# Gemini API

> Builds or debugs Google Gemini features using @google/generative-ai, covering generateContent, function calling, grounding, multimodal input, and streaming, with guidance for editing src/lib/ai/clients/google.ts.

- Skill: `joshuashepherd/gemini-api` (Agent Skill)
- Install (CLI): `npx skillmds@latest add joshuashepherd/gemini-api`
- Raw SKILL.md: https://api.skillmd.com/api/skills/joshuashepherd/gemini-api/raw
- Safety review: PASS (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Integrations & APIs, AI & ML, REST & GraphQL APIs
- Tags: Function Calling, Gemini, Google Generative Ai, Grounding, Multimodal, Streaming, Typescript
- Author: JoshuaShepherd (https://skillmd.com/u/joshuashepherd)
- Updated: 2026-08-22
- Page: https://skillmd.com/skills/joshuashepherd/gemini-api

---


# Gemini API (Cursor)

## Canonical source

**`.claude/skills/gemini-api/SKILL.md`** includes **ai.google.dev** links and patterns for models 2.5/3.x family features.

## In Cursor

1. Read the relevant section in the canonical skill (grounding, vision, streaming, etc.).
2. Use **WebFetch** on the official Gemini docs URLs from that skill when verifying current model IDs or API shapes.
3. Use `googleClient` and `getGeminiModel()` from `src/lib/ai/clients/google.ts`; never read `process.env.GOOGLE_AI_API_KEY` directly in feature code.