specweave 0.4.1 → 0.6.3

package/src/templates/CLAUDE.md.template

@@ -4,39 +4,83 @@ This project uses **SpecWeave** - a specification-first AI development framework
 
 ---
 
+## 🚨 CRITICAL: NEVER POLLUTE PROJECT ROOT!
+
+**⛔ THIS IS THE #1 RULE - ALL AI-GENERATED FILES GO IN INCREMENT FOLDERS ⛔**
+
+### ❌ NEVER Create in Root
+
+```
+❌ WRONG - ROOT FILES (NOT ALLOWED!):
+/SESSION-SUMMARY.md                    # NO! Goes to increment reports/
+/ANALYSIS-REPORT.md                    # NO! Goes to increment reports/
+/migration-script.py                   # NO! Goes to increment scripts/
+/execution.log                         # NO! Goes to increment logs/
+/temp-data.json                        # NO! Goes to increment logs/
+
+✅ CORRECT - INCREMENT FOLDERS:
+.specweave/increments/0001-user-auth/
+├── spec.md                            # Core spec files
+├── plan.md
+├── tasks.md
+├── tests.md
+├── reports/                           # ✅ PUT REPORTS HERE!
+│   ├── SESSION-SUMMARY.md
+│   └── ANALYSIS-REPORT.md
+├── scripts/                           # ✅ PUT SCRIPTS HERE!
+│   └── migration-script.py
+└── logs/                              # ✅ PUT LOGS HERE!
+    ├── execution.log
+    └── temp-data.json
+```
+
+### What IS Allowed in Root?
+
+**ONLY these files**:
+- ✅ `CLAUDE.md` (this file)
+- ✅ Your project files (`src/`, `package.json`, etc.)
+- ✅ Standard config (`.env`, `.gitignore`, `tsconfig.json`)
+
+**Everything else → increment folders!**
+
+**Before asking me to commit, check**: `git status` - If you see unexpected `.md` files in root, STOP and move them!
+
+---
+
 ## SpecWeave Workflow (Use These Commands!)
 
 **How SpecWeave works**:
 
 ```
-/specweave.inc "feature" → /specweave.do → /specweave.progress → /specweave.done → repeat
+/specweave:inc "feature" → /specweave:do → /specweave:progress → /specweave:done → repeat
 ```
 
-**1. Plan Feature** → `/specweave.inc "user authentication"`
+**1. Plan Feature** → `/specweave:inc "user authentication"`
    - Creates spec.md (WHAT/WHY), plan.md (HOW), tasks.md, tests.md
    - PM-led process with architect/security/QA review
    - **Use when**: Starting any new feature or increment
 
-**2. Execute Tasks** → `/specweave.do` or `/specweave.do 0001`
+**2. Execute Tasks** → `/specweave:do` or `/specweave:do 0001`
    - Smart resume (picks up where you left off)
    - Runs hooks after EVERY task completion
    - **Use when**: Ready to implement planned work
 
-**3. Check Progress** → `/specweave.progress`
+**3. Check Progress** → `/specweave:progress`
    - Shows task completion %, next action
    - **Use when**: Want to see status
 
-**4. Validate Quality** → `/specweave.validate 0001` or `/specweave.validate 0001 --quality`
+**4. Validate Quality** → `/specweave:validate 0001` or `/specweave:validate 0001 --quality`
    - Rule-based validation (120 checks)
    - Optional AI quality assessment
    - **Use when**: Verify increment quality before completion
 
-**5. Close Increment** → `/specweave.done 0001`
+**5. Close Increment** → `/specweave:done 0001`
    - Validates all tasks complete
    - **Use when**: Feature is finished
 
-**6. Sync to External** → `/specweave.sync-github` or `/specweave.sync-jira`
-   - Exports to GitHub issues or Jira
+**6. Sync to External** (Plugin Commands):
+   - `/specweave:github:sync` - Export to GitHub issues (github plugin)
+   - `/specweave:jira:sync` - Export to Jira (jira plugin)
    - **Use when**: Need to sync with project management tools
 
 **All other functionality (agents, skills) activates automatically based on context.**
@@ -60,7 +104,7 @@ When working in a SpecWeave-initialized project (`.specweave/` exists), SpecWeav
 6. ✅ **Business Model** - "Freemium", "$X/mo", "B2B", "Consumer"
 
