smithery.ai

genai-integration

Expert guidance for integrating GenAI models, workflows, and observability into applications. (use when designing or implementing LLM/agent/RAG integrations)

First seen Apr 23, 2026

Installation

$ npx skills add https://smithery.ai

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from smithery.ai · top by installs.

npx skills add https://smithery.ai

Browse all from smithery.ai

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Skill metadata

Parsed from SKILL.md frontmatter.

Version1.0.0

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,296 B
  • docs SUMMARY.md 182 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1 installs

SKILL.md

Purpose

Teach the agent how to handle GenAI integration tasks — selecting models, building prompt templates, RAG pipelines, cost optimization, and validation workflows.

When to Apply

Use this Skill when the user asks to:

  • integrate a GenAI API into an application
  • design RAG workflows, embeddings pipelines, or agents
  • build prompt templates or schema-validated prompts
  • write automation for cost or token optimization
  • add testing, logging, or observability around GenAI tasks

Instructions

  1. Detect Task Intent

- Identify if the request is about GenAI model selection, API integration, workflow design, or optimization. - If the task involves specific frameworks (Node/Python, serverless, Vercel/AWS), include relevant context.

  1. Model & Provider Guidance

- Recommend models according to cost, latency, context length, and compliance needs. - Prefer structured outputs (JSON schemas) and function/tool calling where appropriate.

  1. Prompt Engineering

- Generate prompt templates: system, developer, and user layers. - Use few-shot examples and explicit output schemas in prompts.

  1. RAG & Embeddings

- Break documents into chunks with semantic similarity filtering. - Outline vector store choice and search parameters (faiss/pinecone/weaviate).

  1. Agent Workflows

- If task requires agents, design tool use steps, fallback logic, and task decomposition. - Provide stepwise workflows for planning and execution.

  1. Cost & Token Strategy

- Suggest caching, batching, model tiering, and token budget limits. - Provide scripts or commands (in scripts/) for automation.

  1. Validation & Safety

- Add output validators (schema checks). - Mitigate prompt injection and unsafe operations.

Output Format Guidelines

  • Include JSON-schema blocks where structured output is required.

Examples (Trigger Patterns)

  • “Integrate LLM for customer support chatbot with RAG”
  • “Design GenAI prompt templates for summarization API”
  • “Automate token cost reduction for GenAI calls”