blueprint

Generate a multi-session construction plan with dependency graph and review gate.

2|Updated Mar 3, 2026
One-click install
npx skills add https://github.com/MomoDaviluke/star-citizen-promotion --skill blueprint-momodaviluke
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: blueprint
Source: https://github.com/MomoDaviluke/star-citizen-promotion/tree/main/.agents/skills/ecc/blueprint
Command: npx skills add https://github.com/MomoDaviluke/star-citizen-promotion --skill blueprint-momodaviluke

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Breaks down ambiguous, high-level objectives into explicit, self-contained steps that can be executed by autonomous agents across multiple sessions, reducing rework and context loss.

Core Features & Use Cases

  • Five-phase planning pipeline (Research, Design, Draft, Review, Register) that converts objectives into executable steps with dependency and timing considerations.
  • Adversarial review gate and anti-pattern checks to ensure plan completeness and robustness.
  • Dependency graph and parallel step detection to maximize parallel work and minimize bottlenecks.
  • Plan mutation protocol to split, insert, reorder, or remove steps with audit trails.
  • Cold-start execution support so each step contains a self-contained context for fresh agents.
  • Output ready-to-run plans that can generate PRs, branches, or direct edits depending on environment.

Quick Start

Provide a single objective to the blueprint command and it will output a detailed, multi-session construction plan with dependency order.

Frequently Asked Questions about blueprint

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

FAQPage Schema
How do I break down a complex coding project into multi-session steps?

Multi-session project planning converts a single high-level objective into a structured five-phase pipeline: research, design, draft, review, and register. This creates dependency-aware, self-contained steps executable by autonomous agents across sessions.

What is an adversarial review gate in software engineering project planning?

An adversarial review gate validates plan completeness and robustness during the drafting phase. It applies anti-pattern checks to ensure generated multi-session steps are executable and logically sound before final registration.

Can I reorder or insert steps in a multi-agent construction plan after generation?

Yes, plan mutation protocols allow you to split, insert, reorder, or remove steps after generation. All mutations maintain audit trails to preserve dependency graph integrity and sequencing accuracy.

Does multi-agent planning support cold-start execution for fresh sessions?

Cold-start execution support ensures each generated step contains self-contained context. This allows fresh autonomous agents to execute individual steps without prior session memory or loaded project history.

How to maximize parallel work in a dependency-aware project plan?

Dependency graphs detect parallel steps within the generated construction plan to maximize parallel work and minimize bottlenecks. This allows multiple autonomous agents to execute independent tasks simultaneously.

What output format does a multi-session construction plan generate for code execution?

The planning pipeline outputs ready-to-run plans that generate PRs, branches, or direct edits depending on your environment. This executes the dependency-sequenced steps through autonomous agents.