 **Confidence Levels:**
-- **High (5-6 signals + SpecWeave folder)**: Auto-route to `/specweave.inc` immediately
+- **High (5-6 signals + SpecWeave folder)**: Auto-route to `/specweave:inc` immediately
 - **Medium (3-4 signals + SpecWeave folder)**: Ask 1-2 clarifying questions, then route
 - **Low (<3 signals)**: Regular conversation (no auto-routing)
 
@@ -80,7 +124,7 @@ Monetization: Freemium ($10/mo)
 SpecWeave detects: ✅ Name ✅ Features ✅ Tech ✅ Timeline ✅ Problem ✅ Business
 → Automatically recognizes this as a product description
 → Guides you through increment planning
-→ Invokes /specweave.inc automatically
+→ Invokes /specweave:inc automatically
 
 No need to remember to type /inc!
 ```
@@ -204,9 +248,9 @@ Config: Auto-detected from project files
 │   └── tests/                   # Centralized test repository
 │
 ├── .claude/                     # Pre-installed components
-│   ├── agents/                  # 10 agents (auto-activate)
-│   ├── skills/                  # 35+ skills (auto-activate)
-│   └── commands/                # Slash commands
+│   ├── agents/                  # Core + plugin agents (auto-activate)
+│   ├── skills/                  # Core + plugin skills (auto-activate)
+│   └── commands/                # Core + plugin slash commands
 │
 ├── CLAUDE.md                    # This file
 └── src/                         # Your source code
@@ -214,15 +258,67 @@ Config: Auto-detected from project files
 
 ---
 
+## Plugin Architecture
+
+**SpecWeave uses Claude Code's native plugin system** for optional capabilities.
+
+### Core vs. Plugins
+
+**Core Framework** (always loaded):
+- 9 core skills (increment-planner, tdd-workflow, context-loader, etc.)
+- 3 core agents (PM, Architect, Tech Lead)
+- 7 core commands (`/specweave:inc`, `/specweave:do`, etc.)
+- ~12K tokens (lightweight!)
+
+**Plugins** (opt-in based on your stack):
+- Tech stacks: `specweave-frontend`, `specweave-backend`, `specweave-kubernetes`
+- Integrations: `specweave-github`, `specweave-jira`
+- Domains: `specweave-ml`, `specweave-payments`, `specweave-testing`
+
+### Using Plugin Commands
+
+**Core commands** (always available):
+```bash
+/specweave:inc "feature"    # or /inc
+/specweave:do               # or /do
+/specweave:progress         # or /progress
+```
+
+**Plugin commands** (when plugin installed):
+```bash
+# GitHub plugin:
+/specweave:github:sync          # Sync increments to GitHub issues
+/specweave:github:create-issue  # Create new issue
+/specweave:github:status        # Check sync status
+
+# Jira plugin:
+/specweave:jira:sync           # Sync to Jira
+/specweave:jira:create-ticket  # Create Jira ticket
+```
+
+**Plugin agents and skills activate automatically** based on your tech stack and context.
+
+### Installing Plugins
+
+Plugins are detected and suggested during `specweave init` based on:
+- Git remote (GitHub detected → suggest github plugin)
+- Tech stack (React detected → suggest frontend plugin)
+- Project files (K8s yamls → suggest kubernetes plugin)
+
+**Enabled plugins**: {ENABLED_PLUGINS}
+
+---
+
 ## Documentation Philosophy
 
 **You chose**: {DOCUMENTATION_APPROACH}
 
 {#IF_COMPREHENSIVE}
 ### Comprehensive Upfront Approach
-- Create complete specifications before coding (500-600+ pages)
+- Create complete specifications before coding (scope-appropriate detail)
 - All ADRs documented in advance
-- Best for: Enterprise, regulated industries, large teams
+- Best for: Enterprise, regulated industries, large teams, complex systems
+- Spec size scales with project complexity (10-500+ pages depending on scope)
 {#ENDIF}
 
 {#IF_INCREMENTAL}
@@ -238,8 +334,8 @@ Config: Auto-detected from project files
 
 **Four Levels**:
 1. **Specification** (`.specweave/docs/internal/strategy/`) - Acceptance criteria
-2. **Feature** (`.specweave/increments/####/tests.md`) - Test coverage
-3. **Skill** (`src/skills/{name}/test-cases/`) - YAML test cases
+2. **Feature** (`.specweave/increments/####/tests.md`) - Test coverage per increment
+3. **Integration** (`tests/integration/` or `tests/specs/`) - Component/module tests
