skills.rest
javierhbr
javierhbrCOMMUNITY
Explore all skills by this author →
GitHub

review-skill-improver

Analyze feedback logs to identify rejected code review patterns and suggest skill improvements.

Updated Feb 17, 2026
Search Tags:#automation#code review#ai development#skill improvement#false positives#feedback analysis
One-click install
npx skills add https://github.com/javierhbr/random-poc --skill review-skill-improver
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: review-skill-improver
Source: https://github.com/javierhbr/random-poc/tree/main/custom-skills/beagle-main/plugins/beagle-core/skills/review-skill-improver
Command: npx skills add https://github.com/javierhbr/random-poc --skill review-skill-improver

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the analysis of feedback logs to identify and suggest improvements for review skills, reducing false positives and improving accuracy.

Core Features & Use Cases

  • False Positive Identification: Pinpoints rules with high rejection rates.
  • Missing Rule Detection: Highlights issues that were missed by existing rules.
  • Actionable Recommendations: Generates specific, text-based suggestions for skill modification.
  • Use Case: After a code review process, feed the accumulated feedback logs into this skill to automatically generate a report detailing which rules are too strict or which patterns are being missed, along with concrete steps to fix them.

Quick Start

Use the review-skill-improver to analyze feedback logs and generate an improvement report.

Frequently Asked Questions about review-skill-improver

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

FAQPage Schema
How do I analyze code review feedback logs to reduce false positives?▼

To analyze code review feedback logs and reduce false positives, you can automate the identification of rules with high rejection rates. This process generates specific, actionable recommendations to refine existing review skills and improve overall accuracy.

What is the best way to detect missing rules in automated code reviews?▼

Detecting missing rules in automated code reviews involves processing structured feedback data to highlight issues that existing rules missed. This analysis generates a detailed report pinpointing uncovered patterns and providing concrete steps for skill modification.

How do I refine AI code review skills using accumulated feedback data?▼

You refine AI code review skills by feeding accumulated feedback logs into an analysis process. This identifies patterns in rejected code reviews and outputs specific suggestions for skill refinement, enhancing review accuracy and efficiency.

Can I generate actionable recommendations for modifying strict code review rules?▼

Yes, you can generate actionable recommendations for modifying strict code review rules by analyzing structured feedback data. This identifies rules with high rejection rates and provides text-based suggestions for skill modification to address false positives.

Does this feedback analysis approach require specific log formats to identify rejected code reviews?▼

This feedback analysis approach utilizes structured feedback data to identify rejected code reviews. While it requires structured logs to accurately pinpoint high rejection rates and missing rule coverage, no specific external dependencies are needed for the analysis.

Related Skills

Explore More Software Engineering Skills→
ntaksh42ntaksh42
1

receiving-code-review

Evaluate and respond to code review feedback with technical verification.

Community
Intermediate
ZJUxjyZJUxjy

receiving-code-review

Analyze and verify code review feedback for technical accuracy before implementation.

Community
Intermediate
barichterbarichter

rework-rate

Analyze pull request rework rates and review cycle metrics.

Community
Intermediate
mwathibenmwathiben

typescript-review

Review TypeScript and JavaScript diffs against Metabase coding standards.

Community
Intermediate