AI Agent Skill Pack: Shisan Xinuo Roles for Claude & Codex

AI Agent Skill Pack: Shisan Xinuo Roles for Claude & Codex

The "Shisan Xinuo Roles" skill pack provides a set of execution and review roles designed for integration into AI coding agents such as Claude Code, Cursor, and Codex. This package includes eight context-driven roles that assist in workflows including review, execution, and interfacing tasks in accordance with specific requirements.

What this skill does

• Activates predefined roles based on task-specific triggers within the core Shisan Xinuo workflow.
• Utilizes a dispatch matrix to match symptoms and scenarios with appropriate roles, such as critic, risk-reviewer, and security-auditor.
• Provides a structured approach with six key fields: identity, applicable scenes, required processes, review execution checklists, output contracts, and capability boundaries.
• Ensures that specific roles are loaded when their usage is flagged by the core workflow, allowing detailed execution tailored to the task at hand.

Who it is for

This skill pack is designed for developers and teams leveraging AI coding agents like Claude Code, Cursor, and Codex. It is particularly useful for those focusing on systematic risk evaluation, security auditing, performance testing, and other critical software development roles.

Use cases

• Conducting critical and adversarial code reviews to identify weaknesses in proposed designs or implementations.
• Performing security audits on key areas like external inputs, dependencies, and permission handling before deployment.
• Executing systematic debugging processes to identify and rectify the root causes of exceptions before implementing fixes.
• Implementing performance checks to monitor and optimize processing load and concurrency efficiency.

Technical details

• Integrates with existing AI coding frameworks, specifically compatible with Claude Code, Cursor, and Codex.
• Requires the core Shisan Xinuo workflow for full functionality, ensuring seamless role activation upon relevant task detection.
• Roles can be installed independently but function optimally alongside the core package.

For authorised security testing, defensive research, and educational use only.

Source & Licence

This package is built on open-source work published by zxc663 (zxc663/shisan-xinuo-workflow) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.