Advanced AI Rubric & Bucket Upgrade Skill for Codex

Advanced AI Rubric & Bucket Upgrade Skill for Codex

The Advanced AI Rubric & Bucket Upgrade Skill for Codex provides developers with the capability to propose and execute rubric or bucket upgrades within Codex. This skill operates in two modes: a comprehensive rubric bump and a lightweight bucket-only recalibration.

What this skill does

• Allows users to propose changes to the scoring rubric using the --propose command, which initiates a robust multi-step review process.
• Enables the adjustment of bucket boundaries without altering the rubric formula via the --bucket-only command, automatically deriving new boundaries.
• Ensures rubric and bucket updates are completed through cheat-score-blind recalibration, using a standard calibration pool for scoring.
• Supports recalibration with a cheat-bump process that includes phase-specific checks and validations, based on user inputs.
• Integrates independent cross-model review for comprehensive rubric bumps to maintain scoring accuracy.

Who it is for

• Developers and data scientists leveraging AI coding agents such as Codex, Claude Code, and Cursor.
• Teams managing complex AI models requiring dynamic adjustments to evaluation metrics.

Use cases

• Refining AI evaluation metrics where the existing scoring rubric needs significant adjustments for improved model assessments.
• Adjusting evaluation buckets to better fit evolving datasets as project requirements change over time.
• Implementing detailed metric adjustments to cater to new dimensions or weight shifts in AI model evaluations.

Technical details

• Utilizes cheat-bump integration for initiating rubric and bucket modifications.
• Implements a phased approach to execution, beginning with parameter detection and proceeding through recalibration and verification stages.
• Ensures independency in audits, applying comprehensive cross-model reviews for proposed changes to guarantee accuracy.
• Relies on agentic-ai and aiapplication frameworks to facilitate seamless integration with AI development environments like Codex.

Source & Licence

This package is built on open-source work published by LiHongwei-cn (LiHongwei-cn/lihongwei-cn) 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.