smartworldarafath/Google_Antigravity_Plugins / plugins/antigravity-setup/skills/claude-automation-recommender
claude-automation-recommender
VerifiedAnalyze a codebase and recommend Google Antigravity automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Google Antigravity setup, mentions improving Google Antigravity workflows, asks how to first set up Google Antigravity for a project, or wants to know what Google Antigravity features they should use.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.9 KB |
| references/hooks-patterns.md | markdown | 6.5 KB |
| references/mcp-servers.md | markdown | 8.2 KB |
| references/plugins-reference.md | markdown | 3.0 KB |
| references/skills-reference.md | markdown | 9.5 KB |
| references/subagent-templates.md | markdown | 5.2 KB |
references/subagent-templates.md
View on GitHub# Subagent Recommendations
Subagents are specialized Antigravity instances that run in parallel, each with their own context window and tool access. They're ideal for focused reviews, analysis, or generation tasks.
**Note**: These are common patterns. Design custom subagents based on the codebase's specific review and analysis needs.
## Code Review Agents
### code-reviewer
**Best for**: Automated code quality checks on large codebases
| Recommend When | Detection |
|----------------|-----------|
| Large codebase (>500 files) | File count |
| Frequent code changes | Active development |
| Team wants consistent review | Quality focus |
**Value**: Runs code review in parallel while you continue working
**Model**: sonnet (balanced quality/speed)
**Tools**: view_file, run_command, run_command, run_command
---
### security-reviewer
**Best for**: Security-focused code review
| Recommend When | Detection |
|----------------|-----------|
| Auth code present | `auth/`, `login`, `session` patterns |
| Payment processing | `stripe`, `payment`, `billing` patterns |
| User data handling | `user`, `profile`, `pii` patterns |
| API keys in code | Environment variable patterns |
**Value**: Catches OWASP vulnerabilities, auth issues, data exposure
**Model**: sonnet
**Tools**: view_file, run_command, run_command (read-only for safety)
---
### test-writer
**Best for**: Generating comprehensive test coverage
| Recommend When | Detection |
|----------------|-----------|
| Low test coverage | Few test files vs source files |
| Test suite exists | `tests/`, `__tests__/` present |
| Testing framework configured | jest, pytest, vitest in deps |
**Value**: Generates tests matching project conventions
**Model**: sonnet
**Tools**: view_file, write_to_file, run_command, run_command
---
## Specialized Agents
### api-documenter
**Best for**: API documentation generation
| Recommend When | Detection |
|----------------|-----------|
| REST endpoints | Express routes, FastAPI paths |
| GraphQL schema | `.graphql` files |
| OpenAPI exists | `openapi.yaml`, `swagger.json` |
| Undocumented APIs | Routes without docs |
**Value**: Generates OpenAPI specs, endpoint documentation
**Model**: sonnet
**Tools**: view_file, write_to_file, run_command, run_command
---
### performance-analyzer
**Best for**: Finding performance bottlenecks
| Recommend When | Detection |
|----------------|-----------|
| Database queries | ORM usage, raw SQL |
| High-traffic code | API endpoints, hot paths |
| Performance complaints | User reports slowness |
| Complex algorithms | Nested loops, recursion |
**Value**: Finds N+1 queries, O(n²) algorithms, memory leaks
**Model**: sonnet
**Tools**: view_file, run_command, run_command, run_command
---
### ui-reviewer
**Best for**: Frontend accessibility and UX review
| Recommend When | Detection |
|----------------|-----------|
| React/Vue/Angular | Frontend framework detected |
| Component library | `components/` directory |
| User-facing UI | Not just API project |
**Value**: Catches accessibility issues, UX problems, responsive design gaps
**Model**: sonnet
**Tools**: view_file, run_command, run_command
---
## Utility Agents
### dependency-updater
**Best for**: Safe dependency updates
| Recommend When | Detection |
|----------------|-----------|
| Outdated deps | `npm outdated` has results |
| Security advisories | `npm audit` warnings |
| Major version behind | Significant version gaps |
**Value**: Updates dependencies incrementally with testing
**Model**: sonnet
**Tools**: view_file, write_to_file, run_command, run_command
---
### migration-helper
**Best for**: Framework/version migrations
| Recommend When | Detection |
|----------------|-----------|
| Major upgrade needed | Framework version very old |
| Breaking changes coming | Deprecation warnings |
| Refactoring planned | Architectural changes |
**Value**: Plans and executes migrations incrementally
**Model**: opus (complex reasoning needed)
**Tools**: view_file, write_to_file, run_command, run_command, run_command
---
## Quick Reference: Detection → Recommendation
| If You See | Recommend Subagent |
|------------|-------------------|
| Large codebase | code-reviewer |
| Auth/payment code | security-reviewer |
| Few tests | test-writer |
| API routes | api-documenter |
| Database heavy | performance-analyzer |
| Frontend components | ui-reviewer |
| Outdated packages | dependency-updater |
| Old framework version | migration-helper |
---
## Subagent Placement
Subagents go in `.agents/agents/`:
```
.claude/
└── agents/
├── code-reviewer.md
├── security-reviewer.md
└── test-writer.md
```
---
## Model Selection Guide
| Model | Best For | Trade-off |
|-------|----------|-----------|
| **haiku** | Simple, repetitive checks | Fast, cheap, less thorough |
| **sonnet** | Most review/analysis tasks | Balanced (recommended default) |
| **opus** | Complex migrations, architecture | Thorough, slower, more expensive |
---
## Tool Access Guide
| Access Level | Tools | Use Case |
|--------------|-------|----------|
| view_file-only | view_file, run_command, run_command | Reviews, analysis |
| Writing | + write_to_file | Code generation, docs |
| Full | + run_command | Migrations, testing |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |