-langfuse-method → commit message [ML-496] Add to langfuse method
git add <specific-files>
git commit -m "[<ISSUE-ID>] <issue title>"
git push -u origin <branch-name>
Create the PR with the same title as the commit.
Before generating the body, check if the repo has a pull request template at any of these paths:
.github/pull_request_template.md.github/PULL_REQUEST_TEMPLATE.mddocs/pull_request_template.mdPULL_REQUEST_TEMPLATE.mdIf a template exists, read it and use its structure as the PR body — fill in each section with the relevant details from the issue and implementation.
Before creating the PR, select the most appropriate GitHub label by running gh label list and matching against the nature of the change.
git checkout main
Use mcp__linear-server__update_issue to move the issue to "In Review" state (or equivalent review state for the team).
[ISSUE-ID] Titlemain when done, even if a step failsgit add .