cleanup

Coordinate dual AI analyses to reconcile code quality findings into a unified report.

Updated Mar 10, 2026
One-click install
npx skills add https://github.com/dr-code/tessera --skill cleanup-dr-code
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cleanup
Source: https://github.com/dr-code/tessera/tree/main/skills/cleanup
Command: npx skills add https://github.com/dr-code/tessera --skill cleanup-dr-code

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Code quality assessments can vary between AI systems, leading to conflicting findings and unclear remediation paths. This skill coordinates Claude's and GPT's independent analyses, surfaces disagreements, and guides a reconciliation to produce a unified, high-confidence report.

Core Features & Use Cases

  • Independent analysis by Claude and GPT to identify code quality issues and AI-generated patterns.
  • Phase-based reconciliation that surfaces agreed findings first and documents model-specific findings.
  • Auditable, structured reporting that enables faster remediation and accountability.

Quick Start

Run the cleanup workflow on a target project to begin dual-analysis and generate a reconciled report.

Frequently Asked Questions about cleanup

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I reconcile conflicting code review findings from different AI models?

Code quality assessment reconciliation works by coordinating dual AI analyses to surface high-confidence issues, comparing independent findings, documenting disagreements, and generating an auditable unified report for faster remediation.

What is dual AI analysis for code quality assurance?

Dual AI analysis for code quality assurance is a process where independent model assessments are compared to identify agreed findings, surface disagreements, and generate a reconciled, auditable report with higher confidence than single-model reviews.

How do I generate an auditable code quality report for my codebase?

You generate an auditable code quality report by running a phase-by-phase dual-analysis on your codebase, which reconciles independent findings and documents model-specific issues to ensure structured governance and accountability.

Does AI-assisted code review work for identifying AI-generated code patterns?

AI-assisted code review supports identifying AI-generated code patterns by using independent analyses from multiple models to detect, compare, and reconcile quality issues specific to AI-generated codebases.

What is the best way to handle disagreements between AI code review tools?

The best way to handle disagreements between AI code review tools is using a phase-based reconciliation workflow that surfaces agreed findings first, documents model-specific discrepancies, and generates a unified report for clear remediation paths.

Can I use dual-analysis code review without external dependencies?

You can use dual-analysis code review without external dependencies, as the skill operates independently to coordinate analyses, reconcile disagreements, and generate structured reports directly within your environment.