Plan CEO Review for Openclaw

A strategic review skill that applies founder-mode thinking to challenge technical premises and optimize product scope.

loocor
v1.0.0
Mar 21, 2026
0
1.3k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install gstack-plan-ceo-review

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install gstack-plan-ceo-review using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Plan CEO Review?

The plan-ceo-review is a high-level strategic skill designed for AI agents to move beyond simple task execution and into product leadership. It functions as a virtual CEO or founder, rigorously analyzing plans to ensure they are ambitious, complete, and architecturally sound. By utilizing Openclaw Skills like this one, developers can ensure their AI agents don't just write code, but build 10-star products by challenging existing premises and expanding vision where it adds the most value.

This skill operates on the Completeness Principle, acknowledging that AI-assisted coding makes the marginal cost of a 100% complete implementation near-zero. It pushes for "boiling the lake"—achieving full test coverage and handling all edge cases—rather than settling for shortcuts. It provides a structured framework for architecture audits, threat modeling, and observability, ensuring every project is treated as a long-term asset rather than a temporary fix.

Plan CEO Review Use Cases

  • When a user asks to rethink a problem or verify if a plan is ambitious enough.
  • During strategy reviews to determine if a project should expand, hold, or reduce its current scope.
  • Proactively auditing complex plans that feel under-engineered or lack long-term vision.
  • Transitioning a project from a simple proof-of-concept to a production-ready, bulletproof implementation.

How Plan CEO Review Works

  1. The agent detects the base branch and performs a Pre-Review System Audit to understand the current technical context.
  2. It executes a Nuclear Scope Challenge to verify the problem framing and explore implementation alternatives.
  3. The user selects a specific review mode: SCOPE EXPANSION, SELECTIVE EXPANSION, HOLD SCOPE, or SCOPE REDUCTION.
  4. The skill runs through 11 rigorous review sections, including Architecture, Error Mapping, Security, and Observability.
  5. It generates mandatory ASCII diagrams for data flows and system architecture to ensure visual clarity.
  6. The process concludes with a Completion Summary and prompts for subsequent engineering or design reviews.

Plan CEO Review Setup

To integrate this strategic workflow into your environment using Openclaw Skills, ensure your agent has access to the GitHub CLI and follow these steps:

# Ensure the skill file is in your agent's skills directory
# No additional dependencies are required beyond standard git and gh tools

# The agent will automatically trigger the system audit:
git log --oneline -30
git diff <base> --stat

Plan CEO Review Data Schema & Taxonomy

The skill organizes its strategic output into a dedicated directory to ensure long-term persistence and traceability.

File/Path Description
./ceo-plans/{date}-{slug}.md Contains the vision, 10x check, and specific scope decisions.
TODOS.md Persistent registry of deferred tasks with context and priority.
Error & Rescue Registry A table mapping methods to potential exceptions and rescue actions.
Failure Modes Registry Tracks codepaths, failure modes, and visibility to the end user.

Plan CEO Review Advanced Features

  • Founder-Mode Bias: Incorporates cognitive patterns from industry leaders like Bezos and Horowitz to evaluate reversible vs. irreversible decisions.
  • Spec Review Loop: Dispatches reviewer subagents to iterate on documentation completeness up to three times.
  • Shadow Path Tracing: Forces analysis of nil, empty, and error inputs for every data flow.
  • Reversibility Scoring: Rates technical debt and architectural choices on a 1-5 scale to forecast long-term trajectory.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*