skills.rest
romanticamaj
romanticamajCOMMUNITY
Explore all skills by this author →
GitHub

omni-research

Run multi-cycle web research with verified citations into structured knowledge base files.

8|2|Updated Mar 30, 2026
Search Tags:#web-research#knowledge-base#research-automation#source-verification#brief-generation#autonomous-research#background-agent
One-click install
npx skills add https://github.com/romanticamaj/omni-research --skill omni-research
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: omni-research
Source: https://github.com/romanticamaj/omni-research/tree/main/skills/omni-research
Command: npx skills add https://github.com/romanticamaj/omni-research --skill omni-research

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Performing reliable web research with verifiable citations is time-consuming and error-prone when done in a single prompt. Omni-Research runs a multi-cycle autonomous loop that scouts sources, verifies claims by reading pages, synthesizes findings, and accumulates a growing knowledge base with traceable evidence so users get reproducible, source-backed research rather than one-shot, hallucinated answers.

Core Features & Use Cases

  • Interactive setup and configuration: Guided prompts collect topic, type (product/marketing/production/research), seed sources, research lines, and scope before launching an autonomous run.
  • Multi-phase autonomous loop: Phase 0 source scouting, Phase 1 seed/source mining, Phase 2 hypothesis-driven cycles with periodic discovery, scoring, and gate decisions (PROCEED/REFINE/PIVOT).
  • File-driven orchestration and steering: Generates program.md, research.md, experiments.tsv, steer.md and runs a background agent that checks steer.md for mid-run redirects; supports recovery and BRIEF.md generation from saved outputs.
  • Strict source verification and inline citations: Requires WebFetch confirmation for every cited claim, scores sources for authority/recency/relevance, and flags unverified or conflicting evidence.
  • Use cases: product-market research, go-to-market planning, technical literature reviews, competitive analysis, and automated briefing generation for stakeholders.

Quick Start

Start a background research run for the topic "impact of AI on elder care" by invoking /omni-research and answering the setup prompts.

Frequently Asked Questions about omni-research

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

FAQPage Schema
How do I automate web research with verified inline citations instead of single-prompt answers?▼

Autonomous multi-cycle web research automates source scouting, uses WebFetch to verify every cited claim, and synthesizes findings into a structured knowledge base, preventing the hallucinated answers typical of single-prompt research.

What is the best way to conduct iterative hypothesis testing for academic literature reviews?▼

Iterative hypothesis testing uses a multi-phase autonomous loop with periodic discovery, scoring, and gate decisions like PROCEED, REFINE, or PIVOT to progressively refine academic literature reviews and accumulate traceable evidence.

How do I start an autonomous background research run for product-market or competitive analysis?▼

Start an autonomous background research run by invoking the skill and answering guided setup prompts that collect your topic, research type, seed sources, research lines, and scope before the multi-cycle orchestration begins.

Can I redirect or steer an autonomous research agent mid-run without restarting the process?▼

Yes, you can steer an autonomous research agent mid-run by updating the steer.md file, which the background agent continuously checks for mid-run redirects, allowing you to change research direction without restarting.

Does automated web research work for generating stakeholder briefings from multiple sources?▼

Automated web research accumulates a growing knowledge base with traceable evidence across multiple sources, which can be directly synthesized into a BRIEF.md file from templates for stakeholder briefing generation.

What file artifacts are generated when running an autonomous web research workflow?▼

An autonomous web research workflow generates file-based program and research artifacts, specifically program.md, research.md, experiments.tsv, and steer.md, to orchestrate the run and document progressive findings.

Related Skills

Explore More Education & Research Skills→
b566776b566776

bmad-market-research

Define market research scope, methodology, and data sources with web-verified evidence.

Community
Advanced
aviskaaraviskaar
6

whitepaper-engine

Generate cross-functional whitepapers from topic selection to distribution planning.

Official
Advanced
gagan114662gagan114662

researcher-hand-skill

Conduct autonomous deep research and produce structured, fact-checked reports.

Community
Advanced
eggent-aieggent-ai
330

gemini

Run non-interactive Q&A, summarization, and content generation via the Gemini CLI.

Official
Intermediate