Our review

Automates deep research by splitting outline items into parallel agent tasks that output validated JSON files according to a schema.

Strengths

Parallel batch execution speeds up research across multiple topics.
Automatic resume skips completed items, avoiding redundant work.
Strict schema validation ensures complete field coverage.
User approval between batches provides control over the process.

Limitations

Requires pre-existing outline.yaml and fields.yaml with exact structure.
Depends on a validation script located at ~/.claude/skills/research/validate_json.py.
Works only in the Claude Code environment.

When to use it

When you need to research many topics in a structured, repeatable way and collect results as JSON.

When not to use it

When you need a quick answer to a single question without the overhead of defining a schema and outline.

Examples

Start deep research from outline

/research-deep

Run and control batch execution

Execute the deep research workflow on the current outline, asking for approval before each batch.

Resume an interrupted research run

Continue the /research-deep run, skipping items already completed in the output directory.

user-invocable: true description: Read research outline, launch independent agent for each item for deep research. Disable task output. allowed-tools: Bash, Read, Write, Glob, WebSearch, Task

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.

Prompt Template:

prompt = f"""## Task
Research {item_related_info}, output structured JSON to {output_path}

## Field Definitions
Read {fields_path} to get all field definitions

## Output Requirements
1. Output JSON according to fields defined in fields.yaml
2. Mark uncertain field values with [uncertain]
3. Add uncertain array at the end of JSON, listing all uncertain field names
4. All field values must be in English

## Output Path
{output_path}

## Validation
After completing JSON output, run validation script to ensure complete field coverage:
python ~/.claude/skills/research/validate_json.py -f {fields_path} -j {output_path}
Task is complete only after validation passes.
"""

One-shot Example (assuming researching GitHub Copilot):

## Task
Research name: GitHub Copilot
category: International Product
description: Developed by Microsoft/GitHub, first mainstream AI coding assistant, ~40% market share, output structured JSON to /home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json

## Field Definitions
Read /home/weizhena/AIcoding/aicoding-history/fields.yaml to get all field definitions

## Output Requirements
1. Output JSON according to fields defined in fields.yaml
2. Mark uncertain field values with [uncertain]
3. Add uncertain array at the end of JSON, listing all uncertain field names
4. All field values must be in English

## Output Path
/home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json

## Validation
After completing JSON output, run validation script to ensure complete field coverage:
python ~/.claude/skills/research/validate_json.py -f /home/weizhena/AIcoding/aicoding-history/fields.yaml -j /home/weizhena/AIcoding/aicoding-history/results/GitHub_Copilot.json
Task is complete only after validation passes.

Step 4: Wait and Monitor

Wait for current batch to complete
Launch next batch
Display progress

Step 5: Summary Report

After all complete, output:

Completion count
Failed/uncertain marked items
Output directory

Agent Config

Background execution: Yes
Task Output: Disabled (agent has explicit output file when complete)
Resume support: Yes

Deep Research Multi-Agent

Recommended for