autoresearch

Persist validator-gated research loops with init-time mode selection.

24|2|Updated Mar 12, 2025
One-click install
npx skills add https://github.com/Orinks/AccessiWeather --skill autoresearch-orinks
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: autoresearch
Source: https://github.com/Orinks/AccessiWeather/tree/main/.codex/skills/autoresearch
Command: npx skills add https://github.com/Orinks/AccessiWeather --skill autoresearch-orinks

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Solves the need for persistent, validator-gated research loops with native-hook persistence.

Core Features & Use Cases

  • Stateful loop with two init-time validation modes: mission-validator-script or prompt-architect-artifact.
  • Persistent state storage at .omx/state/... to survive restarts and ensure traceability.
  • Completion is artifact-gated, enabling controlled progression based on validator outcomes.

Quick Start

Initialize with a chosen validation mode, then run the autoresearch workflow to emit the completion artifact.

Frequently Asked Questions about autoresearch

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

FAQPage Schema
How do I set up persistent research loops with progressive validation?

Persistent research loops are configured by selecting an init-time validation mode, either mission-validator-script or prompt-architect-artifact, which gates task progression using a generated completion artifact.

What is artifact-gated progression in AI research workflows?

Artifact-gated progression is a validation mechanism where a research workflow cannot advance to the next stage until a specific completion artifact is emitted and verified by the chosen validator mode.

How do I save AI workflow state to survive system restarts?

To save AI workflow state across restarts, the system automatically persists its current state natively to a local JSON file at .omx/state/.../autoresearch-state.json, ensuring full traceability and recovery.

Does this validator-gated research workflow support mission-script and prompt-architect modes?

Yes, this validator-gated research workflow supports both mission-validator-script and prompt-architect-artifact modes, initialized at startup to determine how progressive validation is applied across tasks.

When should I use artifact-gated validation for end-to-end research tasks?

Artifact-gated validation should be used for end-to-end research tasks when you require strict, traceable checkpoints, ensuring each phase meets specific validator criteria before advancing to the next step.