aif-loop

Automate iterative refinement of technical artifacts with quality-gated workflows.

Updated May 16, 2026
One-click install
npx skills add https://github.com/vulikjulik/DeepLom --skill aif-loop-vulikjulik
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: aif-loop
Source: https://github.com/vulikjulik/DeepLom/tree/main/.opencode/skills/aif-loop
Command: npx skills add https://github.com/vulikjulik/DeepLom --skill aif-loop-vulikjulik

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Manually iterating on technical artifacts like API specs, code, or documentation to meet quality standards is time-consuming and inconsistent. This Skill automates the end-to-end refinement workflow, eliminating repetitive manual review and ensuring artifacts meet defined quality criteria before delivery.

Core Features & Use Cases

  • Strict Multi-Phase Iteration Loop: Executes structured PLAN, PRODUCE, PREPARE, EVALUATE, CRITIQUE, and REFINE phases with parallel execution for speed, ensuring every iteration is focused on passing quality gates.
  • Persistent State Tracking: Saves all loop state to disk, allowing you to pause and resume refinement sessions at any time without losing progress.
  • Configurable Quality Rules: Supports custom evaluation criteria and thresholds for different artifact types (API specs, code, docs, config), with built-in templates for common use cases.
  • Use Case: A backend developer can use this Skill to iteratively refine an OpenAPI specification, automatically checking for missing endpoints, invalid schemas, and missing examples until the spec passes all required quality checks.

Quick Start

Use the aif-loop skill to iteratively refine your OpenAPI 3.1 specification until it passes all required quality checks for endpoints, schemas, and examples.

Frequently Asked Questions about aif-loop

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

FAQPage Schema
How do I automate iterative refinement for technical artifacts like API specifications?

You can automate iterative refinement for API specifications by running a structured multi-phase reflex loop that executes PLAN, PRODUCE, EVALUATE, CRITIQUE, and REFINE phases until the artifact passes all configured quality gates.

What is quality-gated artifact evaluation for source code and configuration files?

Quality-gated artifact evaluation is an automated workflow process that checks technical artifacts like source code and configuration files against configurable rules, executing parallel checks to ensure they meet defined quality criteria before delivery.

How do I resume an artifact refinement session after pausing it?

You can resume an artifact refinement session through persistent state tracking, which automatically saves all loop state to disk during execution, allowing you to pause and restart refinement workflows at any time without losing progress.

Can I configure custom quality rules for different artifact types like documentation and code?

Yes, you can configure custom evaluation rules and thresholds for different artifact types including API specs, source code, technical documentation, and configuration files, with built-in templates available for common use cases.

When does the iterative refinement loop stop processing an artifact?

The iterative refinement loop stops automatically when specific stop conditions are met, which include achieving the configured quality threshold, reaching iteration limits, or detecting an absence of major issues during the evaluation phase.

What is the best way to iteratively check an OpenAPI specification for missing endpoints and invalid schemas?

The best way to check an OpenAPI specification is to use an automated quality-gated refinement loop that iteratively evaluates the spec for missing endpoints, invalid schemas, and missing examples until all required quality checks pass.