skills.rest
Tienching
TienchingCOMMUNITY
Explore all skills by this author →
GitHub

autoresearch

Automate a validator-gated research loop with persistent state in .omb/state.

3|Updated Apr 7, 2026
Search Tags:#workflow#research#persistence#state-management#validator#autoresearch
One-click install
npx skills add https://github.com/Tienching/oh-my-codebuddy --skill autoresearch-tienching
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: autoresearch
Source: https://github.com/Tienching/oh-my-codebuddy/tree/main/skills/autoresearch
Command: npx skills add https://github.com/Tienching/oh-my-codebuddy --skill autoresearch-tienching

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Stateful validator-gated research loop with native-hook persistence, enabling continuous alignment and artifact-driven evaluation across sessions.

Core Features & Use Cases

  • Stateful, gated research loop with persistent state in .omb/state
  • Supports mission-validator-script or prompt-architect-artifact validation modes
  • Direct intake and execution flow via deep-interview and autoresearch commands for end-to-end orchestration

Quick Start

Run a clarifying intake with $deep-interview --autoresearch to set mission and evaluator, then start the loop with $autoresearch using the chosen validation mode.

Frequently Asked Questions about autoresearch

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

FAQPage Schema
How do I persist state across multiple research workflow turns?▼

You can persist state across multiple research turns using native-hook persistence that automatically stores mode state and completion artifacts in a dedicated directory.

What is a validator-gated research loop and when do I need it?▼

A validator-gated research loop is a stateful workflow that evaluates research against specific criteria across sessions. You need it for tasks requiring continuous alignment and artifact-driven evaluation.

How do I set up a persistent research workflow with validation?▼

Run a clarifying intake via a deep-interview command to define your mission and evaluator, then initiate the execution loop using your chosen validation mode to start the persistent research workflow.

Can I use a custom mission script for research validation?▼

Yes, you can validate your research using either a custom mission-validator-script or a prompt-architect-artifact mode, ensuring outputs meet your specific gated evaluation criteria.

Does stateful research workflow support continuous alignment across sessions?▼

Stateful research workflows support continuous alignment across sessions by leveraging native-hook persistence to maintain mode state and store completion artifacts between intervals.

What are the limitations of persistent state management for research?▼

Persistent state management for research requires committing to a specific validation mode upfront and depends on a structured deep-intake process, meaning ad-hoc research without defined evaluators is not supported.

Related Skills

Explore More Data & Analytics Skills→
xdkpxdkp

autoresearch

Iterate on a mission using evaluator-driven pass/fail JSON until max-runtime ends.

Community
Intermediate
marcmunoz-unomarcmunoz-uno
3

sciomc

Orchestrate parallel scientist agent workflows to produce cross-validated research reports.

Community
Advanced
YeaChan05YeaChan05

autoresearch

Automate a stateful validator-gated research loop with persistent .omx/state storage.

Community
Intermediate
BetaSBetaS

autoresearch

Manage persistent research workflows with automated validation.

Community
Intermediate