self-eval-bias
CommunityPrevent overconfidence and bias in code reviews.
Software Engineering#code review#critical thinking#bias detection#agent review process#evaluation best practices
AuthorArchive228
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill identifies when an agent overvalues its own work due to context bias, helping ensure a fair and thorough review process.
Core Features & Use Cases
- Detect Bias: Recognizes patterns of self-evaluation in reviews where agents are overly confident about their work.
- Review Mitigation: Recommends actions to avoid the bias, such as seeking fresh perspectives and concrete evidence.
- Use Case: After an agent has completed a piece of work, such as a code patch or report, and the Skill detects an instance of overconfidence, it prompts a reviewer to conduct a fresh and thorough review.
Quick Start
Use the self-eval-bias skill to analyze the latest code review and prevent biased evaluation.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 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: self-eval-bias Download link: https://github.com/Archive228/loopkit/archive/main.zip#self-eval-bias 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.