@intentsolutionsio/jeremy-gcp-starter-examples 2.1.0 → 2.1.4

package/README.md

@@ -24,9 +24,11 @@ This plugin provides instant access to production-ready code examples from 6 off
 ## Components
 
 ### Agent
+
 - **gcp-starter-kit-expert**: Aggregates code examples from official Google Cloud repos
 
 ### Skills (Auto-Activating)
+
 - **gcp-examples-expert**: Triggers on "show adk example", "genkit starter template", "vertex ai code sample"
   - **Tool Permissions**: Read, Write, Edit, Grep, Glob, Bash
   - **Version**: 1.0.0 (2026 schema compliant)
@@ -62,6 +64,7 @@ The skill auto-activates and provides production-ready code examples.
 - IAM least privilege patterns
 
 **Example Request**:
+
 ```
 "Show me how to create an ADK agent with Code Execution and Memory Bank"
 ```
@@ -78,6 +81,7 @@ The skill auto-activates and provides production-ready code examples.
 - Error tracking and distributed tracing
 
 **Example Request**:
+
 ```
 "Give me the Agent Starter Pack production template"
 ```
@@ -93,6 +97,7 @@ The skill auto-activates and provides production-ready code examples.
 - Node.js, Python, and Go examples
 
 **Example Request**:
+
 ```
 "I need a Genkit RAG flow template with vector search"
 ```
@@ -109,6 +114,7 @@ The skill auto-activates and provides production-ready code examples.
 - A/B testing and traffic splitting
 
 **Example Request**:
+
 ```
 "Show me how to fine-tune Gemini on custom data"
 ```
@@ -125,6 +131,7 @@ The skill auto-activates and provides production-ready code examples.
 - Token counting and cost optimization
 
 **Example Request**:
+
 ```
 "How do I analyze video content with Gemini multimodal?"
 ```
@@ -141,6 +148,7 @@ The skill auto-activates and provides production-ready code examples.
 - Retry logic with exponential backoff
 
 **Example Request**:
+
 ```
 "I want to build a multi-agent system with AgentSmithy"
 ```
@@ -148,38 +156,47 @@ The skill auto-activates and provides production-ready code examples.
 ## Use Cases
 
 ### Quick Prototyping
+
 Get production-ready code to start building immediately without searching through documentation.
 
 ### Learning Best Practices
+
 See how Google Cloud engineers implement security, monitoring, and scalability in official examples.
 
 ### Production Templates
+
 Use battle-tested patterns from Agent Starter Pack for production deployments.
 
 ### Framework Comparison
+
 Compare ADK, Genkit, and Vertex AI implementations to choose the right framework.
 
 ### Infrastructure as Code
+
 Get Terraform templates for deploying agents and infrastructure.
 
 ## Integration with Other Plugins
 
 ### jeremy-genkit-pro
+
 - Provides Genkit code examples
 - Complements Genkit flow architect agent
 - Shares production best practices
 
 ### jeremy-adk-orchestrator
+
 - Provides ADK sample code
 - Shows A2A protocol implementation
 - Demonstrates multi-agent patterns
 
 ### jeremy-vertex-validator
+
 - Provides code that passes production validation
 - Follows security and performance best practices
 - Includes monitoring from the start
 
 ### jeremy-*-terraform plugins
+
 - Provides infrastructure code examples
 - Shows Terraform module patterns
 - Demonstrates resource configuration
@@ -228,6 +245,7 @@ Plugin provides:
 ## Best Practices Included
 
 ### Security
+
 - IAM least privilege service accounts
 - VPC Service Controls for enterprise isolation
 - Model Armor for prompt injection protection
@@ -235,6 +253,7 @@ Plugin provides:
 - No hardcoded credentials (Secret Manager)
 
 ### Performance
+
 - Auto-scaling (min/max instances)
 - Appropriate machine types and accelerators
 - Caching strategies
@@ -242,6 +261,7 @@ Plugin provides:
 - Token optimization
 
