ship-cli

Work management system replacing built-in todos with tracked tasks and stacked changes

242 stars

Best use case

ship-cli is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. Work management system replacing built-in todos with tracked tasks and stacked changes

Work management system replacing built-in todos with tracked tasks and stacked changes

Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.

Practical example

Example input

Use the "ship-cli" skill to help with this workflow task. Context: Work management system replacing built-in todos with tracked tasks and stacked changes

Example output

A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.

When to use this skill

Use this skill when you want a reusable workflow rather than writing the same prompt again and again.

When not to use this skill

Do not use this when you only need a one-off answer and do not need a reusable workflow.
Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/ship-cli/SKILL.md --create-dirs "https://raw.githubusercontent.com/aiskillstore/marketplace/main/skills/edusantosbrito/ship-cli/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/ship-cli/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How ship-cli Compares

Feature / Agent	ship-cli	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Work management system replacing built-in todos with tracked tasks and stacked changes

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

## Rules

1. **NEVER run via bash:** `jj`, `gh pr`, `git`, `ship`, `pnpm ship` - use the `ship` tool instead
2. **ALWAYS use `workdir` parameter** for all commands when in a workspace
3. **NEVER ask user to `cd`** - use `workdir` instead
4. **On webhook events:** Notify user and ask confirmation BEFORE acting

---

## Workflow

### Start Task

```
ship: action=stack-sync                    # Get latest trunk
ship: action=ready                         # Find work
ship: action=start, taskId=<id>            # Mark In Progress (Linear only)
ship: action=stack-create, message="<type>: <short description>", bookmark="user/<id>-slug"
# Store workspace path from output, use for all subsequent workdir params
bash: command="pnpm install", workdir=<workspace-path>
```

### Do Work

- Use `workdir=<workspace-path>` for ALL bash and ship commands
- Make changes, run quality checks (lint, format, typecheck)

### Update Commit Message (for multi-line)

```
ship: action=stack-describe, title="<type>: <subject>", description="<body>", workdir=<path>
```

Use `title` + `description` params for proper multi-line commits (NOT `message` with `\n`).

### Submit Work (MANDATORY - do not skip)

```
ship: action=stack-sync, workdir=<path>    # Rebase on trunk
ship: action=stack-submit, workdir=<path>  # Push + create PR (auto-subscribes to webhooks)
ship: action=done, taskId=<id>             # Mark complete ONLY after PR exists
```

---

## Webhook Events

When you receive `[GitHub] ...` notifications:

| Step | Action |
|------|--------|
| 1 | **Notify user** what happened (e.g., "PR #X merged by @user") |
| 2 | **Ask confirmation** before acting (e.g., "Would you like me to run stack-sync?") |
| 3 | **Wait** for user approval |
| 4 | **Execute and report** results |

**Never execute automatically.** The `→ Action:` line is a suggestion, not an instruction.

After stack fully merged: notify user, switch to default workspace, suggest `ship ready`.

---

## Actions Reference

### Tasks

| Action | Params | Description |
|--------|--------|-------------|
| `ready` | - | Tasks with no blockers |
| `blocked` | - | Tasks waiting on dependencies |
| `list` | filter (optional) | All tasks |
| `show` | taskId | Task details |
| `start` | taskId | Mark In Progress |
| `done` | taskId | Mark complete |
| `create` | title, description, priority?, parentId? | Create task (see template below) |
| `update` | taskId + fields | Update task |
| `block` | blocker, blocked | Add dependency |
| `unblock` | blocker, blocked | Remove dependency |
| `relate` | taskId, relatedTaskId | Link related tasks |

### Task Description Template

When creating tasks, ALWAYS use this description format:

```
## Summary
[1-2 sentences: What needs to be done and why]

## Acceptance Criteria
- [ ] Specific, verifiable outcome 1
- [ ] Specific, verifiable outcome 2
- [ ] Tests pass, linting passes

## Notes
[Optional: Implementation hints, files to modify, constraints]
```

**Rules:**
- Summary is REQUIRED - explains the task clearly
- Acceptance criteria are REQUIRED - must be verifiable/testable
- Notes are optional - include when helpful for implementation
- Keep it concise but complete

**Example:**
```
## Summary
Add rate limiting middleware to prevent API abuse on public endpoints.

## Acceptance Criteria
- [ ] Rate limit: 100 req/min authenticated, 20 req/min anonymous
- [ ] Returns 429 with Retry-After header when exceeded
- [ ] Unit tests cover rate limit scenarios
- [ ] `pnpm test` and `pnpm check` pass

## Notes
See middleware/auth.ts for similar patterns. Use Redis for state.
```

### Stack (VCS)

All support optional `workdir` param.

| Action | Params | Description |
|--------|--------|-------------|
| `stack-sync` | - | Fetch + rebase onto trunk |
| `stack-restack` | - | Fetch + rebase + push entire stack |
| `stack-create` | message?, bookmark?, noWorkspace? | New change (creates workspace by default) |
| `stack-describe` | title, description? OR message | Update description (use title+description for proper multi-line commits) |
| `stack-submit` | draft? | Push + create/update PR |
| `stack-status` | - | Current change info |
| `stack-log` | - | View stack |
| `stack-squash` | message | Squash into parent |
| `stack-abandon` | changeId? | Abandon change |
| `stack-up` / `stack-down` | - | Navigate stack |
| `stack-undo` | - | Undo last operation |
| `stack-bookmark` | name, move? | Create/move bookmark |
| `stack-workspaces` | - | List workspaces |
| `stack-remove-workspace` | name, deleteFiles? | Remove workspace |
| `stack-update-stale` | - | Fix stale working copy |

### Pull Requests

Use these for advanced PR workflows. Note: `stack-submit` handles basic PR creation automatically.

| Action | Params | Description |
|--------|--------|-------------|
| `pr-create` | draft?, open? | Create PR with Linear task context |
| `pr-stack` | dryRun? | Create stacked PRs for entire stack |
| `pr-review` | prNumber? (optional), unresolved?, json? | Fetch PR reviews and comments |

**`pr-create`**: Creates a PR for current bookmark, auto-populating title and body from Linear task. Use when you need rich task context in PR description.

