Add 28 diverse agent profiles for multi-project support

[khaliqgant]

Summary

• Adds 28 new generic agent profiles to accommodate different project types
• Profiles organized into 6 categories for easy discovery
• Each profile includes YAML frontmatter and markdown body with persona, principles, and communication patterns

New Profiles by Category

Backend/Infrastructure (6):

• backend - General backend development (APIs, services, databases)
• database - Database design, queries, migrations, optimization
• api-designer - REST/GraphQL API design and implementation
• debugger - Systematic bug investigation and root cause analysis
• refactorer - Code refactoring, technical debt reduction
• performance - Performance optimization, profiling, bottleneck analysis

QA/Testing/Security (5):

• tester - Test writing (unit, integration, e2e)
• security - Security auditing, vulnerability assessment
• qa - Quality assurance, testing protocols
• accessibility - A11y auditing and WCAG compliance
• validator - Input validation, data integrity checks

Documentation/Communication (5):

• documentor - Technical documentation, API docs, READMEs
• explainer - Code explanation, architecture walkthroughs
• reviewer - Code review (direct invocation version)
• researcher - Research tasks, codebase exploration
• architect - System design, architecture decisions

DevOps/Operations (6):

• devops - CI/CD, deployment, infrastructure as code
• devops-ci - CI/CD pipeline specialist
• migrator - Data migrations, schema changes, version upgrades
• deployer - Deployment automation, release management
• monitor - Monitoring setup, alerting, observability
• sysadmin - System administration, configuration management

Specialized/Niche (6):

• data - Data processing, ETL, pipelines
• mobile - Mobile development (React Native, iOS, Android)
• cli - CLI tool development, command-line interfaces
• integrator - Third-party integrations, APIs, webhooks
• prototyper - Rapid prototyping, MVPs, proof of concepts
• fixer - Quick fixes, hotfixes, urgent bug patches

Test plan

• Verify each profile has valid YAML frontmatter
• Spot-check a few profiles for quality and consistency
• Test spawning agents with new profiles

🤖 Generated with Claude Code

[my-senior-dev-pr-review]

🤖 My Senior Dev — Analysis Complete

👤 For @khaliqgant

📁 Expert in src/dashboard/react-components/ (7 edits) • ⚡ 32nd PR this month

View your contributor analytics →

---

📊 35 files reviewed • 3 high risk • 15 need attention

🚨 High Risk:

• .claude/agents/accessibility.md — Lack of testing and validation for critical accessibility implementations.
• .claude/agents/api-designer.md — Critical for maintaining API quality, but lacks validation mechanisms.
• .claude/agents/security.md — Essential for application security, lacking validation for implemented protocols.

⚠️ Needs Attention:

• .claude/agents/architect.md — Offers foundational guidelines but lacks testing verification.
• .claude/agents/cli.md — Specifies critical CLI tool development principles but lacks tests.
• +1 more concerns...

---

🚀 Open Interactive Review →

The full interface unlocks features not available in GitHub:

• 💬 AI Chat — Ask questions on any file, get context-aware answers
• 🔍 Smart Hovers — See symbol definitions and usage without leaving the diff
• 📚 Code Archeology — Understand how files evolved over time (/archeology)
• 🎯 Learning Insights — See how this PR compares to similar changes

---

💬 Chat here: @my-senior-dev explain this change — or try @chaos-monkey @security-auditor @optimizer @skeptic @junior-dev

📖 View all 12 personas & slash commands

You can interact with me by mentioning @my-senior-dev in any comment:

In PR comments or on any line of code:

• Ask questions about the code or PR
• Request explanations of specific changes
• Get suggestions for improvements

Slash commands:

• /help — Show all available commands
• /archeology — See the history and evolution of changed files
• /profile — Performance analysis and suggestions
• /expertise — Find who knows this code best
• /personas — List all available AI personas

AI Personas (mention to get their perspective):

Persona	Focus
@chaos-monkey 🐵	Edge cases & failure scenarios
@skeptic 🤨	Challenge assumptions
@optimizer ⚡	Performance & efficiency
@security-auditor 🔒	Security vulnerabilities
@accessibility-advocate ♿	Inclusive design
@junior-dev 🌱	Simple explanations
@tech-debt-collector 💳	Code quality & shortcuts
@ux-champion 🎨	User experience
@devops-engineer 🚀	Deployment & scaling
@documentation-nazi 📚	Documentation gaps
@legacy-whisperer 🏛️	Working with existing code
@test-driven-purist ✅	Testing & TDD

For the best experience, view this PR on myseniordev.com — includes AI chat, file annotations, and interactive reviews.

[khaliqgant]

AI Conversation Transcript

👤 khaliqgant

Look up the Claude sub agent types. Is agent type: agent a valid parameter in the front matter?

🤖 AI Assistant

The search results indicate that the .claude/agents directory contains several agent profiles, but it does not explicitly show the valid parameters for the agentType. Here are some of the agent files found:

1. lead.md
2. frontend.md
3. shadow-active.md
4. shadow-auditor.md
5. shadow-reviewer.md

To determine if agent type: agent is valid, we would need to look at the contents of these files to find the defined agentType parameters.

Would you like me to check the contents of one of these specific files to find more details?

---

From My Senior Dev

[khaliqgant]

AI Conversation Update

Continuation of previous conversation...

👤 khaliqgant

Fetch the Claude documentation to see if it is a valid front matter param

🤖 AI Assistant

I found some relevant documentation related to Claude agents, but it appears that the specific front matter parameters, including agentType, are not explicitly detailed in the results. However, I can summarize some useful links:

1. Create custom subagents - Claude Code Docs: This documentation discusses creating custom subagents and may contain examples relevant to defining agent types.

2. How to Use Claude Code: A Guide to Slash Commands, Agents, Skills, and Plug-Ins: This guide mentions the creation of user-designed sub-agents, which could provide insights into the expected parameters.

3. Agent SDK overview - Claude Docs: This overview may contain useful information about building agents and their configurations.

4. The Complete Guide to Building Agents with the Claude Agent SDK: This guide might provide in-depth information about creating agents and what parameters are accepted.

To confirm if agentType: agent is a valid parameter, I recommend checking the first link about creating custom subagents or the Agent SDK overview, as they are likely to have the most relevant information regarding agent types and their configurations.

If you need further exploration or specific details from any of these links, let me know!

---

From My Senior Dev

[khaliqgant]

AI Conversation Update

Continuation of previous conversation...

👤 khaliqgant

Link me to the docs

🤖 AI Assistant

Here are the links to the relevant Claude documentation:

1. Create custom subagents - Claude Code Docs: Create custom subagents

2. How to Use Claude Code: A Guide to Slash Commands, Agents, Skills, and Plug-Ins: How to Use Claude Code

3. Agent SDK overview - Claude Docs: Agent SDK overview

4. The Complete Guide to Building Agents with the Claude Agent SDK: The Complete Guide to Building Agents

Feel free to explore these links for more information regarding agent types and other configuration parameters!

---

From My Senior Dev