elicitation

Automate expert agent code self-review and correction across 12 categories.

22|3|Updated Jan 10, 2026
One-click install
npx skills add https://github.com/fusengine/agents --skill elicitation-fusengine
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: elicitation
Source: https://github.com/fusengine/agents/tree/main/plugins/ai-pilot/skills/elicitation
Command: npx skills add https://github.com/fusengine/agents --skill elicitation-fusengine

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables expert agents to automatically review and correct their own code before it undergoes final validation, significantly reducing errors and improving code quality.

Core Features & Use Cases

  • Automated Code Review: Analyzes code for common issues across quality, security, performance, and architecture.
  • Self-Correction: Guides the expert agent to fix identified problems before submission.
  • Use Case: After an expert agent writes a new API endpoint, this skill will analyze the code for security vulnerabilities, performance bottlenecks, and adherence to SOLID principles, then prompt the agent to fix any issues found.

Quick Start

Run the elicitation skill after the execute phase to have the expert agent self-review its code.

Frequently Asked Questions about elicitation

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

FAQPage Schema
How do I automate code review and self-correction for an expert agent?

Automated code review and self-correction for an expert agent is handled by applying a catalog of 75 elicitation techniques across 12 categories, analyzing code for quality, security, and performance before submission.

What security and architecture issues can automated self-review detect?

Automated self-review detects security vulnerabilities, performance bottlenecks, and architecture issues by analyzing code against SOLID principles across quality, security, performance, and maintainability categories.

Can I run elicitation in different modes during the execute phase?

Elicitation can run in manual, auto, or skip modes during the execute phase, allowing you to control how the expert agent analyzes code for data integrity, concurrency, and observability before validation.

How do I ensure code is corrected before sniper validation?

To ensure code is corrected before sniper validation, the skill integrates with the APEX workflow, guiding the expert agent to fix identified problems in testing, documentation, and UX immediately after the execute phase.

What's the best way to review API endpoints for vulnerabilities and performance?

The best way to review API endpoints for vulnerabilities and performance is using self-correction techniques that analyze code for security flaws, performance bottlenecks, and adherence to SOLID principles, prompting fixes automatically.