@cubis/foundry 0.3.32 → 0.3.33

package/workflows/skills/mcp-builder/SKILL.md

@@ -1,176 +1,18 @@
 ---
-name: mcp-builder
-description: MCP (Model Context Protocol) server building principles. Tool design, resource patterns, best practices.
-allowed-tools: Read, Write, Edit, Glob, Grep
+name: "mcp-builder"
+description: "Compatibility wrapper skill. Canonical MCP skill moved to mcp/skills/mcp-builder."
+metadata:
+  deprecated: true
+  replaced_by: "mcp-builder"
+  moved_to: "mcp/skills/mcp-builder/SKILL.md"
+  removal_target: "v0.6.0"
 ---
 
-# MCP Builder
+# mcp-builder (Compatibility Wrapper)
 
-> Principles for building MCP servers.
+This legacy workflow-path skill is kept for backward compatibility.
 
----
-
-## 1. MCP Overview
-
-### What is MCP?
-
-Model Context Protocol - standard for connecting AI systems with external tools and data sources.
-
-### Core Concepts
-
-| Concept | Purpose |
-|---------|---------|
-| **Tools** | Functions AI can call |
-| **Resources** | Data AI can read |
-| **Prompts** | Pre-defined prompt templates |
-
----
-
-## 2. Server Architecture
-
-### Project Structure
-
-```
-my-mcp-server/
-├── src/
-│   └── index.ts      # Main entry
-├── package.json
-└── tsconfig.json
-```
-
-### Transport Types
-
-| Type | Use |
-|------|-----|
-| **Stdio** | Local, CLI-based |
-| **SSE** | Web-based, streaming |
-| **WebSocket** | Real-time, bidirectional |
-
----
-
-## 3. Tool Design Principles
-
-### Good Tool Design
-
-| Principle | Description |
-|-----------|-------------|
-| Clear name | Action-oriented (get_weather, create_user) |
-| Single purpose | One thing well |
-| Validated input | Schema with types and descriptions |
-| Structured output | Predictable response format |
-
-### Input Schema Design
-
-| Field | Required? |
-|-------|-----------|
-| Type | Yes - object |
-| Properties | Define each param |
-| Required | List mandatory params |
-| Description | Human-readable |
-
----
-
-## 4. Resource Patterns
-
-### Resource Types
-
-| Type | Use |
-|------|-----|
-| Static | Fixed data (config, docs) |
-| Dynamic | Generated on request |
-| Template | URI with parameters |
-
-### URI Patterns
-
-| Pattern | Example |
-|---------|---------|
-| Fixed | `docs://readme` |
-| Parameterized | `users://{userId}` |
-| Collection | `files://project/*` |
-
----
-
-## 5. Error Handling
-
-### Error Types
-
-| Situation | Response |
-|-----------|----------|
-| Invalid params | Validation error message |
-| Not found | Clear "not found" |
-| Server error | Generic error, log details |
-
-### Best Practices
-
-- Return structured errors
-- Don't expose internal details
-- Log for debugging
-- Provide actionable messages
-
----
-
-## 6. Multimodal Handling
-
-### Supported Types
-
-| Type | Encoding |
-|------|----------|
-| Text | Plain text |
-| Images | Base64 + MIME type |
-| Files | Base64 + MIME type |
-
----
-
-## 7. Security Principles
-
-### Input Validation
-
-- Validate all tool inputs
-- Sanitize user-provided data
-- Limit resource access
-
-### API Keys
-
-- Use environment variables
-- Don't log secrets
-- Validate permissions
-
----
-
-## 8. Configuration
-
-### Claude Desktop Config
-
-| Field | Purpose |
-|-------|---------|
-| command | Executable to run |
-| args | Command arguments |
-| env | Environment variables |
-
----
-
-## 9. Testing
-
-### Test Categories
-
-| Type | Focus |
-|------|-------|
-| Unit | Tool logic |
-| Integration | Full server |
-| Contract | Schema validation |
-
----
-
-## 10. Best Practices Checklist
-
-- [ ] Clear, action-oriented tool names
-- [ ] Complete input schemas with descriptions
-- [ ] Structured JSON output
-- [ ] Error handling for all cases
-- [ ] Input validation
-- [ ] Environment-based configuration
-- [ ] Logging for debugging
-
----
+Canonical MCP skill path:
+- mcp/skills/mcp-builder/SKILL.md
 
-> **Remember:** MCP tools should be simple, focused, and well-documented. The AI relies on descriptions to use them correctly.
+Install MCP skills with: cbx workflows install --include-mcp

package/workflows/skills/mcp-developer/SKILL.md

@@ -1,85 +1,18 @@
 ---
-name: mcp-developer
-description: "Use for implementing, debugging, and maintaining MCP servers/clients with SDKs, protocol compliance, transports, schemas, and security hardening."
-license: MIT
+name: "mcp-developer"
+description: "Compatibility wrapper skill. Canonical MCP skill moved to mcp/skills/mcp-developer."
 metadata:
-  author: https://github.com/Jeffallan
-  version: "1.0.0"
-  domain: api-architecture
-  triggers: MCP, Model Context Protocol, MCP server, MCP client, Claude integration, AI tools, context protocol, JSON-RPC
-  role: specialist
-  scope: implementation
-  output-format: code
-  related-skills: fastapi-expert, typescript-pro, security-reviewer, devops-engineer
+  deprecated: true
+  replaced_by: "mcp-developer"
+  moved_to: "mcp/skills/mcp-developer/SKILL.md"
+  removal_target: "v0.6.0"
 ---
 
-# MCP Developer
+# mcp-developer (Compatibility Wrapper)
 
-Senior MCP (Model Context Protocol) developer with deep expertise in building servers and clients that connect AI systems with external tools and data sources.
+This legacy workflow-path skill is kept for backward compatibility.
 
-## Role Definition
+Canonical MCP skill path:
+- mcp/skills/mcp-developer/SKILL.md
 
-You are a senior MCP developer with expertise in protocol implementation, SDK usage (TypeScript/Python), and production deployment. You build robust MCP servers that expose resources, tools, and prompts to Claude and other AI systems while maintaining security, performance, and developer experience standards.
-
-## When to Use This Skill
-
-- Building MCP servers for data source integration
-- Implementing tool functions for AI assistants
-- Creating resource providers with URI schemes
-- Setting up MCP clients for Claude integration
-- Debugging protocol compliance issues
-- Optimizing MCP performance and security
-
-## Core Workflow
-
-1. **Analyze requirements** - Identify data sources, tools needed, client apps
-2. **Design protocol** - Define resources, tools, prompts, schemas
-3. **Implement** - Build server/client with SDK, add security controls
-4. **Test** - Verify protocol compliance, performance, error handling
-5. **Deploy** - Package, configure, monitor in production
-
-## Reference Guide
-
-Load detailed guidance based on context:
-
-| Topic | Reference | Load When |
-|-------|-----------|-----------|
-| Protocol | `references/protocol.md` | Message types, lifecycle, JSON-RPC 2.0 |
-| TypeScript SDK | `references/typescript-sdk.md` | Building servers/clients in Node.js |
-| Python SDK | `references/python-sdk.md` | Building servers/clients in Python |
-| Tools | `references/tools.md` | Tool definitions, schemas, execution |
-| Resources | `references/resources.md` | Resource providers, URIs, templates |
-
-## Constraints
-
-### MUST DO
-- Implement JSON-RPC 2.0 protocol correctly
-- Validate all inputs with schemas (Zod/Pydantic)
-- Use proper transport mechanisms (stdio/HTTP/SSE)
-- Implement comprehensive error handling
-- Add authentication and authorization
-- Log protocol messages for debugging
-- Test protocol compliance thoroughly
-- Document server capabilities
-
-### MUST NOT DO
-- Skip input validation on tool inputs
-- Expose sensitive data in resource content
-- Ignore protocol version compatibility
-- Mix synchronous code with async transports
-- Hardcode credentials or secrets
-- Return unstructured errors to clients
-- Deploy without rate limiting
-- Skip security controls
-
-## Output Templates
-
-When implementing MCP features, provide:
-1. Server/client implementation file
-2. Schema definitions (tools, resources, prompts)
-3. Configuration file (transport, auth, etc.)
-4. Brief explanation of design decisions
-
-## Knowledge Reference
-
-Model Context Protocol (MCP), JSON-RPC 2.0, TypeScript SDK (@modelcontextprotocol/sdk), Python SDK (mcp), Zod schemas, Pydantic validation, stdio transport, SSE transport, resource URIs, tool functions, prompt templates, authentication, rate limiting
+Install MCP skills with: cbx workflows install --include-mcp

package/workflows/skills/nextjs-developer/SKILL.md

@@ -1,166 +1,59 @@
 ---
 name: "nextjs-developer"
 displayName: "Next.js Developer"
-description: "Use for implementing/refactoring Next.js App Router features, Server Components/Actions, SEO, and production architecture. Not for version migration workflows or cache-components-only tuning."
-keywords:
-  [
-    "nextjs",
-    "next.js",
-    "react",
-    "app router",
-    "server components",
-    "server actions",
-    "vercel",
-    "ssr",
-    "seo",
-    "typescript",
-  ]
+description: "Use for implementing/refactoring Next.js App Router features, React Server Components/Actions, SEO, and production architecture."
+license: MIT
+metadata:
+  version: "2.0.0"
+  domain: "frontend"
+  role: "specialist"
+  stack: "nextjs"
+  baseline: "Next.js 16 + React 19"
 ---
 
 # Next.js Developer
 
-## Overview
+## Scope
 
-Senior Next.js developer expertise for Next.js 14+ with App Router and full-stack features. Covers server components, server actions, edge runtime, performance optimization, and production deployment with focus on fast, SEO-friendly applications.
+- Primary skill for App Router implementation and refactors.
+- Not for version migration playbooks (`next-upgrade`) or cache-components-only tuning (`next-cache-components`).
 
-## When to Use
+## When to use
 
-- Building new Next.js 14+ projects with App Router
-- Implementing Server Components and Server Actions
-- Optimizing Core Web Vitals and performance
-- Setting up data fetching with caching and revalidation
-- Configuring SEO (metadata, sitemaps, structured data)
-- Deploying to Vercel, Docker, or self-hosted environments
-- Writing tests with Playwright and React Testing Library
+- Building routes/layouts/loading/error boundaries.
+- Implementing server components and server actions.
+- Designing data fetching/revalidation strategy.
+- Improving SEO and web vitals.
 
-## Quick Reference
+## Core workflow
 
-### App Router File Conventions
+1. Define rendering mode per route (static/dynamic/streaming).
+2. Keep server/client component boundaries explicit.
+3. Implement data access with caching semantics by intent.
+4. Add forms/actions with validation and auth checks.
+5. Verify perf, accessibility, and error handling.
 
-```
-app/
-├── layout.tsx          # Root layout (required)
-├── page.tsx            # Home page
-├── loading.tsx         # Loading UI (Suspense boundary)
-├── error.tsx           # Error boundary
-├── not-found.tsx       # 404 page
-├── (auth)/             # Route group (no URL segment)
-│   ├── login/page.tsx
-│   └── register/page.tsx
-├── dashboard/
-│   ├── layout.tsx      # Nested layout
-│   ├── page.tsx
-│   └── @modal/         # Parallel route (slot)
-│       └── (..)settings/page.tsx  # Intercepting route
-└── api/
-    └── route.ts        # API route handler
-```
+## Baseline standards
 
-### Server vs Client Components
+- Default to Server Components; opt into client components only when needed.
+- Keep server-only code out of client bundles.
+- Use route-level loading/error states.
+- Use metadata API and structured data for SEO.
+- Measure Core Web Vitals and act on regressions.
 
-```tsx
-// Server Component (default) — no directive needed
-async function ProductList() {
-  const products = await db.product.findMany();
-  return (
-    <ul>
-      {products.map((p) => (
-        <li key={p.id}>{p.name}</li>
-      ))}
-    </ul>
-  );
-}
+## Avoid
 
-// Client Component — needs 'use client' directive
-("use client");
-import { useState } from "react";
-export function Counter() {
-  const [count, setCount] = useState(0);
-  return <button onClick={() => setCount((c) => c + 1)}>{count}</button>;
-}
-```
+- Unnecessary client hydration.
+- Mixing auth-sensitive logic into client-only paths.
+- Overusing global revalidation when targeted invalidation is possible.
 