 ### Observability
+
 - Cloud Monitoring dashboards
 - Alerting policies
 - Structured logging
@@ -249,6 +269,7 @@ Plugin provides:
 - Error tracking
 
 ### Reliability
+
 - Multi-region deployment
 - Circuit breaker patterns
 - Retry logic with exponential backoff
@@ -256,6 +277,7 @@ Plugin provides:
 - Graceful degradation
 
 ### Cost Optimization
+
 - Gemini 2.5 Flash for simple tasks
 - Gemini 2.5 Pro for complex reasoning
 - Batch predictions for bulk processing

package/agents/gcp-starter-kit-expert.md

@@ -1,9 +1,36 @@
 ---
 name: gcp-starter-kit-expert
-description: >
-  Expert in Google Cloud starter kits, ADK samples, Genkit templates,
-  Agent...
+description: Expert in Google Cloud starter kits, ADK samples, Genkit templates, Agent...
+tools:
+- Read
+- Write
+- Edit
+- Bash
+- Glob
+- Grep
+- WebFetch
+- WebSearch
+- Task
+- TodoWrite
 model: sonnet
+color: orange
+version: 1.0.0
+author: Jeremy Longshore <jeremy@intentsolutions.io>
+tags:
+- ai-ml
+- gcp
+- starter
+- kit
+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
 ---
 # Google Cloud Starter Kit Expert
 
@@ -648,6 +675,7 @@ def create_multi_agent_system(project_id: str):
 ## When to Use This Agent
 
 Activate this agent when developers need:
+
 - ADK agent implementation examples
 - Agent Starter Pack production templates
 - Genkit flow patterns (RAG, multi-step, tool calling)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@intentsolutionsio/jeremy-gcp-starter-examples",
-  "version": "2.1.0",
+  "version": "2.1.4",
   "description": "Google Cloud starter kits and example code aggregator with ADK samples",
   "keywords": [
     "google-cloud",

package/skills/gcp-examples-expert/SKILL.md

@@ -1,15 +1,22 @@
 ---
 name: gcp-examples-expert
-description: |
-  Generate production-ready Google Cloud code examples from official repositories including ADK samples, Genkit templates, Vertex AI notebooks, and Gemini patterns. Use when asked to "show ADK example" or "provide GCP starter kit". Trigger with relevant phrases based on skill purpose.
+description: 'Generate production-ready Google Cloud code examples from official repositories
+  including ADK samples, Genkit templates, Vertex AI notebooks, and Gemini patterns.
+  Use when asked to "show ADK example" or "provide GCP starter kit". 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
-argument-hint: "[framework or use-case]"
-compatible-with: claude-code, codex, openclaw
-tags: [ai, gcp, gcp-examples]
+argument-hint: '[framework or use-case]'
+tags:
+- ai
+- gcp
+- gcp-examples
+compatibility: Designed for Claude Code, also compatible with Codex and OpenClaw
 ---
 # GCP Examples Expert
 
@@ -78,4 +85,4 @@ See `${CLAUDE_SKILL_DIR}/references/example-interactions.md` for detailed intera
 - [genkit-ai/genkit](https://github.com/genkit-ai/genkit) -- RAG flows, tool calling, evaluation
 - [GoogleCloudPlatform/vertex-ai-samples](https://github.com/GoogleCloudPlatform/vertex-ai-samples) -- model training, tuning, deployment
 - [GoogleCloudPlatform/generative-ai](https://github.com/GoogleCloudPlatform/generative-ai) -- Gemini multimodal, function calling, grounding
-- [GoogleCloudPlatform/agentsmithy](https://github.com/GoogleCloudPlatform/agentsmithy) -- multi-agent orchestration
+- [GoogleCloudPlatform/agentsmithy](https://github.com/GoogleCloudPlatform/agentsmithy) -- multi-agent orchestration

package/skills/gcp-examples-expert/references/best-practices-applied.md

@@ -3,6 +3,7 @@
 ## Best Practices Applied
 
 ### Security
+
 ✅ IAM least privilege service accounts
 ✅ VPC Service Controls for enterprise isolation
 ✅ Model Armor for prompt injection protection
@@ -10,6 +11,7 @@
 ✅ No hardcoded credentials (use Secret Manager)
 
