autoplan

Automate multi-phase software review pipelines with auto-decisions and structured artifacts.

Updated Apr 11, 2026
One-click install
npx skills add https://github.com/akiyoshi/gstack-copilot-jp --skill autoplan-akiyoshi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: autoplan
Source: https://github.com/akiyoshi/gstack-copilot-jp/tree/main/.github/skills/autoplan
Command: npx skills add https://github.com/akiyoshi/gstack-copilot-jp --skill autoplan-akiyoshi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates the end-to-end coordination of multi-phase software reviews, turning scattered tasks into a deterministic, repeatable workflow that reduces manual overhead and human error. Manual coordination of CEO, design, engineering, and DX reviews is slow and inconsistent; autoplan orchestrates these phases with consistent artifacts. Single source of truth ensures the same criteria and outputs across teams, improving traceability and quality.

Core Features & Use Cases

  • End-to-end pipeline orchestration: CEO → Design → Eng → DX reviews execute in sequence with auto-decisions.
  • 6-principles decision automation: Predefined rules drive intermediate answers while surfacing taste decisions at gates.
  • Artifact generation: Produces phase outputs, consensus metrics, and risk registries for governance and audits.
  • Developer-facing integration: Reads skill definitions and loads sub-skills to form a cohesive workflow.

Quick Start

Invoke the /autoplan command to execute the full CEO → Design → Eng → DX review pipeline.

Frequently Asked Questions about autoplan

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

FAQPage Schema
How do I automate an end-to-end code review pipeline for engineering governance?

Automating an end-to-end code review pipeline involves orchestrating sequential phases like CEO strategy, design critique, architecture review, and DX readiness. This skill executes predefined plan files with auto-decisions to generate structured phase outputs and governance artifacts.

What is the best way to coordinate multi-phase software reviews without manual overhead?

Coordinating multi-phase software reviews deterministically requires a single source of truth for consistent criteria across teams. This skill reads skill definitions and orchestrates CEO, Design, Eng, and DX reviews in sequence to reduce human error.

How does decision automation work in an automated engineering review workflow?

Decision automation in an engineering review workflow applies predefined 6-principles rules to drive intermediate answers automatically. This approach surfaces taste decisions specifically at review gates while producing consensus metrics and risk registries.

Do I need predefined skill files to run an automated review pipeline?

Predefined skill files are required to run the automated review pipeline, as the skill reads these definitions to execute each phase with auto-decisions. You must provide access to plan definitions, skill files, and the environment for running subagents.

Can I generate governance artifacts and risk registries from a automated architecture review?

Generating governance artifacts and risk registries from an automated architecture review is supported natively. The pipeline produces structured phase outputs, consensus metrics, and audit-ready artifacts for comprehensive project governance.

Why does my multi-phase review pipeline lack traceability and consistent outputs across teams?

Multi-phase review pipelines lack traceability when manual coordination of CEO, design, engineering, and DX reviews causes inconsistent artifacts. Automating the pipeline with a single source of truth ensures identical criteria and outputs across teams.