autoplan

Execute CEO, design, and engineering review skills sequentially with an approval gate.

1|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/bhianerd/aimemory --skill autoplan-bhianerd
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: autoplan
Source: https://github.com/bhianerd/aimemory/tree/main/.claude/skills/gstack/autoplan
Command: npx skills add https://github.com/bhianerd/aimemory --skill autoplan-bhianerd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It removes the repetitive back-and-forth of running multiple review passes by automatically reading your CEO, design, and engineering review skills from disk and executing them in order, so you get a fully reviewed plan without answering dozens of intermediate prompts.

Core Features & Use Cases

  • Manual trigger only pipeline: Runs only when the user explicitly invokes /autoplan, to avoid unexpected behavior.
  • Sequential full review gauntlet: Executes CEO → Design (when UI scope is detected) → Eng reviews, enforcing the required order and producing all required outputs.
  • Auto-decided intermediate questions: Applies six decision principles to choose between options, while surfacing taste/borderline decisions at a final approval gate.
  • Dual-voice strategy and design review: Runs an independent CEO/design subagent plus a Codex voice (when available) to improve coverage and catch strategic or UX blind spots.
  • Final “approval gate” with surfaced taste decisions: Keeps mechanical decisions automatic while flagging where reasonable people could disagree.

Quick Start

Invoke /autoplan to have gstack run the full CEO → (Design if applicable) → Eng review pipeline and output a fully reviewed plan.

Frequently Asked Questions about autoplan

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

FAQPage Schema
How do I automate multiple code and design reviews for a product plan?

Automate product plan reviews by invoking a manual command to run sequential CEO, design, and engineering skill files from disk. This pipeline auto-decides intermediate questions and outputs a fully reviewed plan without repetitive back-and-forth prompts.

What is the best way to run sequential plan validation without answering intermediate prompts?

Run plan validation sequentially by executing a full review gauntlet that enforces strict phase ordering. It applies six decision principles to automatically resolve intermediate mechanical questions, only stopping at a final approval gate to surface taste or borderline decisions.

Does the auto review pipeline support conditional design reviews?

Yes, the auto review pipeline conditionally executes design reviews when UI scope is detected in the input plan. It enforces a strict CEO to design to engineering ordering, ensuring all required outputs are produced only when applicable.

Can I use dual-voice evaluation to catch strategic and UX blind spots during plan validation?

Use dual-voice evaluation to run an independent CEO and design subagent alongside a Codex voice when available. This strategy improves coverage during plan validation, helping to independently catch strategic or UX blind spots.

How does telemetry logging work during an automated plan review?

Telemetry and restore-point logging operate during the automated plan review to ensure reliable operation. This logging records the pipeline state, allowing the sequential execution of skill files to recover or resume safely if interrupted.

When should I not use an automated review pipeline for product planning?

Avoid using an automated review pipeline for product planning when you need manual control over every intermediate decision. This pipeline is designed for manual-only triggering and auto-decides mechanical questions, only surfacing borderline taste decisions at the final approval gate.