Research DeepSAFE

Structured deep research skill for Claude Code/Open Code/Codex with human-in-the-loop control

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: research-deep
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**:
```python
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 {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:
python ~/.claude/skills/research/validate_json.py -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

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.

[![ModelsAtlas audit: Research Deep](https://modelsatlas.com/skills/weizhena/research-deep/badge.svg)](https://modelsatlas.com/skills/weizhena/research-deep/)

Not your listing, or something out of date? Claim or update your listing.