A strategic review layer for AI coding agents that challenges plan premises and ensures high-standard implementation through founder-mode analysis.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install gstack-openclaw-ceo-review
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install gstack-openclaw-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 CEO Plan Review Skill?
The CEO Plan Review skill transforms your AI agent into a rigorous technical strategist. Instead of simply executing tasks, it forces the agent to adopt a founder-mode posture, evaluating every plan for long-term viability, edge cases, and architectural integrity. By integrating this into Openclaw Skills, developers ensure that their AI-driven projects maintain a 10-star quality standard, avoiding common pitfalls and silent failures. This skill is specifically designed to act as a gatekeeper, preventing premature implementation while optimizing for the 6-month future.
At its core, this Openclaw Skills component operates on the philosophy that focus is subtraction and every interaction must build user trust. It provides the agent with the cognitive patterns of high-performing founders, such as inversion reflex and proxy skepticism. This ensures that every technical decision is weighed against business outcomes and long-term leverage rather than just immediate task completion.
CEO Plan Review Skill Use Cases
- Challenging the core premises of a complex technical plan before implementation begins.
- Scaling a greenfield feature by exploring 10x expansion opportunities to create a cathedral-tier product.
- Performing a ruthless scope reduction for urgent, minimal viable releases to ensure speed without sacrifice.
- Identifying hidden failure modes and data flow shadow paths in existing architectural plans.
- Auditing plans for observability, security, and performance bottlenecks before a single line of code is written.
How CEO Plan Review Skill Works
- Nuclear Scope Challenge: The agent interrogates the problem to ensure the right problem is being solved and maps existing code leverage.
- Implementation Alternatives: The skill generates 2-3 distinct approaches, ranging from minimal viable to ideal architecture, for user approval.
- Mode Selection: The user chooses between Scope Expansion, Selective Expansion, Hold Scope, or Scope Reduction based on the project phase.
- Temporal Interrogation: The agent predicts implementation bottlenecks by simulating what will happen at Hour 1, Hour 3, and Hour 6 of the coding process.
- Multi-Section Review: The agent performs a non-skippable 11-step deep dive into architecture, error mapping, security, observability, and UX.
- Strategic Summary: A final CEO Review Summary is generated, documenting the accepted scope and deferred items, then saved to the memory directory.
CEO Plan Review Skill Setup
To integrate this capability into your workflow, ensure your agent environment is configured to support Openclaw Skills by following these steps:
# Navigate to your agent skills directory
cd path/to/your/agent/skills
# Create the skill definition file
touch gstack-openclaw-ceo-review.md
Ensure that the agent has write permissions for the memory/ directory to store review summaries and maintains a persistent state across the review lifecycle. No external API keys are required as this is a logic-based strategic skill.
CEO Plan Review Skill Data Schema & Taxonomy
The CEO Plan Review skill organizes its analysis into structured summaries to maintain consistency across Openclaw Skills implementations. It uses the following data taxonomy:
| Attribute | Description |
|---|---|
| Mode | One of four operational postures: Expansion, Selective, Hold, or Reduction. |
| Shadow Paths | Trace of nil input, empty input, and upstream error paths for every data flow. |
| Reversibility | Categorization of decisions by magnitude and the ability to undo changes (Two-way doors). |
| Performance Map | Analysis of system behavior at 10x and 100x load levels. |
| Memory Summary | A persistent log saved in markdown format documenting accepted vs. deferred scope items. |
CEO Plan Review Skill Advanced Features
- Temporal Interrogation: Predicting specific implementation surprises at different time intervals (Hour 1 to Hour 6+).
- Cognitive Thinking Patterns: Employs founder-mode instinct, paranoid scanning, and inversion reflex to find hidden risks.
- Shadow Path Analysis: Automatically traces data flows through three distinct failure modes for every happy path.
- Atomic Issue Reporting: Enforces a one-issue-at-a-time rule to prevent user overwhelm and ensure thorough review of each architectural component.
- Dependency Graphing: Mandatory diagramming for all non-trivial flows to ensure narrative coherence within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Industrial Design Robot Brief
An automated research agent that synthesizes technical humanoid-robot papers into professional Chinese briefs focused on industrial design and product definition.
GitHub Sync Skill
A powerful automation tool to synchronize local AI agent skills with GitHub repositories for versioning, sharing, and secure backup.
Systematic Debugging & Root Cause Investigation
A high-integrity debugging framework for AI agents that enforces a root-cause-first approach to eliminate symptom-only fixes.
Engineering Retrospective & Git Insights
An advanced git analysis tool that generates comprehensive weekly engineering retrospectives with team-aware metrics and trend tracking.
Geo-Fix-Content: AI Citability Optimizer
A precision tool for transforming standard website copy into authoritative, data-backed, and highly citable content optimized for AI search engines and LLMs.
Monochrome Music
A high-fidelity music discovery and streaming skill for AI agents powered by the Monochrome API.
Featured*
