mirror of
https://github.com/x1xhlol/system-prompts-and-models-of-ai-tools.git
synced 2026-02-08 16:00:50 +00:00
Add 25 world-class Claude Code skills for comprehensive software development
Created comprehensive skill collection covering all aspects of modern software development with production-ready patterns, best practices, and detailed documentation. ## Skills Organized by Domain ### Code Quality & Architecture (2 skills) - advanced-code-refactoring: SOLID principles, design patterns, refactoring patterns - code-review: Automated/manual review, security, performance, maintainability ### API & Integration (2 skills) - api-integration-expert: REST/GraphQL/WebSocket with auth, retry, caching - graphql-schema-design: Schema design, resolvers, optimization, subscriptions ### Database & Data (3 skills) - database-optimization: SQL/NoSQL tuning, indexing, query optimization - data-pipeline: ETL/ELT with Airflow, Spark, dbt - caching-strategies: Redis, Memcached, CDN, invalidation patterns ### Security & Authentication (2 skills) - security-audit: OWASP Top 10, vulnerability scanning, security hardening - auth-implementation: OAuth2, JWT, session management, SSO ### Testing & Quality (2 skills) - test-automation: Unit/integration/E2E tests, TDD/BDD, coverage - performance-profiling: CPU/memory profiling, Core Web Vitals optimization ### DevOps & Infrastructure (3 skills) - docker-kubernetes: Containerization, orchestration, production deployments - ci-cd-pipeline: GitHub Actions, automated testing, deployment strategies - logging-monitoring: Observability with Datadog, Prometheus, Grafana, ELK ### Frontend Development (3 skills) - frontend-accessibility: WCAG 2.1 compliance, ARIA, keyboard navigation - ui-component-library: Design systems with React/Vue, Storybook - mobile-responsive: Responsive design, mobile-first, PWAs ### Backend & Scaling (2 skills) - backend-scaling: Load balancing, sharding, microservices, horizontal scaling - real-time-systems: WebSockets, SSE, WebRTC for real-time features ### ML & AI (1 skill) - ml-model-integration: Model serving, inference optimization, monitoring ### Development Tools (2 skills) - git-workflow-optimizer: Git workflows, branching strategies, conflict resolution - dependency-management: Package updates, security patches, version conflicts ### Code Maintenance (3 skills) - error-handling: Robust error patterns, logging, graceful degradation - documentation-generator: API docs, README, technical specifications - migration-tools: Database/framework migrations with zero downtime ## Key Features Each skill includes: - YAML frontmatter with name, description, allowed tools - Clear purpose and when to use - Comprehensive capabilities overview - Production-ready code examples - Best practices and patterns - Success criteria - Tool-specific configurations ## Highlights - 25 comprehensive skills covering full development lifecycle - Production-ready patterns and examples - Security-first approach throughout - Performance optimization built-in - Comprehensive testing strategies - DevOps automation and infrastructure as code - Modern frontend with accessibility focus - Scalable backend architectures - Data engineering and ML integration - Advanced Git workflows ## File Structure claude_skills/ ├── README.md (comprehensive documentation) ├── advanced-code-refactoring/ │ ├── SKILL.md (main skill definition) │ ├── reference.md (design patterns, SOLID principles) │ └── examples.md (refactoring examples) ├── api-integration-expert/ │ └── SKILL.md (REST/GraphQL/WebSocket integration) ├── [23 more skills...] Total: 25 skills + comprehensive README + supporting documentation ## Usage Personal skills: cp -r claude_skills/* ~/.claude/skills/ Project skills: cp -r claude_skills/* .claude/skills/ Skills automatically activate based on context and description triggers.
This commit is contained in:
84
claude_skills/ml-model-integration/SKILL.md
Normal file
84
claude_skills/ml-model-integration/SKILL.md
Normal file
@@ -0,0 +1,84 @@
|
||||
---
|
||||
name: ml-model-integration
|
||||
description: Expert in integrating AI/ML models into applications including model serving, API design, inference optimization, and monitoring. Use when deploying ML models, building AI features, or optimizing model performance in production.
|
||||
allowed-tools: Read, Write, Edit, Grep, Glob, Bash
|
||||
---
|
||||
|
||||
# ML Model Integration Expert
|
||||
|
||||
## Purpose
|
||||
Deploy and integrate machine learning models into production applications.
|
||||
|
||||
## Capabilities
|
||||
- Model serving (FastAPI, TensorFlow Serving)
|
||||
- Inference optimization
|
||||
- A/B testing models
|
||||
- Model versioning
|
||||
- Monitoring and drift detection
|
||||
- Batch and real-time inference
|
||||
- Feature stores
|
||||
|
||||
## FastAPI Model Serving
|
||||
```python
|
||||
from fastapi import FastAPI
|
||||
from pydantic import BaseModel
|
||||
import joblib
|
||||
import numpy as np
|
||||
|
||||
app = FastAPI()
|
||||
|
||||
# Load model at startup
|
||||
model = joblib.load('model.pkl')
|
||||
|
||||
class PredictionRequest(BaseModel):
|
||||
features: list[float]
|
||||
|
||||
class PredictionResponse(BaseModel):
|
||||
prediction: float
|
||||
confidence: float
|
||||
|
||||
@app.post('/predict', response_model=PredictionResponse)
|
||||
async def predict(request: PredictionRequest):
|
||||
features = np.array([request.features])
|
||||
prediction = model.predict(features)[0]
|
||||
confidence = model.predict_proba(features).max()
|
||||
|
||||
return PredictionResponse(
|
||||
prediction=float(prediction),
|
||||
confidence=float(confidence)
|
||||
)
|
||||
|
||||
@app.get('/health')
|
||||
async def health():
|
||||
return {'status': 'healthy', 'model_version': '1.0.0'}
|
||||
```
|
||||
|
||||
## Model Monitoring
|
||||
```python
|
||||
import mlflow
|
||||
|
||||
# Log model performance
|
||||
with mlflow.start_run():
|
||||
mlflow.log_metric('accuracy', accuracy)
|
||||
mlflow.log_metric('precision', precision)
|
||||
mlflow.log_metric('recall', recall)
|
||||
mlflow.log_param('model_type', 'random_forest')
|
||||
mlflow.sklearn.log_model(model, 'model')
|
||||
|
||||
# Monitor drift
|
||||
from evidently import ColumnMapping
|
||||
from evidently.report import Report
|
||||
from evidently.metric_preset import DataDriftPreset
|
||||
|
||||
report = Report(metrics=[DataDriftPreset()])
|
||||
report.run(reference_data=train_data, current_data=prod_data)
|
||||
report.save_html('drift_report.html')
|
||||
```
|
||||
|
||||
## Success Criteria
|
||||
- ✓ Inference latency < 100ms
|
||||
- ✓ Model accuracy monitored
|
||||
- ✓ A/B testing framework
|
||||
- ✓ Rollback capability
|
||||
- ✓ Feature drift detected
|
||||
|
||||
Reference in New Issue
Block a user