research

# Research Skill

> **Quick Ref:** Deep codebase exploration with multi-angle analysis. Output: `.agents/research/*.md`

**YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it.**

## Execution Steps

Given `/research <topic>`:

### Step 1: Create Output Directory
```bash
mkdir -p .agents/research
```

### Step 2: Check Prior Art

**First, inject existing knowledge (if ao available):**
```bash
ao inject <topic> 2>/dev/null
```

Search for existing research on this topic:
```bash
ls -la .agents/research/ 2>/dev/null | grep -i "<topic>" || echo "No prior research found"
```

Also use Grep to search `.agents/` for related content. Check TEMPERED learnings:
```bash
ls -la .agents/learnings/ .agents/patterns/ 2>/dev/null | head -10
```

### Step 3: Launch Explore Agent

**YOU MUST USE THE TASK TOOL NOW.** Call it with these exact parameters:

```
Tool: Task
Parameters:
  subagent_type: "Explore"
  description: "Research: <topic>"
  prompt: |
    Thoroughly investigate: <topic>

    Search strategy:
    1. Glob for relevant files (*.md, *.py, *.ts, *.go, etc.)
    2. Grep for keywords related to <topic>
    3. Read key files and understand the architecture
    4. Check docs/ and .agents/ for existing documentation

    Return a detailed report with:
    - Key files found (with paths)
    - How the system works
    - Important patterns or conventions
    - Any issues or concerns

    Cite specific file:line references for all claims.
```

### Step 4: Dispatch Research Quality Swarm (Optional)

**For thorough research, launch parallel quality validation agents:**

```
Launch ALL FOUR agents in parallel (single message, 4 Task tool calls):

Tool: Task
Parameters:
  subagent_type: "agentops:coverage-expert"
  model: "haiku"
  description: "Coverage validation"
  prompt: |
    Validate research breadth for: <topic>
    Research artifact: .agents/research/YYYY-MM-DD-<topic-slug>.md

    Check: Did we look everywhere we should? Any unexplored areas?
    Return: Coverage score