Cristiano Bilacchi
Community@bilacchi · Brazil - SP
Data Scientist & Bs.C Science and Technology, Bs.C Robotics Engineering and Bs.C Neuroscience.
Agent Skills by Cristiano Bilacchi
Showing 100 vetted skills indexed across 1 GitHub repositories.
bilacchilangfuse
Instrument LLM applications with tracing, prompt management, and evaluation using Langfuse.
bilacchireact-patterns
Guides writing and reviewing React 18/19 components using hooks discipline, RSC boundaries, and accessibility patterns.
bilacchiplaywright-skill
Provides Playwright testing guidance for E2E, API, visual, accessibility, and CI/CD workflows.
bilacchilanggraph
Build stateful multi-actor AI agents with graph-based workflows in Python.
bilacchikubernetes-architect
Design Kubernetes platform architecture, GitOps workflows, and multi-cluster deployment strategies.
bilacchicontainer-security-hardening
Harden Docker images and Kubernetes deployments with scanning, signing, and runtime security controls.
bilacchiweb-security-testing
Tests web applications against OWASP Top 10 vulnerabilities through a seven-phase assessment workflow.
bilacchiarchitecture-decision-records
Create and manage Architecture Decision Records documenting technical decisions and trade-offs.
bilacchibackend-dev-guidelines
Enforces layered architecture and error handling standards for Node.js Express backend services.
bilacchipython-testing
Write and organize Python tests using pytest fixtures, parametrization, mocking, and coverage analysis.
bilacchipython-testing-patterns
Implement pytest test suites with fixtures, mocking, parameterization, and coverage reporting.
bilacchidocker-patterns
Configure Docker Compose stacks, Dockerfiles, networking, volumes, and container security for development environments.
bilacchifrontend-developer
Builds and optimizes React and Next.js components with accessibility and performance guidance.
bilacchiapi-design-principles
Design REST and GraphQL APIs with versioning, pagination, and error handling patterns.
bilacchipython-packaging
Create, build, and publish Python packages using pyproject.toml and PyPI.
bilacchitest-driven-development
Enforces red-green-refactor test-driven development workflow for features and bugfixes.
bilacchipostgres-patterns
Provides PostgreSQL patterns for query optimization, schema design, indexing, and security.
bilacchillm-evaluation
Evaluate LLM application outputs using automated metrics, LLM-as-judge, and A/B testing.
bilacchiarchitecture-patterns
Design backend systems using Clean Architecture, Hexagonal Architecture, and Domain-Driven Design patterns.
bilacchidatabase-design
Guides database selection, schema design, indexing, and query optimization decisions.
bilacchicontext7-auto-research
Fetches up-to-date library and framework documentation via the Context7 API.
bilacchifastapi-pro
Guides building async FastAPI services with Pydantic validation, authentication, testing, and deployment.
bilacchinextjs-best-practices
Applies Next.js App Router best practices for components, routing, caching, and performance.
bilacchihandoff
Generate a conversation summary document for continuing work in a new agent session.
Frequently Asked Questions About Cristiano Bilacchi
FAQPage SchemaWhat tasks can I accomplish with bilacchi's skill collection?▼
You can build LLM applications with RAG and structured output, design Kubernetes architectures with Helm charts and GitOps, write pytest and Playwright test suites, optimize PostgreSQL queries, perform OWASP security assessments, and apply React 18/19, FastAPI, Rust, and async Python patterns.
Who is the target audience for these skills?▼
Backend and frontend engineers, platform engineers managing Kubernetes clusters, QA engineers building E2E test suites, security reviewers auditing containers and GitHub Actions, and ML engineers implementing LLM observability, evaluation rubrics, and prompt optimization.
What LLM engineering capabilities are covered?▼
Skills cover LangChain and LangGraph agent architectures, Langfuse observability, agent memory systems, function calling, hybrid vector-keyword retrieval, structured JSON output via schema-constrained decoding, LLM-as-judge evaluation with bias mitigation, and prompt optimization to reduce hallucinations and token usage.
Are these skills free and open source?▼
Yes. Skills carry permissive licenses including Apache 2.0 (vibeship-spawner-skills) and MIT (playwright-skill, skill-optimizer, Supabase-derived postgres-patterns). Most community-sourced skills list no restrictive license, making them free to adopt and modify.
What prerequisites or dependencies do these skills require?▼
Dependencies vary by skill: Playwright skills need TypeScript/JavaScript environments, Python skills target 3.12+ with pytest or uv, Kubernetes skills require cluster access and Helm, and search skills need Exa, Tavily, or Firecrawl API keys. Database skills assume PostgreSQL or ORMs like Prisma.