@intentsolutionsio/jeremy-genkit-pro 2.1.0 → 2.1.5

package/README.md

@@ -56,6 +56,7 @@ Firebase Genkit Pro is a comprehensive Claude Code plugin providing expert guida
 ```
 
 Then follow the prompts to:
+
 1. Select your language (Node.js/Python/Go)
 2. Configure project structure
 3. Set up environment variables
@@ -127,6 +128,7 @@ const ragFlow = ai.defineFlow(async (query) => {
 ### Works with ADK Plugin
 
 For complex multi-agent orchestration:
+
 - Use Genkit for specialized AI flows
 - Use ADK for orchestrating multiple flows
 - Communication via A2A protocol
@@ -134,6 +136,7 @@ For complex multi-agent orchestration:
 ### Works with Vertex AI Validator
 
 For production deployment:
+
 - Genkit implements the flows
 - Validator ensures production readiness
 - Validates monitoring and security
@@ -158,6 +161,7 @@ npm run genkit:dev
 ```
 
 View production monitoring in Firebase Console:
+
 - Token consumption
 - Latency metrics
 - Error rates

package/agents/genkit-flow-architect.md

@@ -1,8 +1,36 @@
 ---
 name: genkit-flow-architect
-description: >
-  Expert Firebase Genkit flow architect specializing in designing...
+description: Expert Firebase Genkit flow architect specializing in designing...
+tools:
+- Read
+- Write
+- Edit
+- Bash
+- Glob
+- Grep
+- WebFetch
+- WebSearch
+- Task
+- TodoWrite
 model: sonnet
+color: pink
+version: 1.0.0
+author: Jeremy Longshore <jeremy@intentsolutions.io>
+tags:
+- ai-ml
+- genkit
+- flow
+- architect
+disallowedTools: []
+skills: []
+background: false
+# ── upgrade levers — uncomment + set when tuning this agent ──
+# effort: high            # reasoning depth: low/medium/high/xhigh/max (omit = inherit session)
+# maxTurns: 50            # cap the agentic loop (omit = engine default)
+# memory: project         # persistent scope: user/project/local (omit = ephemeral)
+# isolation: worktree     # run in an isolated git worktree
+# initialPrompt: "…"      # seed the agent's first turn
+# hooks / mcpServers / permissionMode → set at the PLUGIN level, not on a plugin agent
 ---
 # Genkit Flow Architect
 
@@ -11,6 +39,7 @@ You are an expert Firebase Genkit architect specializing in designing, implement
 ## Core Responsibilities
 
 ### 1. Flow Design & Architecture
+
 - Design multi-step AI workflows using Genkit's flow primitives
 - Implement structured generation with JSON schemas and custom formats
 - Architect tool/function calling for complex agent-driven tasks
@@ -18,6 +47,7 @@ You are an expert Firebase Genkit architect specializing in designing, implement
 - Implement context caching and compression strategies
 
 ### 2. Model Integration
+
 - Configure Gemini models (2.5 Pro, 2.5 Flash) via Vertex AI plugin
 - Integrate Imagen 2 for image generation tasks
 - Set up custom model providers (OpenAI, Anthropic, local LLMs)
@@ -25,6 +55,7 @@ You are an expert Firebase Genkit architect specializing in designing, implement
 - Configure temperature, top-p, and other generation parameters
 
 ### 3. Production Deployment
+
 - Deploy to Firebase with AI monitoring enabled
 - Deploy to Google Cloud Run with proper scaling
 - Configure OpenTelemetry tracing for observability
@@ -34,6 +65,7 @@ You are an expert Firebase Genkit architect specializing in designing, implement
 ### 4. Language-Specific Expertise
 
 #### Node.js/TypeScript (Genkit 1.0)
+
 ```typescript
 import { genkit, z } from 'genkit';
 import { googleAI, gemini25Pro, textEmbedding004 } from '@genkit-ai/googleai';
@@ -60,6 +92,7 @@ const myFlow = ai.defineFlow(
 ```
 
 #### Python (Alpha)
+
 ```python
 from genkit import genkit, z
 from genkit.plugins import google_ai
@@ -79,6 +112,7 @@ async def menu_suggestion_flow(subject: str) -> str:
 ```
 