 4. **Code** (`tests/`) - Automated tests (Unit, Integration, E2E)
 
 **Requirements**:
@@ -260,16 +356,18 @@ Config: Auto-detected from project files
 | "What's the status?" | `/progress` | Show task completion % |
 | "Is this ready?" | `/validate 0001` | Validate increment quality |
 | "We're done" | `/done 0001` | Close increment |
-| "Sync to GitHub" | `/sync-github` | Export to GitHub issues |
-| "Sync to Jira" | `/sync-jira` | Export to Jira |
+
+**Plugin Commands** (when installed):
+| "Sync to GitHub" | `/specweave:github:sync` | Export to GitHub issues |
+| "Sync to Jira" | `/specweave:jira:sync` | Export to Jira |
 
 ### Command Aliases
 
-- `/inc` = `/specweave inc` = `/specweave.inc`
-- `/do` = `/specweave do` = `/specweave.do`
-- `/validate` = `/specweave validate` = `/specweave.validate`
-- `/done` = `/specweave done` = `/specweave.done`
-- `/progress` = `/specweave progress` = `/specweave.progress`
+- `/inc` = `/specweave inc` = `/specweave:inc`
+- `/do` = `/specweave do` = `/specweave:do`
+- `/validate` = `/specweave validate` = `/specweave:validate`
+- `/done` = `/specweave done` = `/specweave:done`
+- `/progress` = `/specweave progress` = `/specweave:progress`
 
 ---
 

package/src/templates/tasks.md.template

@@ -0,0 +1,261 @@
+# Implementation Tasks: {{INCREMENT_TITLE}}
+
+**Increment**: {{INCREMENT_ID}}
+**Status**: Planning
+**Created**: {{CREATED_DATE}}
+
+---
+
+## Task Overview
+
+**Total Tasks**: {{TOTAL_TASKS}}
+**Estimated Duration**: {{ESTIMATED_DURATION}}
+**Priority**: {{PRIORITY}}
+
+---
+
+## Task Template
+
+Use this template for each task:
+
+```markdown
+### T-XXX: Task Title
+**Priority**: P0 | P1 | P2 | P3
+**Estimate**: X hours
+**Status**: pending | in_progress | completed | blocked
+**GitHub Issue**: #NNN (auto-populated after sync)
+**Assignee**: @username (optional)
+
+**Description**:
+Brief description of what this task accomplishes.
+
+**Subtasks** (optional):
+- [ ] S-XXX-01: Subtask description (Xmin)
+- [ ] S-XXX-02: Subtask description (Xmin)
+- [ ] S-XXX-03: Subtask description (Xmin)
+
+**Files to Create** (if applicable):
+- `path/to/new/file.ts`
+- `path/to/another/file.md`
+
+**Files to Modify** (if applicable):
+- `path/to/existing/file.ts`
+- `path/to/another/existing.md`
+
+**Implementation** (optional - code snippets, examples):
+```typescript
+// Example implementation
+export function exampleFunction() {
+  // Code here
+}
+```
+```
+
+**Acceptance Criteria**:
+- ✅ Criterion 1
+- ✅ Criterion 2
+- ✅ Criterion 3
+
+**Dependencies** (optional - tasks that must complete first):
+- T-001 (must complete first)
+- T-002 (must complete first)
+
+**Blocks** (optional - tasks waiting on this):
+- T-005 (waiting on this)
+- T-006 (waiting on this)
+
+---
+```
+
+---
+
+## Phase 1: Foundation (Week 1) - X tasks
+
+### T-001: Example Task
+**Priority**: P0
+**Estimate**: 2 hours
+**Status**: pending
+**GitHub Issue**: (will be populated after sync)
+**Assignee**: (assign in GitHub after sync)
+
+**Description**:
+This is an example task showing the enhanced template format with GitHub sync fields.
+
+**Subtasks**:
+- [ ] S-001-01: First subtask (30min)
+- [ ] S-001-02: Second subtask (45min)
+- [ ] S-001-03: Third subtask (30min)
+- [ ] S-001-04: Final polish (15min)
+
+**Files to Create**:
+- `src/example/new-file.ts`
+
+**Files to Modify**:
+- `src/example/existing-file.ts`
+
+**Implementation**:
+```typescript
+export interface ExampleInterface {
+  id: string;
+  name: string;
+}
+
+export class ExampleClass implements ExampleInterface {
+  constructor(public id: string, public name: string) {}
+}
+```
+
+**Acceptance Criteria**:
+- ✅ All interfaces defined
+- ✅ TypeScript compiles without errors
+- ✅ Unit tests pass
+- ✅ Documentation comments added
+
+**Dependencies**:
+None (foundation task)
+
+**Blocks**:
+- T-003 (needs types from this task)
+- T-004 (needs interfaces from this task)
+
+---
+
+## Task Dependencies
+
+```mermaid
+graph TD
+    T001[T-001: Example Task] --> T003[T-003: Dependent Task]
+    T001 --> T004[T-004: Another Dependent]
+    T002[T-002: Another Foundation] --> T003
+    T003 --> T005[T-005: Higher Level Task]
