skills.rest
mlamla123
mlamla123COMMUNITY
Explore all skills by this author →
GitHub

deep-code-review

Coordinate five hunter agents and a verifier to surface true bugs.

Updated Aug 23, 2026
Search Tags:#verification#multi-agent#static-analysis#code-review#bug-hunting#cross-module
One-click install
npx skills add https://github.com/mlamla123/openclaw-starter-kit --skill deep-code-review
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deep-code-review
Source: https://github.com/mlamla123/openclaw-starter-kit/tree/main/skills/deep-code-review
Command: npx skills add https://github.com/mlamla123/openclaw-starter-kit --skill deep-code-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Performs a multi-agent code review workflow to catch real bugs by coordinating specialized reviewers and a verifier to reduce false positives.

Core Features & Use Cases

  • Phase-based workflow: discovers code structure, launches five specialized hunter agents, and runs a verification step to filter findings.
  • Cross-project and PR reviews: suitable for full projects, PR diffs, or targeted modules to surface real issues across boundaries.
  • Structured reporting: aggregates findings into a concise report with verification results and recommended remediations.

Quick Start

Provide a comprehensive multi-agent code review following the DISCOVER, HUNT, VERIFY phases and produce a final report.

Frequently Asked Questions about deep-code-review

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

FAQPage Schema
How do I perform a multi-agent code review to catch real bugs?▼

A multi-agent code review coordinates five specialized hunter agents to find bugs across full codebases or PR diffs, followed by a verification step to filter false positives and produce a final report.

What is the best way to reduce false positives during static-analysis bug hunting?▼

To reduce false positives in static-analysis bug hunting, run a verification phase where a verifier agent filters the findings from specialized hunters, ensuring only true bugs are reported.

Can I use multi-agent code review for pull requests or targeted modules?▼

Yes, multi-agent code review can be applied to pull request diffs or targeted modules to surface real issues and cross-module bugs without reviewing the entire project.

How does cross-module code review work?▼

Cross-module code review works by coordinating specialized hunter agents to analyze boundaries across different modules, aggregating findings into a structured report with verification results.

What steps are involved in multi-agent code review?▼

Multi-agent code review follows the DISCOVER, HUNT, and VERIFY phases: discovering code structure, launching parallel hunter agents, and verifying findings to generate a regression-friendly report.

Related Skills

Explore More Software Engineering Skills→
zfedoranzfedoran
15

rsmap

Generate multi-layer LLM-friendly indexes for Rust codebases.

Community
Intermediate
igij01igij01

bug-fix-and-ship

Automate bug fixes from structured reports to verified source changes.

Community
Advanced
codexstar69codexstar69
479

skeptic

Review reported vulnerabilities in code to identify false positives.

Community
Advanced
cjinzycjinzy
2

jin-swe-fix

Orchestrate multi-agent pipelines to analyze, fix, and verify software issues.

Community
Advanced