ce-code-review

Orchestrate parallel reviewer personas to merge deduplicated code review findings into a report.

Updated Sep 25, 2024
One-click install
npx skills add https://github.com/kwam1na/athena --skill ce-code-review-kwam1na
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ce-code-review
Source: https://github.com/kwam1na/athena/tree/main/.agents/skills/ce-code-review
Command: npx skills add https://github.com/kwam1na/athena --skill ce-code-review-kwam1na

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Code review is time-consuming and inconsistent across reviewers; this Skill coordinates tiered personas to produce structured JSON findings, then deduplicates and merges results into a unified report that can be filed as tickets or fed into downstream workflows.

Core Features & Use Cases

  • Spawn multiple reviewer personas in parallel to inspect diffs; merge and deduplicate results into a single report.
  • Outputs are designed for downstream workflows: ticket creation, dashboards, and accelerator pipelines.
  • Supports an interactive walk-through mode and an automated mode with explicit intent capture and remediation pathways.

Quick Start

Run the ce-code-review skill on the current diff to generate a structured, multi-perspective findings report.

Frequently Asked Questions about ce-code-review

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

FAQPage Schema
How do I automate multi-persona code reviews to merge structured findings across a diff?

To automate multi-persona code reviews, you can orchestrate parallel reviewer agents to inspect a diff, then deduplicate and merge the structured findings into a single unified report suitable for downstream ticket creation and dashboards.

What is the best way to generate structured JSON findings from a PR review?

The best way to generate structured JSON findings from a PR review is to run parallel reviewer personas across the diff. This approach deduplicates results and outputs a unified report designed for downstream workflows and accelerator pipelines.

Can I use an interactive walk-through mode for code reviews instead of fully automated pipelines?

Yes, you can use an interactive walk-through mode for code reviews. The system supports both interactive walk-throughs and automated modes, capturing explicit intent and defining remediation pathways for each finding.

Do I need any specific dependencies to run persona-based code review orchestration?

No specific dependencies are required to run persona-based code review orchestration. The Skill operates independently to spawn parallel reviewer agents and merge structured findings from your diff.

How do multi-persona code review reports integrate with existing ticket and dashboard workflows?

Multi-persona code review reports integrate by outputting structured JSON findings that are explicitly designed for downstream workflows. You can feed these deduplicated, merged results directly into ticket creation systems and dashboards.