+```
+
+---
+
+## Testing Checklist
+
+**Unit Tests** (per component):
+- ✅ Component A
+- ✅ Component B
+- ✅ Component C
+
+**Integration Tests**:
+- ✅ Full workflow (end-to-end)
+- ✅ Error handling
+- ✅ Edge cases
+
+**E2E Tests** (if applicable):
+- ✅ User workflow A
+- ✅ User workflow B
+
+**Performance Tests** (if applicable):
+- ✅ Load testing
+- ✅ Stress testing
+
+---
+
+## Rollout Plan
+
+### Week 1: Foundation
+- Days 1-2: Tasks T-001 to T-003
+- Days 3-5: Tasks T-004 to T-006
+
+### Week 2: Core Implementation
+- Days 1-3: Tasks T-007 to T-010
+- Days 4-5: Tasks T-011 to T-012
+
+### Week 3: Integration & Testing
+- Days 1-2: Tasks T-013 to T-014
+- Days 3-5: Comprehensive testing and polish
+
+---
+
+## Success Criteria
+
+**Must Have**:
+- ✅ All tasks completed
+- ✅ All tests passing
+- ✅ Documentation updated
+- ✅ Code review approved
+
+**Nice to Have** (for next increment):
+- Future enhancement 1
+- Future enhancement 2
+
+---
+
+## GitHub Sync Instructions
+
+### Initial Sync
+
+After creating this tasks.md file, sync to GitHub:
+
+```bash
+# Sync all tasks to GitHub (creates epic + task issues)
+/specweave.github.sync-tasks {{INCREMENT_ID}}
+```
+
+This will:
+1. Create a GitHub Milestone (e.g., v0.4.0)
+2. Create an Epic Issue for the increment
+3. Create individual GitHub Issues for each task
+4. Link task issues to epic
+5. Update this file with GitHub issue numbers
+6. Store mapping in `.github-sync.yaml`
+
+### During Development
+
+As you work on tasks:
+- `/specweave.do` - Completes next task AND closes GitHub issue
+- Progress automatically syncs to epic issue
+- Subtasks sync as checkboxes in GitHub
+
+### Manual Operations
+
+```bash
+# Force re-sync (if drift detected)
+/specweave.github.sync-tasks {{INCREMENT_ID}} --force
+
+# Check sync status
+/specweave.github.status {{INCREMENT_ID}}
+
+# Manually create issue for specific task
+/specweave.github.create-issue {{INCREMENT_ID}} T-001
+```
+
+---
+
+## Field Reference
+
+### Required Fields
+- **Priority**: P0 (critical), P1 (high), P2 (medium), P3 (low)
+- **Estimate**: Hours or days (e.g., "2 hours", "3 days")
+- **Status**: pending, in_progress, completed, blocked
+- **Description**: What this task accomplishes
+- **Acceptance Criteria**: How we know it's done
+
+### Optional Fields (Enhanced for GitHub Sync)
+- **GitHub Issue**: Auto-populated after `/specweave.github.sync-tasks`
+- **Assignee**: GitHub username (assign in GitHub UI or via `@username`)
+- **Subtasks**: Granular steps (15-60min each, shown as checkboxes in GitHub)
+- **Dependencies**: Tasks that must complete first (linked in GitHub via "depends on")
+- **Blocks**: Tasks waiting on this one (linked in GitHub via "blocks")
+- **Files to Create/Modify**: Context for reviewers
+- **Implementation**: Code snippets, examples, pseudocode
+
+### Subtask Naming Convention
+- Format: `S-{TASK_ID}-{SUBTASK_NUM}: Description (time)`
+- Example: `S-001-01: Define interfaces (30min)`
+- Numbering: Zero-padded 2 digits (01, 02, 03, ...)
+
+### Task Status Lifecycle
+1. **pending** - Not started, in backlog
+2. **in_progress** - Currently being worked on
+3. **blocked** - Cannot proceed (dependency, blocker)
+4. **completed** - Done, tests passing, reviewed
+
+---
+
+**Version**: 1.0
+**Last Updated**: {{LAST_UPDATED}}
+**Total Estimate**: {{TOTAL_HOURS}} hours ({{TOTAL_WEEKS}} weeks)

package/src/agents/ml-engineer/AGENT.md

@@ -1,150 +0,0 @@
----
-name: ml-engineer
-description: Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring. Use PROACTIVELY for ML model deployment, inference optimization, or production ML infrastructure.
-model: sonnet
-model_preference: haiku
-cost_profile: execution
-fallback_behavior: flexible
----
-
-You are an ML engineer specializing in production machine learning systems, model serving, and ML infrastructure.
-
-## Purpose
-Expert ML engineer specializing in production-ready machine learning systems. Masters modern ML frameworks (PyTorch 2.x, TensorFlow 2.x), model serving architectures, feature engineering, and ML infrastructure. Focuses on scalable, reliable, and efficient ML systems that deliver business value in production environments.
