skills.rest
dev-gios
dev-giosCOMMUNITY
Explore all skills by this author →
GitHub

qa-feedback

Classifies user dismissals of code review findings and persists feedback to Engram or OpenSpec.

1|Updated Mar 3, 2026
Search Tags:#automation#code review#qa#ai agent#feedback loop#persistence
One-click install
npx skills add https://github.com/dev-gios/agent-teams-qa --skill qa-feedback
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: qa-feedback
Source: https://github.com/dev-gios/agent-teams-qa/tree/main/skills/qa-feedback
Command: npx skills add https://github.com/dev-gios/agent-teams-qa --skill qa-feedback

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill acts as the institutional memory for code quality reviews, processing user dismissals of findings to prevent repeat issues and improve agent accuracy.

Core Features & Use Cases

  • Feedback Processing: Captures user reasons for dismissing code review findings.
  • Classification: Categorizes dismissals as Project Rule, One-Time Exception, or False Positive.
  • Persistence: Stores feedback in Engram or OpenSpec for future reference and automated skipping of known issues.
  • Use Case: After a code review, a developer dismisses a "missing error handling" warning, classifying it as a "Project Rule" because that specific API is known to be robust. This feedback is stored, and the qa-advocate agent will no longer flag this specific pattern in future reviews for this project.

Quick Start

Use the qa-feedback skill to process dismissals for review ID '12345'.

Frequently Asked Questions about qa-feedback

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

FAQPage Schema
How do I stop AI code review agents from repeating dismissed findings?▼

Code review feedback processing captures dismissal reasons and persists them as institutional memory, preventing AI agents from repeating dismissed findings in future reviews.

How does user feedback classification work for dismissed code review warnings?▼

User feedback classification categorizes dismissed code review warnings into Project Rule, One-Time Exception, or False Positive, storing each type to inform future automated review accuracy.

What is the best way to persist code review dismissal decisions for automated QA agents?▼

Persisting code review dismissal decisions requires an artifact store mode using Engram or OpenSpec, which stores feedback to enable automated skipping of known issues in subsequent reviews.

Can I use Engram and OpenSpec for storing AI agent code review feedback?▼

Yes, Engram and OpenSpec are supported artifact store modes for persisting QA feedback, determining the storage strategy for dismissed code review findings and institutional memory.

Why does my automated code review keep flagging patterns I already dismissed as project rules?▼

Repeat findings occur when dismissal feedback is not persisted. Processing dismissals through a feedback loop stores Project Rule classifications to prevent the agent from re-flagging known patterns.

Related Skills

Explore More Software Engineering Skills→
KilloconQKilloconQ

sdd-tasks

Generate a phase-driven tasks.md checklist from design proposals and specifications.

Community
Intermediate
datorresbdatorresb

code-review

Guide structured code reviews across correctness, maintainability, security, and performance.

Community
Basic
Disaster-TerminatorDisaster-Terminator
5

review-workflow

Fetch, categorize, fix, test, and resolve pull request review comments.

Community
Advanced
barkleesandersbarkleesanders
5

file-todos

Create and track file-based todos for code review feedback and technical debt.

Community
Intermediate