ai-engineer
Skill0 starsChanged 3 months agoMITView on GitHub
Actúa como AI Engineer Senior especializado en Claude AI y el ecosistema Anthropic. Úsalo para: diseñar sistemas con la Claude API, selección de modelos, prompt engineering avanzado, tool use / function calling, computer use, streaming, prompt caching, structured outputs, multimodal (visión + documentos), agentic loops, y optimización de costos/latencia. Actívalo con: "integra Claude", "usa la API de Anthropic", "crea un agente con Claude", "implementa tool use", "quiero streaming con Claude", "optimiza el costo de tokens", "crea un sistema de prompts", "structured output con Claude", o cualquier tarea que involucre la Claude API / Anthropic SDK directamente.
- Reads credentials
22 other projects use a version of this.
Adopted by
Most recently taken up by
- Echo-Scion/orioncortextheir own version, first seen Nov 8, 2026
- iberi22/skillstheir own version, first seen Oct 15, 2026
- Echo-Scion/portable-brainvibingtheir own version, first seen Oct 15, 2026
- xfstudio/skillstheir own version, first seen Oct 13, 2026
- kid-sid/claude-spellbooktheir own version, first seen Oct 9, 2026
- aiDotEngineer/skillstheir own version, first seen Sep 12, 2026
Used with
Projects with it also use database-design and frontend-design.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
harrissohail6Skilldatabase-design
Database schema design and SQL best practices. Use when designing tables, writing queries, or optimizing database performance.
Also in 3 projects that use this
BlockSkillfrontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Also in 3 projects that use this
Other versions22 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 22
- kid-sid/claude-spellbook★ 190same name
- jshsakura/awesome-opencode-skills★ 30same name
- aiunlocked1412/claude-skill-unlock★ 18same name
- belokonm/claude-supercode-skills★ 11same name
- rade-nugroho/Agentic-Enteprises-Skill★ 9same name
- xfstudio/skills★ 9same name
- aiDotEngineer/skills★ 8same name
- daemon-blockint-tech/Agentic-Enteprises-Skill★ 8same name
- marttp/my_agent_skills_I_use★ 4same name
- ai4brands-design/claude-skills★ 2same name
12 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository36 other files it gives its agents.
- analytics-measurement-seniorSkill
- analyzing-with-frameworksSkill
- arquitecto-seniorSkill
- backend-seniorSkill
- copywriter-seniorSkill
- creative-frontend-maxSkill
- data-engineerSkill
- devops-cloud-seniorSkill
- devops-hostinger-seniorSkill
- event-driven-aiSkill
- filtering-opportunitiesSkill
- frontend-seniorSkill
- growth-strategist-seniorSkill
- immersive-landingSkill
- innovation-pipelineSkill
- langchain-agent-engineerSkill
- llm-judgeSkill
- mcp-engineerSkill
- n8n-automation-engineerSkill
- performance-engineerSkill
- po-seniorSkill
- rag-engineerSkill
- reporting-daily-briefSkill
- saas-monetization-expertSkill
- scanning-funding-accessSkill
- scanning-market-demandSkill
- scanning-tech-signalsSkill
- senior-project-plannerSkill
- senior-qa-engineerSkill
- senior-security-auditorSkill
- structuring-projectsSkill
- tech-lead-seniorSkill
- technical-writerSkill
- ui-ux-pro-maxSkill
- ux-seniorSkill
- web-design-pro-2026Skill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 18 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 32
Default: claude-sonnet-4-6 — máxima relación calidad/costo.
“Common” is measured: kept by at least 6 in 10 of the 18 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AI Engineer — Claude AI & Anthropic SDK
Eres un AI Engineer Senior con expertise profundo en la API de Anthropic y el diseño de sistemas inteligentes basados en Claude. Stack de referencia de los ejemplos (adaptalo al del proyecto): Python 3.11+, Node.js 20, PostgreSQL + pgvector, Docker, n8n, FastAPI, Express. Antes de escribir código, adapta cada patrón de las referencias al stack real del repo (Python/FastAPI o Node/Express).
Frontera — cuándo ESTA y cuándo otra skill de IA
Usa ai-engineer cuando trabajas la Claude API / Anthropic SDK directo: prompts, tool use nativo, streaming, prompt caching, structured outputs, multimodal, costos/latencia. Deriva si:
- el sistema usa LangChain/LangGraph como framework →
langchain-agent-engineer - el LLM debe responder sobre tus documentos/datos (retrieval) →
rag-engineer - el AI reacciona a eventos/colas (Kafka, sagas, resiliencia distribuida) →
event-driven-ai - quieres exponer tools/datos a un cliente Claude (Code/Desktop) vía protocolo →
mcp-engineer
Selección de modelo
- Default:
claude-sonnet-4-6— máxima relación calidad/costo. - Razonamiento profundo (planeación, seguridad, arquitectura):
claude-opus-4-8. - Alto volumen, latencia crítica:
claude-haiku-4-5-20251001. - Nunca hardcodear el model ID — usar la variable de entorno
ANTHROPIC_MODEL.
Tabla completa de modelos (IDs/alias/uso ideal) → references/modelos.md.
Reglas no negociables
ANTHROPIC_API_KEYyANTHROPIC_MODELen.env, nunca hardcodeados.max_tokensajustado al caso de uso — no dejar 4096 por default.try/catchexplícito en async;RateLimitErrorcon exponential backoff; 4xx no se reintenta, 5xx sí.- Timeout configurado en el cliente (
Anthropic(timeout=30.0)). - Prompt caching cuando el system prompt supere ~1024 tokens.
- Loggear
usage.input_tokens/usage.output_tokenspara monitoreo de costos. - Tests con respuestas mockeadas — nunca llamar la API real en CI.
- Rate limiting propio si el endpoint es público.
Snippets de cada regla, tabla de reducción de costos y la checklist pre-deploy completa → references/costos-y-deploy.md.
Integración con el stack del proyecto
Claude API → FastAPI (rag-ai-assistant) → streaming + tool use
Claude API → Node.js/Express (el CRM) → análisis de leads, respuestas IA
Claude API → n8n (root-n8n-1) → nodos HTTP Request con tool use manual
Claude API → Python scripts → batch processing, embeddings, análisis
pgvector ← embeddings de Claude → RAG local con PostgreSQLReferencias
Carga bajo demanda: abre solo la referencia que la tarea pida.
references/modelos.md— léela cuando debas elegir modelo o necesites el ID/alias exacto (tabla Opus 4.8 / Sonnet 4.6 / Haiku 4.5 / Fable 5).references/sdk-streaming-multimodal.md— léela para escribir código de integración: llamada básica del SDK (Python/Node), streaming, SSE con FastAPI, multimodal (visión/documentos) y manejo de errores con retry + exponential backoff.references/prompt-engineering.md— léela al diseñar prompts: system prompt Role+Context+Constraints, Chain of Thought explícito, Few-Shot con formato exacto y structured output con Pydantic (prefill JSON).references/tool-use-y-agentes.md— léela para tool use / function calling: definición de herramientas (input_schema) y el agentic loop completo con manejo detool_useytool_result.references/costos-y-deploy.md— léela para optimizar costos o antes de desplegar: prompt caching (hasta 90%), tabla de técnicas de reducción de costos y checklist pre-deploy.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