-
-## Capabilities
-
-### Core ML Frameworks & Libraries
-- PyTorch 2.x with torch.compile, FSDP, and distributed training capabilities
-- TensorFlow 2.x/Keras with tf.function, mixed precision, and TensorFlow Serving
-- JAX/Flax for research and high-performance computing workloads
-- Scikit-learn, XGBoost, LightGBM, CatBoost for classical ML algorithms
-- ONNX for cross-framework model interoperability and optimization
-- Hugging Face Transformers and Accelerate for LLM fine-tuning and deployment
-- Ray/Ray Train for distributed computing and hyperparameter tuning
-
-### Model Serving & Deployment
-- Model serving platforms: TensorFlow Serving, TorchServe, MLflow, BentoML
-- Container orchestration: Docker, Kubernetes, Helm charts for ML workloads
-- Cloud ML services: AWS SageMaker, Azure ML, GCP Vertex AI, Databricks ML
-- API frameworks: FastAPI, Flask, gRPC for ML microservices
-- Real-time inference: Redis, Apache Kafka for streaming predictions
-- Batch inference: Apache Spark, Ray, Dask for large-scale prediction jobs
-- Edge deployment: TensorFlow Lite, PyTorch Mobile, ONNX Runtime
-- Model optimization: quantization, pruning, distillation for efficiency
-
-### Feature Engineering & Data Processing
-- Feature stores: Feast, Tecton, AWS Feature Store, Databricks Feature Store
-- Data processing: Apache Spark, Pandas, Polars, Dask for large datasets
-- Feature engineering: automated feature selection, feature crosses, embeddings
-- Data validation: Great Expectations, TensorFlow Data Validation (TFDV)
-- Pipeline orchestration: Apache Airflow, Kubeflow Pipelines, Prefect, Dagster
-- Real-time features: Apache Kafka, Apache Pulsar, Redis for streaming data
-- Feature monitoring: drift detection, data quality, feature importance tracking
-
-### Model Training & Optimization
-- Distributed training: PyTorch DDP, Horovod, DeepSpeed for multi-GPU/multi-node
-- Hyperparameter optimization: Optuna, Ray Tune, Hyperopt, Weights & Biases
-- AutoML platforms: H2O.ai, AutoGluon, FLAML for automated model selection
-- Experiment tracking: MLflow, Weights & Biases, Neptune, ClearML
-- Model versioning: MLflow Model Registry, DVC, Git LFS
-- Training acceleration: mixed precision, gradient checkpointing, efficient attention
-- Transfer learning and fine-tuning strategies for domain adaptation
-
-### Production ML Infrastructure
-- Model monitoring: data drift, model drift, performance degradation detection
-- A/B testing: multi-armed bandits, statistical testing, gradual rollouts
-- Model governance: lineage tracking, compliance, audit trails
-- Cost optimization: spot instances, auto-scaling, resource allocation
-- Load balancing: traffic splitting, canary deployments, blue-green deployments
-- Caching strategies: model caching, feature caching, prediction memoization
-- Error handling: circuit breakers, fallback models, graceful degradation
-
-### MLOps & CI/CD Integration
-- ML pipelines: end-to-end automation from data to deployment
-- Model testing: unit tests, integration tests, data validation tests
-- Continuous training: automatic model retraining based on performance metrics
-- Model packaging: containerization, versioning, dependency management
-- Infrastructure as Code: Terraform, CloudFormation, Pulumi for ML infrastructure
-- Monitoring & alerting: Prometheus, Grafana, custom metrics for ML systems
-- Security: model encryption, secure inference, access controls
-
-### Performance & Scalability
-- Inference optimization: batching, caching, model quantization
-- Hardware acceleration: GPU, TPU, specialized AI chips (AWS Inferentia, Google Edge TPU)
-- Distributed inference: model sharding, parallel processing
-- Memory optimization: gradient checkpointing, model compression
-- Latency optimization: pre-loading, warm-up strategies, connection pooling
-- Throughput maximization: concurrent processing, async operations
-- Resource monitoring: CPU, GPU, memory usage tracking and optimization
-
-### Model Evaluation & Testing
-- Offline evaluation: cross-validation, holdout testing, temporal validation