 #### Go (1.0)
+
 ```go
 package main
 
@@ -105,6 +139,7 @@ func menuSuggestionFlow(ctx context.Context, subject string) (string, error) {
 ### 5. Advanced Patterns
 
 #### RAG with Vector Search
+
 ```typescript
 import { retrieve } from 'genkit';
 
@@ -135,6 +170,7 @@ const ragFlow = ai.defineFlow(async (query) => {
 ```
 
 #### Tool Calling Pattern
+
 ```typescript
 const weatherTool = ai.defineTool(
   {
@@ -165,6 +201,7 @@ const agentFlow = ai.defineFlow(async (input) => {
 ```
 
 ### 6. Monitoring & Debugging
+
 - Enable AI monitoring in Firebase Console
 - Configure custom trace attributes
 - Set up alerting for failures and latency
@@ -172,6 +209,7 @@ const agentFlow = ai.defineFlow(async (input) => {
 - Debug flows using Genkit Developer UI
 
 ### 7. Best Practices
+
 - Always use typed schemas (Zod for TS/JS, Pydantic for Python)
 - Implement proper error boundaries and retries
 - Use context caching for large prompts
@@ -183,6 +221,7 @@ const agentFlow = ai.defineFlow(async (input) => {
 ## When to Use This Agent
 
 Activate this agent when the user mentions:
+
 - "Create a Genkit flow"
 - "Design AI workflow"
 - "Implement RAG with Genkit"
@@ -194,6 +233,7 @@ Activate this agent when the user mentions:
 ## Integration with Vertex AI ADK
 
 This agent can collaborate with ADK agents for:
+
 - Complex multi-agent orchestration (use ADK for orchestration, Genkit for individual flows)
 - Passing Genkit flow results to ADK agents via A2A protocol
 - Using Genkit for deterministic data validation before ADK deployment tasks
@@ -203,4 +243,4 @@ This agent can collaborate with ADK agents for:
 - Genkit Documentation: https://genkit.dev/
 - Vertex AI Plugin: https://genkit.dev/docs/integrations/vertex-ai/
 - Firebase Genkit Announcement (Feb 2025): https://firebase.blog/posts/2025/02/announcing-genkit/
-- Genkit Go 1.0 (Sep 2025): https://developers.googleblog.com/en/announcing-genkit-go-10/
+- Genkit Go 1.0 (Sep 2025):

package/commands/init-genkit-project.md

@@ -10,6 +10,7 @@ Initialize a production-ready Firebase Genkit project with proper structure, con
 ## Step 1: Determine Project Language
 
 Ask the user to choose the target language:
+
 - **Node.js/TypeScript** (Genkit 1.0 - Stable, recommended for most use cases)
 - **Python** (Alpha - Early adopters, Python ecosystem integration)
 - **Go** (1.0 - High performance, backend services)
@@ -36,6 +37,7 @@ npx tsc --init
 ```
 
 Create `tsconfig.json`:
+
 ```json
 {
   "compilerOptions": {
@@ -57,6 +59,7 @@ Create `tsconfig.json`:
 ```
 
 Create `src/index.ts`:
+
 ```typescript
 import { genkit, z } from 'genkit';
 import { googleAI, gemini25Flash } from '@genkit-ai/googleai';
@@ -99,6 +102,7 @@ export { exampleFlow };
 ```
 
 Create `package.json` scripts:
+
 ```json
 {
   "scripts": {
@@ -128,6 +132,7 @@ pip freeze > requirements.txt
 ```
 
 Create `main.py`:
+
 ```python
 from genkit import genkit
 from genkit.plugins import google_ai
@@ -169,6 +174,7 @@ go get github.com/firebase/genkit/go/plugins/googleai
 ```
 
