cheat-bump
CommunityUpgrade rubrics and buckets with auditable bumps.
AuthorJason5330
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill automates the process of upgrading calibration rubrics and bucket boundaries, enabling controlled, auditable changes to scoring systems and reducing drift in model evaluation.
Core Features & Use Cases
- Complete rubric bump mode: performs a full, cross-model evaluated rubric upgrade with enforced steps and review.
- Bucket-only mode: recalibrates only bucket boundaries for lightweight adjustment without altering the rubric formula.
- Phase-driven workflow: includes proposed formulas, validation protocols, blind scoring sub-agents, and state tracking for auditability.
Quick Start
Trigger a rubric bump by issuing /cheat-bump --propose "<new formula>" or run /cheat-bump --bucket-only to perform a lightweight bucket recalibration.
Dependency Matrix
Required Modules
None requiredComponents
scriptsreferences
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: cheat-bump Download link: https://github.com/Jason5330/ai-self-eval/archive/main.zip#cheat-bump Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.