From liti-garage
Run the appropriate reviewer agents based on the mode and stack.
npx claudepluginhub litisaude/garage --plugin liti-garageThis skill uses the workspace's default tool permissions.
Run the appropriate reviewer agents based on the mode and stack.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).
Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.
Run the appropriate reviewer agents based on the mode and stack.
/review plan — Review a plan/feature description before coding. Produces a requirements checklist./review code — Review actual code changes. Produces a violation report./review code backend — Limit code review to backend reviewers only./review code frontend — Limit code review to frontend reviewers only.planWhen: Before coding starts. The user has a feature description or plan draft.
What it does: Launches two agents in parallel — one for engineering standards (@agents/plan-requirements-reviewer.md) and one for business/product readiness (@agents/business-readiness-reviewer.md). Together they produce a comprehensive review covering both technical requirements and business blind spots. No code scanning.
Behavior:
subagent_type: "general-purpose":
@agents/plan-requirements-reviewer.md (engineering standards)@agents/business-readiness-reviewer.md (business/product readiness)codeWhen: After coding. The user has made changes and wants them reviewed.
What it does: Launches specialized reviewer agents in parallel to scan actual code for violations.
Behavior:
Determine scope: Look at the files the user wants reviewed. If no files are specified, use recent git changes (git diff --name-only HEAD~1).
Detect stack (if not explicitly provided):
.py, .go, .java, .rs files, models/, api/, services/, domains/, background_jobs/.tsx, .jsx, .ts, .js, .swift, .kt, .dart files, components/, screens/, pages/, hooks/Launch reviewers in parallel using the Task tool with subagent_type: "general-purpose":
For backend code, launch two parallel agents:
@agents/production-hardening-reviewer.md scoped to the target files@agents/audit-compliance-reviewer.md scoped to the target filesFor frontend/mobile code, launch one agent:
@agents/analytics-coverage-reviewer.md scoped to the target filesMerge results: Combine the outputs from all agents into a single report.
# Plan Review: [Feature Name]
## Stack: [Backend / Frontend / Full Stack]
## Engineering Requirements
### [Category]
- ⚠️ **[Requirement]**: Why it applies and what the plan should specify
- ✅ **[Requirement]**: Already addressed in the plan
## Business & Product Readiness
### [Pillar Name]
- ⚠️ **[Requirement]**: Why it applies and what the plan should specify
- ✅ **[Requirement]**: Already addressed in the plan
## Summary
- **Engineering gaps**: N items
- **Business/product gaps**: N items
- **Already covered**: N items
# Code Review Report
## Stack: [Backend / Frontend / Full Stack]
## Files reviewed: [list or summary]
---
## Production Hardening
[Output from production-hardening-reviewer]
---
## Audit Compliance
[Output from audit-compliance-reviewer]
---
## Analytics Coverage
[Output from analytics-coverage-reviewer]
---
## Summary
- **Critical**: N findings
- **High**: N findings
- **Medium**: N findings
- **Low**: N findings