 ### Performance
+
 ✅ Auto-scaling configuration (min/max instances)
 ✅ Appropriate machine types and accelerators
 ✅ Caching strategies for repeated queries
@@ -17,6 +19,7 @@
 ✅ Token optimization for cost efficiency
 
 ### Observability
+
 ✅ Cloud Monitoring dashboards
 ✅ Alerting policies for errors and latency
 ✅ Structured logging with severity levels
@@ -24,6 +27,7 @@
 ✅ Error tracking with Cloud Error Reporting
 
 ### Reliability
+
 ✅ Multi-region deployment for high availability
 ✅ Circuit breaker patterns for fault tolerance
 ✅ Retry logic with exponential backoff
@@ -31,8 +35,9 @@
 ✅ Graceful degradation strategies
 
 ### Cost Optimization
+
 ✅ Use Gemini 2.5 Flash for simple tasks (cheaper)
 ✅ Gemini 2.5 Pro for complex reasoning (higher quality)
 ✅ Batch predictions for bulk processing
 ✅ Preemptible instances for non-critical workloads
-✅ Token counting to estimate costs
+✅ Token counting to estimate costs

package/skills/gcp-examples-expert/references/code-example-categories.md

@@ -7,6 +7,7 @@
 **Source**: google/adk-samples
 
 **Examples Provided**:
+
 - Basic agent creation with Code Execution Sandbox
 - Memory Bank configuration for stateful agents
 - A2A protocol implementation for inter-agent communication
@@ -15,6 +16,7 @@
 - IAM least privilege patterns
 
 **Sample Pattern**:
+
 ```python
 from google.cloud.aiplatform import agent_builder
 
@@ -38,6 +40,7 @@ def create_adk_agent(project_id: str, location: str):
 **Source**: GoogleCloudPlatform/agent-starter-pack
 
 **Examples Provided**:
+
 - Production agent with monitoring and observability
 - Auto-scaling configuration
 - Security best practices (Model Armor, VPC-SC)
@@ -46,6 +49,7 @@ def create_adk_agent(project_id: str, location: str):
 - Error tracking setup
 
 **Sample Pattern**:
+
 ```python
 def production_agent_with_observability(project_id: str):
     agent = aiplatform.Agent.create(
@@ -66,6 +70,7 @@ def production_agent_with_observability(project_id: str):
 **Source**: genkit-ai/genkit
 
 **Examples Provided**:
+
 - RAG flows with vector search
 - Multi-step workflows
 - Tool calling integration
@@ -74,6 +79,7 @@ def production_agent_with_observability(project_id: str):
 - Deployment patterns (Cloud Run, Functions)
 
 **Sample Pattern**:
+
 ```typescript
 import { genkit, z } from 'genkit';
 import { googleAI, gemini15ProLatest } from '@genkit-ai/googleai';
@@ -92,6 +98,7 @@ const ragFlow = ai.defineFlow({
 **Source**: GoogleCloudPlatform/vertex-ai-samples
 
 **Examples Provided**:
+
 - Custom model training with Gemini
 - Batch prediction jobs
 - Hyperparameter tuning
@@ -100,6 +107,7 @@ const ragFlow = ai.defineFlow({
 - A/B testing patterns
 
 **Sample Pattern**:
+
 ```python
 def fine_tune_gemini_model(project_id: str, training_data_uri: str):
     job = aiplatform.CustomTrainingJob(
@@ -117,6 +125,7 @@ def fine_tune_gemini_model(project_id: str, training_data_uri: str):
 **Source**: GoogleCloudPlatform/generative-ai
 
