autoresearch

Automate a stateful validator-gated research loop with native-hook persistence.

1|Updated Mar 17, 2025
One-click install
npx skills add https://github.com/ozby/node-pubsub --skill autoresearch-ozby
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: autoresearch
Source: https://github.com/ozby/node-pubsub/tree/main/.codex/skills/autoresearch
Command: npx skills add https://github.com/ozby/node-pubsub --skill autoresearch-ozby

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates the management of a stateful validator-gated research loop with native-hook persistence.

Core Features & Use Cases

  • Stateful loop with optional validation modes (mission-validator-script or prompt-architect-artifact).
  • Persistence of loop state under the .omx/state directory, including completion_artifact_path and mode.
  • Artifact-gated completion with clear guardrails and a repeatable flow.

Quick Start

Launch the autoresearch flow with the selected validation mode and allow the loop to continue until a completion artifact is produced.

Frequently Asked Questions about autoresearch

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

FAQPage Schema
How do I automate a research loop with persistent state and validation?

Automating a research loop with persistent state requires a validator-gated flow that saves progress to a state directory and continues auto-nudging until validated evidence is produced. This ensures the loop persists across interruptions and completes only when an artifact is generated.

What is artifact-gated completion in a stateful workflow?

Artifact-gated completion in a stateful workflow means the loop does not terminate until a completion artifact is produced and validated. The state directory tracks this artifact path, enforcing clear guardrails and a repeatable flow before signaling success.

How do I configure validation modes for a persistent research workflow?

Configuring validation modes for a persistent research workflow involves selecting between a mission-validator-script or prompt-architect-artifact mode during initialization. The chosen mode determines how the loop auto-nudges and validates evidence before allowing completion.

Does the research loop state persist across sessions in the .omx state directory?

Yes, research loop state persists across sessions by saving to a native-hook persistence file under the .omx/state directory. This file stores the completion artifact path and active mode, allowing the workflow to resume exactly where it left off.

When should I use a validator-driven research loop instead of manual research?

Use a validator-driven research loop instead of manual research when your workflow requires configurable validation modes, persistent state across sessions, and auto-nudging until validated evidence exists. It is ideal for complex investigations needing strict guardrails and artifact-based completion.