blueprint

Automate a brief objective into a structured multi-session engineering execution plan.

2|2|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/zhmxiaowo/opencode-simple --skill blueprint-zhmxiaowo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: blueprint
Source: https://github.com/zhmxiaowo/opencode-simple/tree/main/.opencode/skills/blueprint
Command: npx skills add https://github.com/zhmxiaowo/opencode-simple --skill blueprint-zhmxiaowo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Turn a one-line objective into a step-by-step construction plan for multi-session, multi-agent engineering projects. Each step has a self-contained context brief so a fresh agent can execute it cold. Includes adversarial review gate, dependency graph, parallel step detection, anti-pattern catalog, and plan mutation protocol.

Core Features & Use Cases

  • Five-phase pipeline (Research, Design, Draft, Review, Register) to transform objectives into executable plans.
  • Adversarial review gate and dependency graphs to ensure completeness and correctness.
  • Parallel step detection and plan mutation protocol to optimize multi-agent collaboration.
  • Supports multi-priority, multi-PR tasks and projects spanning multiple sessions.

Quick Start

Provide a complex objective and ask Blueprint to generate a step-by-step, cold-execution plan with dependencies and parallelism.

Frequently Asked Questions about blueprint

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

FAQPage Schema
How do I turn a brief objective into a multi-session execution plan for software engineering?

To turn a brief objective into a multi-session execution plan, provide your objective to generate a structured, step-by-step construction plan. This applies a five-phase workflow including Research, Design, Draft, Review, and Register to transform objectives into executable plans.

How do I create step-by-step plans with cold-start context briefs for fresh agents?

Creating step-by-step plans with cold-start context briefs ensures each step has a self-contained context brief so a fresh agent can execute it cold. This preserves context across sessions for large features, refactors, migrations, or multi-agent coordination.

What is the best way to manage dependencies and parallelism in multi-agent engineering projects?

Managing dependencies and parallelism in multi-agent engineering projects is handled through parallel step detection and dependency graphs. These features optimize multi-agent collaboration by ensuring steps are correctly sequenced and identifying opportunities for parallel execution.

Can I use an adversarial review gate to ensure completeness and correctness in my project plan?

Yes, you can use an adversarial review gate to ensure completeness and correctness in your project plan. This review mechanism acts as a checkpoint during the Draft phase to validate the generated steps before final registration.

How do I handle plan mutations during multi-priority or multi-PR tasks?

Handling plan mutations during multi-priority or multi-PR tasks is managed through a dedicated plan mutation protocol. This protocol allows adjustments to the execution plan while maintaining the integrity of the overall dependency graph and multi-session workflow.

When do I need a structured construction plan for multi-agent coordination?

You need a structured construction plan for multi-agent coordination when working on large features, refactors, migrations, or projects spanning multiple sessions. It ensures context is preserved across sessions and provides self-contained briefs for cold agent execution.