vc-autoresearch

Coordinate gap-finding, fix, and verification loops until metrics improve.

1.1k|223|Updated May 27, 2026
One-click install
npx skills add https://github.com/withkynam/vibecode-pro-max-kit --skill vc-autoresearch-withkynam
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: vc-autoresearch
Source: https://github.com/withkynam/vibecode-pro-max-kit/tree/main/.claude/skills/vc-autoresearch
Command: npx skills add https://github.com/withkynam/vibecode-pro-max-kit --skill vc-autoresearch-withkynam

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This reusable loop primitive coordinates a structured workflow that finds gaps, writes reports, applies fixes, and repeats until metrics improve or a cap is reached, enabling reliable quality improvements across PVL/EVL/harness scenarios.

Core Features & Use Cases

  • Unified loop orchestration: coordinates gap discovery, fix application, guard checks, and re-verification across multiple phases.
  • PVL/EVL compatibility: designed to drive plan-validate-fix and execute-validate-fix cycles with shared bookkeeping.
  • References-driven guidance: ships with canonical loop protocol docs and harness domain configuration for immediate deployment.

Quick Start

Initiate an autoresearch run against your corpus to perform the gap-finding, fix, and verify loop across PVL/EVL workflows.

Frequently Asked Questions about vc-autoresearch

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

FAQPage Schema
How do I automate iterative quality loops for AI agents?

A self-contained autoresearch loop automates gap discovery, report writing, issue fixing, and outcome rechecking until metrics improve or a cap is reached. It enforces structured iteration reporting and deterministic configurations for repeatable improvements.

What is an autoresearch loop in AI agent workflow orchestration?

An autoresearch loop is a structured workflow orchestration primitive that finds gaps, writes reports, applies fixes, and repeats until quality metrics improve. It serves as shared bookkeeping for multi-phase plan-validate-fix and execute-validate-fix cycles.

Does this iterative quality loop support PVL and EVL workflows?

Yes, the loop explicitly drives plan-validate-fix (PVL) and execute-validate-fix (EVL) cycles. It provides shared bookkeeping and unified orchestration across these phases for consistent quality improvements.

How do I ensure repeatable improvements when fixing AI agent outputs?

You ensure repeatable improvements by enforcing structured iteration reporting, guard checks, and deterministic configurations during the fix and recheck phases. This prevents regression and guarantees quality metrics trend upward until targets are met.

What's the best way to orchestrate multi-phase quality validation for AI agents?

The best way is using a shared loop primitive that coordinates gap discovery, fix application, and guard checks across multiple phases. This approach maintains consistent bookkeeping between validation cycles to ensure reliable outcomes.

When should I cap an automated AI agent quality improvement loop?

You should cap the loop when quality metrics reach the desired target or when the maximum iteration limit is hit. Guard checks enforce these boundaries to prevent infinite cycles and ensure the workflow terminates deterministically.