Migrate subagent roles to skills and role definitions

Summary

Before removing the subagent role system, migrate the useful parts to skills and role definitions. Each SubagentRole (WebCrawler, CodeReviewer, DataExtractor, Researcher) represents a useful pattern that should be preserved.

Current SubagentRoles to Migrate

WebCrawler

Tools: web_search, read_webpages, search_codebase Model: claude-3-haiku (fast/cheap) Purpose: Quick web research

Migrate to: Omni/Agent/Skills/shared/web-research/SKILL.md

---
name: web-research
description: Research a topic using web search. Use when you need to find current information, verify facts, or explore a topic online.
---

# Web Research

## Process

1. Formulate search queries - be specific, try multiple phrasings
2. Use `web_search` to find relevant sources
3. Use `read_webpages` to extract content from top 3-5 results
4. Synthesize findings, always cite sources with URLs

## Guidelines

- Be EFFICIENT - extract key facts, don't save full page contents
- Limit to 3-5 most relevant sources
- Work iteratively: search → skim → read best 2-3 → synthesize
- ALWAYS cite sources - every claim needs a URL
- Stop when you have sufficient information

CodeReviewer

Tools: read_file, search_codebase, search_and_read, run_bash Model: claude-sonnet-4 Purpose: Thorough code analysis

Migrate to: Omni/Agent/Roles/Reviewer.md (already planned in t-307)

The Reviewer role covers code review. The skill for code review process:

Omni/Agent/Skills/shared/code-review/SKILL.md

---
name: code-review
description: Review code changes for quality, correctness, and conventions. Use when asked to review a PR, diff, or code changes.
---

# Code Review

<role:reviewer>
Review the code with focus on:

1. **Correctness**: Does it do what it's supposed to?
2. **Testing**: Are there tests? Do they cover edge cases?
3. **Conventions**: Does it follow project patterns?
4. **Security**: Any obvious vulnerabilities?
5. **Performance**: Any obvious inefficiencies?

Use `search_codebase` to understand existing patterns.
Use `run_bash` to run tests if needed.

Provide specific, actionable feedback with file:line references.
</role>

DataExtractor

Tools: read_webpages, read_file, search_codebase Model: claude-3-haiku Purpose: Structured data extraction

Migrate to: Omni/Agent/Skills/shared/data-extraction/SKILL.md

---
name: data-extraction
description: Extract structured data from web pages or documents. Use when you need to pull specific information into a structured format.
---

# Data Extraction

## Process

1. Identify the source (URL or file path)
2. Determine what data to extract (fields, format)
3. Read the source content
4. Extract into structured format (JSON, table, etc.)

## Output Format

Return extracted data as JSON:
\`\`\`json
{
  "source": "url or file",
  "extracted_at": "timestamp",
  "data": { ... }
}
\`\`\`

Researcher

Tools: web_search, read_webpages, read_file, search_codebase, search_and_read Model: claude-sonnet-4 Purpose: General research

Migrate to: Omni/Agent/Skills/shared/research/SKILL.md

---
name: research
description: Deep research on a topic combining web sources and local knowledge. Use for thorough investigation requiring multiple sources.
---

# Research

## Process

1. Clarify the research question
2. Search local codebase/files for existing knowledge
3. Search web for external sources
4. Cross-reference and synthesize findings
5. Document with citations

## Output Format

\`\`\`json
{
  "summary": "Brief overall summary",
  "confidence": 0.85,
  "findings": [
    {
      "claim": "Key insight",
      "source_url": "https://...",
      "source_name": "Source"
    }
  ],
  "caveats": "Limitations or uncertainties"
}
\`\`\`

Acceptance Criteria

• [ ] web-research skill created
• [ ] code-review skill created (uses <role:reviewer>)
• [ ] data-extraction skill created
• [ ] research skill created
• [ ] Each skill captures the essence of the original subagent role