ship-playbook

Coordinate feature delivery with dependency-aware planning, implementation, review, and validation.

4|3|Updated Mar 15, 2026
One-click install
npx skills add https://github.com/ulpi-io/skills --skill ship-playbook
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ship-playbook
Source: https://github.com/ulpi-io/skills/tree/main/ship-playbook
Command: npx skills add https://github.com/ulpi-io/skills --skill ship-playbook

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill prevents feature delivery from becoming an ad hoc, error-prone process by coordinating planning, implementation, review, validation, and launch auditing in one controlled autonomous pass.

Core Features & Use Cases

  • DAG-Based Planning: Decomposes feature requests into dependency-aware tasks and executes them in topological order.
  • Guarded Implementation Workflow: Builds each task in isolated worktrees, integrates changes safely, runs slice-scoped reviews, and applies bounded fixes.
  • Resumable Quality Gates: Tracks plan, build, review, validation, and audit status in durable workflow files, with fail-closed gates and checkpoint resume support.
  • Use Case: Give the Skill a feature request and it can produce a grounded task plan, implement each task with appropriate specialists, cross-review the final result, run a launch audit when requested, and return verified findings for your decision.

Quick Start

Ask the ship-playbook skill to plan, build, review, validate, and optionally audit a feature request from end to end.

Frequently Asked Questions about ship-playbook

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate feature delivery from planning to code review in Git?

Automated feature delivery coordinates request intake, dependency-aware planning, isolated worktree implementation, and slice-scoped code review in one controlled pass. It decomposes requests into topologically ordered tasks for safe execution.

What is a dependency-aware task plan for software feature implementation?

A dependency-aware task plan uses a directed acyclic graph to decompose feature requests into topologically ordered tasks. This ensures prerequisites are built first, preventing integration conflicts during isolated worktree execution.

Can I resume a workflow state if a feature validation gate fails midway?

Yes, workflow state is tracked in durable checkpoint files across plan, build, review, and validation phases. If a feature validation gate fails, fail-closed logic pauses execution and supports checkpoint resume to continue safely.

Does the feature delivery workflow work with isolated Git worktrees?

Yes, the feature delivery workflow builds each task in isolated Git worktrees to integrate changes safely. This prevents branch contamination and enables slice-scoped reviews before merging code into the main workspace.

What is the best way to run a launch audit before shipping a new feature?

The best way to run a launch audit is to execute an optional final validation pass after implementation and review. This audits the workspace, reports unresolved findings honestly, and returns verified results for your shipping decision.

Why should I use DAG-based planning instead of linear task lists for feature delivery?

DAG-based planning maps task dependencies topologically, unlike linear lists, allowing specialist execution where safe and enforcing strict ordering where required. This prevents build failures from missing prerequisites during worktree implementation.