dsh-skills/skills/research-deep/SKILL.md

name, description, user-invocable

name	description	user-invocable
research-deep	Read research outline, launch independent agent for each item for deep research. Disable task output.	true

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 (before launching the next batch, ask the user to confirm via ask_user_question)
• Each agent handles items_per_agent items
• Launch one background web-search subagent per batch via the subagent tool (run_in_background: true). Its prompt is the Prompt Template below with the {xxx} variables filled, immediately followed by the research methodology loaded from .agents/skills/research/agents/web-search-agent.md (resolved against the session workspace) with every {RESEARCH_SKILL_DIR} placeholder replaced by the absolute research skill directory. The subagent writes its JSON file itself and returns only a one-line completion note (task output disabled).

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)
• {validator_path}: absolute path to this skill's bundled validate_json.py (this skill's Base directory from <skill_resources> + validate_json.py)

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:
python3 {validator_path} -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 {project_dir}/results/GitHub_Copilot.json

## Field Definitions
Read {project_dir}/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
{project_dir}/results/GitHub_Copilot.json

## Validation
After completing JSON output, run validation script to ensure complete field coverage:
python3 {validator_path} -f {project_dir}/fields.yaml -j {project_dir}/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

Prerequisites

Require python3 with PyYAML. Export RESEARCH_DEEP_SKILL_DIR as this skill's absolute directory (the Base directory from <skill_resources>) on its own line before running the validator, e.g. python3 "$RESEARCH_DEEP_SKILL_DIR/validate_json.py" -f <fields.yaml> -j <result.json>; the launcher fills {validator_path} with that absolute path. (On the Windows shell tool the export is $env:RESEARCH_DEEP_SKILL_DIR = "<path>" on its own line within the same pwsh invocation.)