worktree-deliver
The worktree-deliver command automates the process of packaging and delivering work from a Git worktree as a pull request. It validates the worktree environment, reviews all changes, stages files with user confirmation, generates a conventional commit message based on the diff analysis, commits the work, pushes to the remote, and creates a PR. Use this when you have completed work in a worktree branch and want to streamline the delivery workflow from local development through PR creation.
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/davila7/claude-code-templates/HEAD/.claude/commands/worktree-deliver.md -o ~/.claude/commands/worktree-deliver.mdworktree-deliver.md
# Worktree Deliver
Commit all work, push, and create a pull request from the current worktree.
## Instructions
You are inside a worktree. Package up the work and deliver it as a PR.
### Step 1: Validate Environment
1. Verify this is a worktree (not the main working tree) using `git worktree list`
2. Get current branch: `git branch --show-current`
3. Verify branch follows `claude/*`, `claude-daniel/*`, or `review/*` pattern. If not, warn the user and ask if they want to continue.
4. Read `.worktree-task.md` if it exists to get the original task description
### Step 2: Review Changes
1. Run `git diff --stat` and `git diff --cached --stat` to show all changes
2. Run `git status --short` to show the full picture
3. If there are no changes at all (clean working tree, no commits ahead of main), inform the user there's nothing to deliver and stop.
### Step 3: Clean Up Task File
Before staging anything, remove the worktree task file so it doesn't end up in the commit:
```bash
rm -f .worktree-task.md
```
### Step 4: Confirm Files to Commit
Use AskUserQuestion to show the user what will be committed and ask for confirmation. List all modified, added, and untracked files.
Options:
- "Stage all changes" — stage everything
- "Let me choose" — user will specify which files to include
If the user wants to choose, ask them which files to stage.
### Step 5: Stage and Commit
1. Stage the confirmed files with `git add`
2. Generate a commit message following conventional commits format
**Commit Message Strategy:**
1. **Analyze the diff** to determine the conventional commit type:
- `feat:` — New functionality, new files, new exports, new API endpoints
- `fix:` — Bug fixes, error corrections, fixing broken behavior
- `refactor:` — Code restructuring without changing behavior
- `docs:` — Documentation only changes
- `test:` — Adding or modifying tests
- `chore:` — Build scripts, configs, maintenance tasks
2. **Generate a commit message** based on:
- The task description from `.worktree-task.md` (if it was found)
- A brief summary of what the diff actually changed
- Format: `<type>: <subject>` (max 72 characters)
3. **Show the proposed message** to the user with AskUserQuestion:
- Display the generated message clearly
- Options: "Use this message" / "Let me write my own"
4. **If user chooses to write their own:**
- Ask them to provide their commit message
- Validate it follows conventional commits format (warn if not, but allow)
5. **Always include body and co-author:**
- Add a brief body summarizing what changed (2-3 bullet points if multiple changes)
- Include the standard co-author line
3. Create the commit with the message using a HEREDOC:
```bash
git commit -m "$(cat <<'EOF'
<commit message here>
EOF
)"
```
### Step 6: Push
Push the branch to origin:
```bash
git push -u origin HEAD
```
If push fails due to no upstream, the `-u` flag should handle it. If it fails for another reason, show the error and suggest fixes.
### Step 7: Create Pull Request
1. Determine the base branch (main or master) using the same detection as worktree-init
2. Create the PR using `gh pr create`:
```bash
gh pr create --base <main-branch> --title "<PR title>" --body "$(cat <<'EOF'
## Summary
<bullet points describing the changes based on task description and diff>
## Original Task
<task description from .worktree-task.md>
## Changes
<git diff --stat summary>
---
Created from worktree `claude/<name>` using `/worktree-deliver`
EOF
)"
```
3. Display the PR URL prominently
### Step 8: Next Steps
Tell the user:
- PR is ready for review at `<URL>`
- After merging, run `/worktree-cleanup` from the main repo to clean up
- They can close this terminal panelTesting and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.
Use this agent when creating specialized Claude Code agents for the claude-code-templates components system. Specializes in agent design, prompt engineering, domain expertise modeling, and agent best practices. Examples: <example>Context: User wants to create a new specialized agent. user: 'I need to create an agent that specializes in React performance optimization' assistant: 'I'll use the agent-expert agent to create a comprehensive React performance agent with proper domain expertise and practical examples' <commentary>Since the user needs to create a specialized agent, use the agent-expert agent for proper agent structure and implementation.</commentary></example> <example>Context: User needs help with agent prompt design. user: 'How do I create an agent that can handle both frontend and backend security?' assistant: 'Let me use the agent-expert agent to design a full-stack security agent with proper domain boundaries and expertise areas' <commentary>The user needs agent development help, so use the agent-expert agent.</commentary></example>
Create, manage, and orchestrate AI agents using the AI Maestro CLI. Use when the user asks to "create agent", "list agents", "delete agent", "hibernate agent", "wake agent", "install plugin", "show agent", "restart agent", or any agent lifecycle management task.
Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling. JSON Schema best practices, description writing that actually helps the LLM, validation, and the emerging MCP standard that's becoming the lingua franca for AI tools. Key insight: Tool descriptions are more important than tool implementa