 Create `main.go`:
+
 ```go
 package main
 
@@ -218,6 +224,7 @@ func main() {
 ## Step 3: Environment Configuration
 
 Create `.env` file:
+
 ```bash
 # Google API Key (for Google AI plugin)
 GOOGLE_API_KEY=your_api_key_here
@@ -230,6 +237,7 @@ NODE_ENV=development
 ```
 
 Create `.env.example` (committed to git):
+
 ```bash
 GOOGLE_API_KEY=
 GOOGLE_CLOUD_PROJECT=
@@ -278,6 +286,7 @@ firebase init
 ```
 
 Update `firebase.json`:
+
 ```json
 {
   "functions": [
@@ -315,6 +324,7 @@ Access UI at: `http://localhost:4000`
 ## Step 7: Testing
 
 Create test file `tests/flows.test.ts`:
+
 ```typescript
 import { describe, it, expect } from 'vitest';
 import { exampleFlow } from '../src/index';
@@ -341,6 +351,7 @@ describe('exampleFlow', () => {
 ## Next Steps
 
 After initialization:
+
 1. Review and customize the example flow
 2. Add your specific business logic
 3. Implement additional flows for your use case
@@ -353,4 +364,4 @@ After initialization:
 - Genkit Documentation: https://genkit.dev/
 - Node.js Guide: https://genkit.dev/docs/get-started/
 - Python Guide: https://firebase.blog/posts/2025/04/genkit-python-go/
-- Go Guide: https://developers.googleblog.com/en/announcing-genkit-go-10/
+- Go Guide:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@intentsolutionsio/jeremy-genkit-pro",
-  "version": "2.1.0",
+  "version": "2.1.5",
   "description": "Firebase Genkit expert for production-ready AI workflows with RAG and tool calling",
   "keywords": [
     "firebase",

package/skills/genkit-production-expert/SKILL.md

@@ -1,14 +1,22 @@
 ---
 name: genkit-production-expert
-description: |
-  Build production Firebase Genkit applications including RAG systems, multi-step flows, and tool calling for Node.js/Python/Go. Deploy to Firebase Functions or Cloud Run with AI monitoring. Use when asked to "create genkit flow" or "implement RAG". Trigger with relevant phrases based on skill purpose.
+description: 'Build production Firebase Genkit applications including RAG systems,
+  multi-step flows, and tool calling for Node.js/Python/Go. Deploy to Firebase Functions
+  or Cloud Run with AI monitoring. Use when asked to "create genkit flow" or "implement
+  RAG". Trigger with relevant phrases based on skill purpose.
+
+  '
 allowed-tools: Read, Write, Edit, Grep, Glob, Bash(cmd:*)
 version: 2.1.0
 author: Jeremy Longshore <jeremy@intentsolutions.io>
 license: MIT
 effort: medium
-compatible-with: claude-code, codex, openclaw
-tags: [ai, deployment, monitoring, python]
+tags:
+- ai
+- deployment
+- monitoring
+- python
+compatibility: Designed for Claude Code, also compatible with Codex and OpenClaw
 ---
 # Genkit Production Expert
 
@@ -78,4 +86,4 @@ See `${CLAUDE_SKILL_DIR}/references/workflow-examples.md` for complete code exam
 - [Zod Schema Library](https://zod.dev) -- TypeScript schema validation
 - [OpenTelemetry for Node.js](https://opentelemetry.io/docs/languages/js/) -- tracing and observability
 - Gemini model selection guide: Flash for throughput, Pro for reasoning quality
-- Context caching and token optimization strategies for cost management
+- Context caching and token optimization strategies for cost management

package/skills/genkit-production-expert/references/examples.md

@@ -448,6 +448,7 @@ curl -X POST http://localhost:3400/assistant-agent \
 ### Expected Output
 
 Weather query:
+
 ```json
 {
   "reply": "The weather in San Francisco is currently 62F and foggy with 78% humidity. You might want to bring a jacket!",
@@ -456,6 +457,7 @@ Weather query:
 ```
 
 Combined query:
+
 ```json
 {
   "reply": "I've scheduled your picnic for tomorrow at 2:00 PM (2 hours). The weather in Austin looks great - 85F, sunny, and 40% humidity. Perfect picnic weather!",

package/skills/genkit-production-expert/references/how-it-works.md

@@ -3,6 +3,7 @@
 ## How It Works
 
 ### Phase 1: Requirements Analysis
+
 ```
 User Request → Analyze needs → Determine:
 - Target language (Node.js/Python/Go)
@@ -12,6 +13,7 @@ User Request → Analyze needs → Determine:
 ```
 
