audit-fix-loop
CommunityIteratively improve quality with scored audits.
Software Engineering#testing#quality assurance#workflow automation#ai agent#auditing#iterative improvement
Authoredwinhu
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill addresses the challenge of ensuring high-quality output by implementing a structured, iterative improvement process that prevents the agent from approving its own work.
Core Features & Use Cases
- Independent Auditing: Ensures that the entity performing the audit is separate from the entity performing the fix, preventing biased self-assessment.
- Scored Iterations: Progress is measured by objective scores against defined criteria, with a clear threshold for completion.
- Targeted Fixing: Focuses on addressing the most severe issues first in each iteration.
- Use Case: You have a draft of a critical report. You can use this Skill to have an independent auditor score it against a style guide and factual accuracy checklist. If it doesn't meet the 9.5/10 threshold, the Skill will then attempt to fix the highest-priority issues before undergoing another independent audit.
Quick Start
Use the audit-fix-loop skill to iteratively improve the quality of the 'draft-report.md' file using AI anti-patterns and style guide scorers until it reaches a score of 9.5.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 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: audit-fix-loop Download link: https://github.com/edwinhu/workflows/archive/main.zip#audit-fix-loop 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 223,000+ vetted skills library on demand.