Research Deep

This automates deep research by spinning up parallel agents for each item in your outline. Point it at an outline.yaml file and it launches independent web search agents in the background, each writing structured JSON output to disk. The setup is clever: it resumes from where you left off, batches work for your approval, and validates output against field definitions. You'd use this when you need to research dozens of similar items (like competitive products or market segments) and want consistent structured data without babysitting each query. The task output is disabled since agents write directly to files, which keeps your terminal clean during long runs.

skills.sh installs: 938
GitHub stars: 2.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add weizhena/deep-research-skills --skill research-deep --agent claude-code

Installs into .claude/skills of the current project.

Files

Research Deep - Deep Research

Trigger

/research-deep

Workflow

Step 1: Auto-locate Outline

Find */outline.yaml file in current working directory, read items list, execution config (including items_per_agent).

Step 2: Resume Check

Check completed JSON files in output_dir
Skip completed items

Step 3: Batch Execution

Batch by batch_size (need user approval before next batch)
Each agent handles items_per_agent items
Launch web-search-agent (background parallel, disable task output)

Parameter Retrieval:

{topic}: topic field from outline.yaml
{item_name}: item's name field
{item_related_info}: item's complete yaml content (name + category + description etc.)
{output_dir}: execution.output_dir from outline.yaml (default: ./results)
{fields_path}: absolute path to {topic}/fields.yaml
{output_path}: absolute path to {output_dir}/{item_name_slug}.json (slugify item_name: replace spaces with _, remove special chars)

Hard Constraint: The following prompt must be strictly reproduced, only replacing variables in {xxx}, do not modify structure or wording.

SKILL.md on GitHub