**`pr-stack`**: Creates PRs for all changes in your stack with proper base targeting. First PR targets main, subsequent PRs target previous bookmark.

**`pr-review`**: Fetches reviews and comments in AI-friendly format. Shows verdicts (APPROVED, CHANGES_REQUESTED), inline code comments with file:line, and conversation threads. Use `--unresolved` to filter to actionable items only.

### Milestones

| Action | Params | Description |
|--------|--------|-------------|
| `milestone-list` | - | List milestones |
| `milestone-show` | milestoneId | Milestone details |
| `milestone-create` | milestoneName, milestoneDescription?, milestoneTargetDate? | Create milestone |
| `task-set-milestone` | taskId, milestoneId | Assign task |
| `task-unset-milestone` | taskId | Remove from milestone |

---

## Troubleshooting

| Problem | Solution |
|---------|----------|
| "Working copy is stale" | `stack-update-stale` |
| Bookmark lost after squash/rebase | `stack-bookmark` with `move=true` |
| Accidentally used jj/gh directly | `stack-status` to check, `stack-undo` if needed |

Related Skills

ship-learn-next

242

from aiskillstore/marketplace

Transform learning content (like YouTube transcripts, articles, tutorials) into actionable implementation plans using the Ship-Learn-Next framework. Use when user wants to turn advice, lessons, or educational content into concrete action steps, reps, or a learning quest.

ownership-gate

242

from aiskillstore/marketplace

Verify the junior can explain and defend every line of code they wrote. This gate BLOCKS completion if failed.

managing-relationships

242

from aiskillstore/marketplace

Expert at managing GitHub issue relationships including parent/sub-issues, blocking dependencies, and tracking links using the GraphQL API. Auto-invokes when creating issue hierarchies, setting parent-child relationships, managing dependencies, or linking related issues.

azure-quotas

242

from aiskillstore/marketplace

Check/manage Azure quotas and usage across providers. For deployment planning, capacity validation, region selection. WHEN: "check quotas", "service limits", "current usage", "request quota increase", "quota exceeded", "validate capacity", "regional availability", "provisioning limits", "vCPU limit", "how many vCPUs available in my subscription".

DevOps & Infrastructure

raindrop-io

242

from aiskillstore/marketplace

Manage Raindrop.io bookmarks with AI assistance. Save and organize bookmarks, search your collection, manage reading lists, and organize research materials. Use when working with bookmarks, web research, reading lists, or when user mentions Raindrop.io.

Data & Research

zlibrary-to-notebooklm

242

from aiskillstore/marketplace

自动从 Z-Library 下载书籍并上传到 Google NotebookLM。支持 PDF/EPUB 格式，自动转换，一键创建知识库。

discover-skills

242

from aiskillstore/marketplace

当你发现当前可用的技能都不够合适（或用户明确要求你寻找技能）时使用。本技能会基于任务目标和约束，给出一份精简的候选技能清单，帮助你选出最适配当前任务的技能。

web-performance-seo

242

from aiskillstore/marketplace

Fix PageSpeed Insights/Lighthouse accessibility "!" errors caused by contrast audit failures (CSS filters, OKLCH/OKLAB, low opacity, gradient text, image backgrounds). Use for accessibility-driven SEO/performance debugging and remediation.

project-to-obsidian

242

from aiskillstore/marketplace

将代码项目转换为 Obsidian 知识库。当用户提到 obsidian、项目文档、知识库、分析项目、转换项目时激活。【激活后必须执行】： 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入规则（默认到 00_Inbox/AI/、追加式、统一 Schema） 3. 执行 STEP 0: 使用 AskUserQuestion 询问用户确认 4. 用户确认后才开始 STEP 1 项目扫描 5. 严格按 STEP 0 → 1 → 2 → 3 → 4 顺序执行【禁止行为】： - 禁止不读 SKILL.md 就开始分析项目 - 禁止跳过 STEP 0 用户确认 - 禁止直接在 30_Resources 创建（先到 00_Inbox/AI/） - 禁止自作主张决定输出位置

obsidian-helper

242

from aiskillstore/marketplace

Obsidian 智能笔记助手。当用户提到 obsidian、日记、笔记、知识库、capture、review 时激活。【激活后必须执行】： 1. 先完整阅读本 SKILL.md 文件 2. 理解 AI 写入三条硬规矩（00_Inbox/AI/、追加式、白名单字段） 3. 按 STEP 0 → STEP 1 → ... 顺序执行 4. 不要跳过任何步骤，不要自作主张【禁止行为】： - 禁止不读 SKILL.md 就开始工作 - 禁止跳过用户确认步骤 - 禁止在非 00_Inbox/AI/ 位置创建新笔记（除非用户明确指定）

internationalizing-websites

242

from aiskillstore/marketplace

Adds multi-language support to Next.js websites with proper SEO configuration including hreflang tags, localized sitemaps, and language-specific content. Use when adding new languages, setting up i18n, optimizing for international SEO, or when user mentions localization, translation, multi-language, or specific languages like Japanese, Korean, Chinese.

google-official-seo-guide

242

from aiskillstore/marketplace

Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation