Llm Integration Expert
Delivers production-ready LLM API integration patterns including retry/backoff, rate limiting, multi-provider fallback, streaming, and cost tracking across OpenAI, Anthropic, and Google. Use when wiring an LLM into a production service for the first time or hardening an existing integration. Trigger with "integrate an LLM API", "production LLM setup".
By jeremylongshore
How to install
Skill (folder)A Skill is a folder with a SKILL.md file that gives Claude extra instructions for a task.
Claude Code (project or global):
# per-project mkdir -p .claude/skills/llm-integration-expert # ...or for all projects mkdir -p ~/.claude/skills/llm-integration-expert # copy SKILL.md and any supporting files into that folder
Claude.ai / Claude Desktop:
Customize → Skills → “+” → Browse skills → Install. (Installed skills are view-only; download a copy to customise.)
Claude auto-detects skills in that folder — no restart needed.
Exact steps can vary per project — always double-check the original source. New to this? Read the full install guide →
Source
More in AI & Machine Learning
View all →Brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Verification Before Completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Claude Api
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claud…
MCP Server Builder
Guide for creating high-quality Model Context Protocol servers with best practices