 ### Phase 2: Project Setup
+
 ```
 Check existing project → If new:
   - Initialize project structure
@@ -26,6 +28,7 @@ If existing:
 ```
 
 ### Phase 3: Implementation
+
 ```
 Design flow architecture → Implement:
   - Input/output schemas (Zod/Pydantic/Go structs)
@@ -37,6 +40,7 @@ Design flow architecture → Implement:
 ```
 
 ### Phase 4: Testing & Validation
+
 ```
 Create test cases → Run locally:
   - Genkit Developer UI
@@ -46,10 +50,11 @@ Create test cases → Run locally:
 ```
 
 ### Phase 5: Production Deployment
+
 ```
 Configure deployment → Deploy:
   - Firebase Functions (with AI monitoring)
   - Cloud Run (with auto-scaling)
   - Set up monitoring dashboards
   - Configure alerting
-```
+```

package/skills/genkit-production-expert/references/production-best-practices-applied.md

@@ -3,10 +3,12 @@
 ## Production Best Practices Applied
 
 ### 1. Schema Validation
+
 - All inputs/outputs use Zod (TS), Pydantic (Python), or structs (Go)
 - Prevents runtime errors from malformed data
 
 ### 2. Error Handling
+
 ```typescript
 try {
   const result = await ai.generate({...});
@@ -22,19 +24,22 @@ try {
 ```
 
 ### 3. Cost Optimization
+
 - Context caching for repeated prompts
 - Token usage monitoring
 - Temperature tuning for use case
 - Model selection (Flash vs Pro)
 
 ### 4. Monitoring
+
 - OpenTelemetry tracing enabled
 - Custom span attributes
 - Firebase Console integration
 - Alert configuration
 
 ### 5. Security
+
 - Environment variable management
 - API key rotation support
 - Input sanitization
-- Output filtering
+- Output filtering

package/skills/genkit-production-expert/references/workflow-examples.md

@@ -7,8 +7,10 @@
 **User Request**: "Create a Genkit flow that answers user questions using Gemini 2.5 Flash"
 
 **Skill Response**:
+
 1. Creates TypeScript project (default)
 2. Implements flow with input validation:
+
 ```typescript
 const qaFlow = ai.defineFlow(
   {
@@ -26,16 +28,19 @@ const qaFlow = ai.defineFlow(
   }
 );
 ```
-3. Sets up local testing
-4. Provides deployment instructions
+
+1. Sets up local testing
+2. Provides deployment instructions
 
 ### Example 2: RAG System with Vector Search
 
 **User Request**: "Implement RAG with Genkit for our documentation search"
 
 **Skill Response**:
+
 1. Analyzes document storage needs
 2. Implements retriever with embeddings:
+
 ```typescript
 const docRetriever = ai.defineRetriever(
   {
@@ -58,16 +63,19 @@ const docRetriever = ai.defineRetriever(
   }
 );
 ```
-3. Creates RAG flow combining retrieval + generation
-4. Sets up vector database connection
-5. Implements caching for efficiency
+
+1. Creates RAG flow combining retrieval + generation
+2. Sets up vector database connection
+3. Implements caching for efficiency
 
 ### Example 3: Multi-Agent Tool Calling
 
 **User Request**: "Create a Genkit agent with weather and calendar tools"
 
 **Skill Response**:
+
 1. Defines tools with proper schemas:
+
 ```typescript
 const weatherTool = ai.defineTool({
   name: 'getWeather',
@@ -90,7 +98,9 @@ const calendarTool = ai.defineTool({
   // Check calendar API
 });
 ```
-2. Creates agent flow with tool access:
+
+1. Creates agent flow with tool access:
+
 ```typescript
 const agentFlow = ai.defineFlow(async (userQuery) => {
   const { text } = await ai.generate({
@@ -101,5 +111,6 @@ const agentFlow = ai.defineFlow(async (userQuery) => {
   return text;
 });
 ```
-3. Implements proper error handling
-4. Sets up tool execution tracing
+
+1. Implements proper error handling
+2. Sets up tool execution tracing