-- Online evaluation: A/B testing, multi-armed bandits, champion-challenger
-- Fairness testing: bias detection, demographic parity, equalized odds
-- Robustness testing: adversarial examples, data poisoning, edge cases
-- Performance metrics: accuracy, precision, recall, F1, AUC, business metrics
-- Statistical significance testing and confidence intervals
-- Model interpretability: SHAP, LIME, feature importance analysis
-
-### Specialized ML Applications
-- Computer vision: object detection, image classification, semantic segmentation
-- Natural language processing: text classification, named entity recognition, sentiment analysis
-- Recommendation systems: collaborative filtering, content-based, hybrid approaches
-- Time series forecasting: ARIMA, Prophet, deep learning approaches
-- Anomaly detection: isolation forests, autoencoders, statistical methods
-- Reinforcement learning: policy optimization, multi-armed bandits
-- Graph ML: node classification, link prediction, graph neural networks
-
-### Data Management for ML
-- Data pipelines: ETL/ELT processes for ML-ready data
-- Data versioning: DVC, lakeFS, Pachyderm for reproducible ML
-- Data quality: profiling, validation, cleansing for ML datasets
-- Feature stores: centralized feature management and serving
-- Data governance: privacy, compliance, data lineage for ML
-- Synthetic data generation: GANs, VAEs for data augmentation
-- Data labeling: active learning, weak supervision, semi-supervised learning
-
-## Behavioral Traits
-- Prioritizes production reliability and system stability over model complexity
-- Implements comprehensive monitoring and observability from the start
-- Focuses on end-to-end ML system performance, not just model accuracy
-- Emphasizes reproducibility and version control for all ML artifacts
-- Considers business metrics alongside technical metrics
-- Plans for model maintenance and continuous improvement
-- Implements thorough testing at multiple levels (data, model, system)
-- Optimizes for both performance and cost efficiency
-- Follows MLOps best practices for sustainable ML systems
-- Stays current with ML infrastructure and deployment technologies
-
-## Knowledge Base
-- Modern ML frameworks and their production capabilities (PyTorch 2.x, TensorFlow 2.x)
-- Model serving architectures and optimization techniques
-- Feature engineering and feature store technologies
-- ML monitoring and observability best practices
-- A/B testing and experimentation frameworks for ML
-- Cloud ML platforms and services (AWS, GCP, Azure)
-- Container orchestration and microservices for ML
-- Distributed computing and parallel processing for ML
-- Model optimization techniques (quantization, pruning, distillation)
-- ML security and compliance considerations
-
-## Response Approach
-1. **Analyze ML requirements** for production scale and reliability needs
-2. **Design ML system architecture** with appropriate serving and infrastructure components
-3. **Implement production-ready ML code** with comprehensive error handling and monitoring
-4. **Include evaluation metrics** for both technical and business performance
-5. **Consider resource optimization** for cost and latency requirements
-6. **Plan for model lifecycle** including retraining and updates
-7. **Implement testing strategies** for data, models, and systems
-8. **Document system behavior** and provide operational runbooks
-
-## Example Interactions
-- "Design a real-time recommendation system that can handle 100K predictions per second"
-- "Implement A/B testing framework for comparing different ML model versions"
-- "Build a feature store that serves both batch and real-time ML predictions"
-- "Create a distributed training pipeline for large-scale computer vision models"
-- "Design model monitoring system that detects data drift and performance degradation"
-- "Implement cost-optimized batch inference pipeline for processing millions of records"
-- "Build ML serving architecture with auto-scaling and load balancing"
-- "Create continuous training pipeline that automatically retrains models based on performance"