AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

ULW-Research — Maximum-Saturation Research

A research orchestrator that fans parallel explore/librarian/browsing workers across your codebase, the web, official docs and OSS repos, recursively expands every lead, and ships a fully cited PDF/DOCX report.

AutomationAdvanced★ 67,531⑂ 5,507AI score 9/10Last updated: Aug 9, 2026

What it does

  • Decomposes the question into 3+ orthogonal axes and proposes the final deliverable format (PDF + DOCX by default) and template before any searching starts.
  • Launches the entire first wave at once — codebase explorers, web librarians, browsing agents for blocked pages, and repo deep-divers — with a minimum-worker table per query scope.
  • Reads each worker's mandatory ## EXPAND tail and immediately spawns expansion waves per lead, stopping only on zero unchecked leads, 3 barren waves, or depth 5.
  • Keeps an auditable, real-time session journal: intent-diff.md, claim-graph.md, observation-manifest.md, verification-economics.md, excursion-log.md.
  • Proves or refutes contested, undocumented, or performance claims by actually running code; every sentence in the deliverable carries a citation or a verification artifact, and the delivery ends with a source-count/runtime briefing.

Who it's for

  • Anyone doing research where a wrong claim is expensive: legal, medical, financial, procurement, or public-facing work.
  • Engineers who need documented technology decisions (library comparisons, architecture choices) with evidence trails.
  • Users on harnesses that support parallel subagents (OMO / Codex / OpenCode) who want deep investigation automated.

Examples

  1. /ulw-research compare three payment gateways → per-axis workers cover pricing, API docs, incident history, and real-world reviews, returning a cited comparison in PDF + DOCX.
  2. ulw-research exhaustively map session-expiry handling in this repo → grep variants, structural search, LSP references, and git log -S history (including deleted code) cross-validated into file:line evidence.
  3. ultradebate: is this benchmark claim true? → red-team members attack claim quality and source independence while contested points get settled by executed verification scripts.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/HEAD/packages/shared-skills/skills/ulw-research/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the packages/shared-skills/skills/ulw-research folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/code-yeongyu-ulw-research/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/code-yeongyu/oh-my-openagent.git /tmp/oh-my-openagent && mkdir -p ~/.claude/skills && cp -r /tmp/oh-my-openagent/packages/shared-skills/skills/ulw-research ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open your terminal.
  2. Clone the repo: git clone https://github.com/code-yeongyu/oh-my-openagent.git /tmp/oh-my-openagent
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r /tmp/oh-my-openagent/packages/shared-skills/skills/ulw-research ~/.claude/skills/
  5. Verify ~/.claude/skills/ulw-research/SKILL.md exists.
  6. Restart Claude Code and trigger it explicitly with /ulw-research <topic> or "do deep ulw-research on ...".
  7. Note: it shines when your harness exposes parallel subagent tools and the companion skills (ulw-loop, ultimate-browsing). Without them it degrades to a single-agent run, and each full run can consume a lot of time and tokens.
View source on GitHub ↗License: NOASSERTION