execute-review-findings

Normalize code review findings into tasks and execute them in priority waves.

2|Updated Jan 24, 2026
One-click install
npx skills add https://github.com/ahrav/scratch-scanner-rs --skill execute-review-findings
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: execute-review-findings
Source: https://github.com/ahrav/scratch-scanner-rs/tree/main/.claude/skills/execute-review-findings
Command: npx skills add https://github.com/ahrav/scratch-scanner-rs --skill execute-review-findings

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates the process of taking code review findings, PR comments, or review reports and systematically turning them into actionable tasks that can be executed efficiently, especially when dealing with multiple issues across various files.

Core Features & Use Cases

  • Normalization: Parses findings from different sources (PR comments, review reports) into a standardized format.
  • Task Creation: Generates self-contained tasks for each finding, suitable for execution by agents.
  • Concurrency Analysis: Identifies which tasks can be run in parallel and which have dependencies.
  • Phased Execution: Executes tasks in priority waves (MUST FIX, SHOULD FIX, etc.) to ensure critical issues are addressed first.
  • Use Case: After a code review identifies several bugs, performance issues, and documentation gaps across multiple files, this Skill will create individual tasks for each, determine which can be fixed concurrently, and then execute them in order of severity, ensuring all tests pass between waves.

Quick Start

Use the execute-review-findings skill to process findings from the most recent /review-dispatch output.

Frequently Asked Questions about execute-review-findings

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

FAQPage Schema
How do I systematically address code review findings across multiple files?

To systematically address code review findings, normalize PR comments and review reports into self-contained tasks, then execute them in priority waves with parallel agents. This process manages findings by creating tasks with detailed resolution steps and acceptance criteria.

Can I automate bug fixing and refactoring tasks from PR comments?

Yes, you can automate bug fixing and refactoring from PR comments by parsing them into a standardized format. The system generates self-contained tasks for each finding, suitable for execution by parallel agents to improve developer productivity.

How do I determine which code review tasks can be run in parallel?

Concurrency analysis identifies which code review tasks can run in parallel and which have dependencies. It optimizes execution flow by analyzing task concurrency, ensuring independent bug fixing and refactoring tasks execute simultaneously across different files.

How do I prioritize bug fixing and refactoring tasks from a code review?

Prioritize bug fixing and refactoring tasks using phased execution in priority waves like MUST FIX and SHOULD FIX. This ensures critical issues are addressed first, maintaining quality gates between waves to verify all tests pass.

What is the best way to manage task dependencies when fixing code review findings?

The best way to manage task dependencies when fixing code review findings is through concurrency analysis that maps task relationships. This optimizes execution flow by grouping independent tasks for parallel agents while sequencing dependent tasks correctly.

How do I ensure quality gates pass between task execution waves?

To ensure quality gates pass between task execution waves, the system enforces test verification after each priority wave completes. This phased execution approach guarantees that all tests pass before proceeding to the next set of refactoring or bug fixing tasks.