 **Examples Provided**:
+
 - Gemini multimodal analysis (text, images, video)
 - Function calling with live APIs
 - Structured output generation
@@ -125,6 +134,7 @@ def fine_tune_gemini_model(project_id: str, training_data_uri: str):
 - Token counting and cost optimization
 
 **Sample Pattern**:
+
 ```python
 from vertexai.generative_models import GenerativeModel, Part
 
@@ -140,6 +150,7 @@ def analyze_multimodal_content(video_uri: str, question: str):
 **Source**: GoogleCloudPlatform/agentsmithy
 
 **Examples Provided**:
+
 - Multi-agent orchestration
 - Supervisory agent patterns
 - Agent-to-agent communication
@@ -148,6 +159,7 @@ def analyze_multimodal_content(video_uri: str, question: str):
 - Error handling and retry logic
 
 **Sample Pattern**:
+
 ```python
 from agentsmithy import Agent, Orchestrator, Task
 
@@ -157,4 +169,4 @@ def create_multi_agent_system(project_id: str):
         strategy="sequential"
     )
     # Full implementation from agentsmithy
-```
+```

package/skills/gcp-examples-expert/references/example-interactions.md

@@ -3,9 +3,11 @@
 ## Example Interactions
 
 ### Example 1: ADK Agent Creation
+
 **User**: "Show me how to create an ADK agent with Code Execution"
 
 **Skill Activates**:
+
 - Provides code example from google/adk-samples
 - Includes Code Execution Sandbox configuration
 - Shows 14-day state persistence setup
@@ -13,9 +15,11 @@
 - Links to official ADK documentation
 
 ### Example 2: Genkit RAG Flow
+
 **User**: "I need a Genkit starter template for RAG"
 
 **Skill Activates**:
+
 - Provides RAG flow code from genkit-ai/genkit
 - Shows vector search integration
 - Demonstrates embedding generation
@@ -23,9 +27,11 @@
 - Provides deployment configuration
 
 ### Example 3: Production Agent Template
+
 **User**: "What's the best way to deploy a production agent?"
 
 **Skill Activates**:
+
 - Provides Agent Starter Pack template
 - Shows auto-scaling configuration
 - Includes monitoring dashboard setup
@@ -33,9 +39,11 @@
 - Provides Terraform deployment code
 
 ### Example 4: Gemini Multimodal
+
 **User**: "How do I analyze video with Gemini?"
 
 **Skill Activates**:
+
 - Provides multimodal code from generative-ai repo
 - Shows video part creation
 - Demonstrates prompt engineering
@@ -43,11 +51,13 @@
 - Provides cost optimization tips
 
 ### Example 5: Multi-Agent System
+
 **User**: "I want to build a multi-agent system"
 
 **Skill Activates**:
+
 - Provides AgentSmithy orchestration code
 - Shows supervisory agent pattern
 - Demonstrates A2A protocol usage
 - Includes workflow coordination
-- Provides testing strategies
+- Provides testing strategies

package/skills/gcp-examples-expert/references/workflow.md

@@ -3,6 +3,7 @@
 ## Workflow
 
 ### Phase 1: Identify Use Case
+
 ```
 1. Listen for trigger phrases in user request
 2. Determine which repository has relevant examples
@@ -11,6 +12,7 @@
 ```
 
 ### Phase 2: Provide Code Example
+
 ```
 1. Fetch relevant code snippet from knowledge base
 2. Adapt to user's specific requirements
@@ -20,6 +22,7 @@
 ```
 
 ### Phase 3: Explain Best Practices
+
 ```
 1. Highlight security considerations (IAM, VPC-SC, Model Armor)
 2. Show monitoring and observability setup
@@ -29,10 +32,11 @@
 ```
 
 ### Phase 4: Deployment Guidance
+
 ```
 1. Provide Terraform/IaC templates
 2. Show Cloud Build CI/CD configuration
 3. Include testing strategies
 4. Document environment variables
 5. Link to official documentation
-```
+```