-### Server Actions
+## Reference files
 
-```tsx
-// Inline server action
-async function createPost(formData: FormData) {
-  "use server";
-  const title = formData.get("title") as string;
-  await db.post.create({ data: { title } });
-  revalidatePath("/posts");
-}
-
-// In a form
-<form action={createPost}>
-  <input name="title" />
-  <button type="submit">Create</button>
-</form>;
-```
-
-### Data Fetching with Cache
-
-```tsx
-// Cached by default (static)
-const data = await fetch("https://api.example.com/data");
-
-// Revalidate every 60 seconds (ISR)
-const data = await fetch("https://api.example.com/data", {
-  next: { revalidate: 60 },
-});
-
-// No cache (dynamic)
-const data = await fetch("https://api.example.com/data", {
-  cache: "no-store",
-});
-```
-
-### Metadata API
-
-```tsx
-// Static metadata
-export const metadata: Metadata = {
-  title: "My App",
-  description: "Description",
-  openGraph: { title: "My App", images: ["/og.png"] },
-};
-
-// Dynamic metadata
-export async function generateMetadata({ params }): Promise<Metadata> {
-  const product = await getProduct(params.id);
-  return { title: product.name };
-}
-```
-
-## Quality Checklist
-
-- [ ] TypeScript strict mode enabled
-- [ ] Core Web Vitals > 90
-- [ ] SEO score > 95
-- [ ] Error boundaries on all routes
-- [ ] Loading states for async content
-- [ ] Edge runtime compatible where needed
-- [ ] Monitoring and error tracking configured
-
-## Steering Files
-
-| File                   | Load When                                                            |
-| ---------------------- | -------------------------------------------------------------------- |
-| `app-router.md`        | Route structure, layouts, route groups, parallel/intercepting routes |
-| `server-components.md` | Server/Client component patterns, streaming, Suspense                |
-| `server-actions.md`    | Form handling, mutations, validation, optimistic updates             |
-| `data-fetching.md`     | Fetch patterns, caching, revalidation, SWR/React Query               |
-| `performance.md`       | Image/font/script optimization, Core Web Vitals, bundle analysis     |
-| `seo.md`               | Metadata API, sitemaps, structured data, Open Graph                  |
-| `deployment.md`        | Vercel, Docker, self-hosting, monitoring, multi-region               |
-| `testing.md`           | Playwright E2E, component tests, visual regression, accessibility    |
-
-## Performance Targets
-
-| Metric | Target  |
-| ------ | ------- |
-| TTFB   | < 200ms |
-| FCP    | < 1s    |
-| LCP    | < 2.5s  |
-| CLS    | < 0.1   |
-| FID    | < 100ms |
+- `references/app-router.md`
+- `references/server-components.md`
+- `references/server-actions.md`
+- `references/data-fetching.md`
+- `references/performance.md`
+- `references/seo.md`
+- `references/deployment.md`
+- `references/testing.md`

package/workflows/skills/nextjs-react-expert/SKILL.md

@@ -1,21 +1,15 @@
 ---
-name: nextjs-react-expert
+name: "nextjs-react-expert"
 description: "Compatibility alias skill. Deprecated: use react-best-practices."
 metadata:
   deprecated: true
   replaced_by: react-best-practices
-  removal_target: v0.6.0
+  removal_target: "v0.6.0"
+  alias_of: "react-best-practices"
 ---
 
-# Nextjs React Expert
-
-## Compatibility Alias
+# nextjs-react-expert (Compatibility Alias)
 
 This skill is deprecated and kept for backward compatibility.
 
-Use `react-best-practices` as the canonical skill.
-
-## Migration
-
-1. Replace direct references to `nextjs-react-expert` with `react-best-practices`.
-2. Apply the full workflow from `react-best-practices` for new work.
+Use `react-best-practices` for optimization/review workflows.