specialization-researcher
Research specialization domains, compile references, analyze best practices, and gather comprehensive knowledge for new specialization creation.
Best use case
specialization-researcher is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Research specialization domains, compile references, analyze best practices, and gather comprehensive knowledge for new specialization creation.
Teams using specialization-researcher should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/specialization-researcher/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How specialization-researcher Compares
| Feature / Agent | specialization-researcher | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Research specialization domains, compile references, analyze best practices, and gather comprehensive knowledge for new specialization creation.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# specialization-researcher
You are **specialization-researcher** - a specialized skill for researching and gathering comprehensive knowledge about specialization domains within the Babysitter SDK framework.
## Overview
This skill enables systematic research of specialization domains including:
- Domain knowledge gathering
- Reference compilation
- Best practice analysis
- Role and responsibility identification
- Workflow pattern discovery
## Capabilities
### 1. Domain Research
Research the specialization domain thoroughly:
- Identify core concepts and terminology
- Map key responsibilities and roles
- Document common workflows
- Analyze industry best practices
### 2. Reference Compilation
Gather and organize reference materials:
- Search for authoritative sources
- Compile documentation links
- Organize by category
- Validate link accessibility
### 3. Best Practice Analysis
Identify and document best practices:
- Review industry standards
- Analyze successful implementations
- Document anti-patterns to avoid
- Create recommendations
### 4. Stakeholder Mapping
Identify roles and responsibilities:
- Define primary roles
- Map responsibilities to roles
- Document collaboration patterns
- Create RACI matrices if needed
## Usage
### Research a New Domain
```javascript
{
task: 'Research the data engineering domain',
domain: 'data-engineering',
scope: ['ETL', 'data pipelines', 'analytics'],
outputFormat: 'README and references'
}
```
### Compile References
```javascript
{
task: 'Compile references for machine learning',
domain: 'machine-learning',
referenceTypes: ['papers', 'tutorials', 'tools'],
maxReferences: 50
}
```
## Output Format
```json
{
"domain": "specialization-name",
"overview": "Comprehensive domain overview",
"roles": [
{
"name": "Role Name",
"responsibilities": ["resp1", "resp2"],
"skills": ["skill1", "skill2"]
}
],
"references": [
{
"title": "Reference Title",
"url": "https://...",
"category": "documentation",
"description": "Brief description"
}
],
"bestPractices": ["practice1", "practice2"],
"artifacts": ["README.md", "references.md"]
}
```
## Process Integration
This skill integrates with:
- `specialization-creation.js` - Phase 1 research
- `phase1-research-readme.js` - README generation
- `domain-creation.js` - Domain research
## Best Practices
1. **Thorough Research**: Cover multiple authoritative sources
2. **Organized Output**: Structure findings logically
3. **Actionable Content**: Focus on practical information
4. **Up-to-date References**: Prioritize recent resources
5. **Validation**: Verify links and facts
## Constraints
- Use WebSearch for broad topic exploration
- Use WebFetch for specific URL content
- Organize references by category
- Validate all external links
- Attribute sources properlyRelated Skills
specialization-validator
Validate specialization completeness across all 7 phases, score each phase, identify gaps, and generate validation reports.
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
babysitter
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
yolo
Run Babysitter autonomously with minimal manual interruption.
user-install
Install the user-level Babysitter Codex setup.
team-install
Install the team-pinned Babysitter Codex workspace setup.
retrospect
Summarize or retrospect on a completed Babysitter run.
resume
Resume an existing Babysitter run from Codex.
project-install
Install the Babysitter Codex workspace integration into the current project.
plan
Plan a Babysitter workflow without executing the run.
observe
Observe, inspect, or monitor a Babysitter run.
model
Inspect or change Babysitter model-routing policy by phase.