skills.rest
EndUser123
EndUser123COMMUNITY
Explore all skills by this author →
GitHub

ai-pi-nv-qwen-coder

Dispatch adversarial code review to Qwen3 Coder 480B via pi agent.

Updated Apr 26, 2026
Search Tags:#ai-assistant#code-review#multi-provider#adversarial-review#pi-agent#qwen3-coder
One-click install
npx skills add https://github.com/EndUser123/cc-marketplace --skill ai-pi-nv-qwen-coder
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-pi-nv-qwen-coder
Source: https://github.com/EndUser123/cc-marketplace/tree/main/plugins/cc-skills-ai-cli/skills/ai-pi-nv-qwen-coder
Command: npx skills add https://github.com/EndUser123/cc-marketplace --skill ai-pi-nv-qwen-coder

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates adversarial code review by dispatching to the Qwen3 Coder 480B model via a pi agent to identify vulnerabilities and quality issues.

Core Features & Use Cases

  • Multi-provider dispatch: Orchestrates code review across providers to compare results and enhance coverage.
  • Structured findings: Parses JSON output to extract a score, a concise summary, and a list of issues.
  • Synthesis & reporting: Generates a final risk assessment and actionable suggestions for code improvements.

Quick Start

Provide a target file or code snippet to be reviewed and let the agent return a structured JSON with findings.

Frequently Asked Questions about ai-pi-nv-qwen-coder

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

FAQPage Schema
How do I automate adversarial code review for vulnerabilities using Qwen3 Coder?▼

Adversarial code review is automated by dispatching source files to the Qwen3 Coder 480B model via a pi agent to identify vulnerabilities and quality issues. The workflow parses a JSON output schema containing a score, summary, and list of issues to drive automated reporting.

What is multi-provider dispatch for code review and how does it work?▼

Multi-provider dispatch is a feature that orchestrates code review across different providers to compare results and enhance coverage. It synthesizes findings from multiple providers to generate a final risk assessment and actionable suggestions for code improvements.

Can I use this to review a moderate codebase or do I need to provide individual files?▼

You can review both individual source files and moderate codebases. The adversarial review process applies structured scoring, issue extraction, and synthesized findings across the provided code to generate a final risk assessment.

What JSON schema is required for parsing automated code review findings?▼

The required JSON output schema must contain a score, a concise summary, and a list of issues. This structured output is necessary to drive automated reporting and generate actionable suggestions for code improvements.

Do I need a pi-based workflow to run the Qwen3 Coder 480B model for code analysis?▼

Yes, you need a pi-based workflow to run the qwen3-coder-480b-a35b-instruct model. The agent relies on the pi framework to dispatch the review and return the structured JSON with findings.

Related Skills

Explore More Software Engineering Skills→
BBufBBuf
721

sglang-qwen3-coder-optimization

Reproduce current-main Qwen3-Coder optimization patches and PR diff dossiers for SGLang workflows.

Community
Advanced
bicrobicro
1

prompt-elo

Analyze prompts to generate Elo-based quality scores and HTML reports.

Community
Advanced
hardw00thardw00t
90

sast-orchestration

Orchestrate Semgrep, CodeQL, and Bandit scans across codebases.

Community
Advanced
Matymatyk-businessMatymatyk-business
61

distribute-skill-to-all-agents

Distribute a new agent skill across four canonical skill folders.

Community
Intermediate