How do I install the Lumina Gemini API skill?

Run npx skillmds@latest add tomevault-io/lumina-gemini-api in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Lumina Gemini API safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Lumina Gemini API?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Lumina Gemini API free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Lumina Gemini API?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Lumina Gemini API by tomevault-io — Agent Skill

Name: Lumina Gemini API
Author: tomevault-io

Lumina Gemini API

Project-specific guidance for Lumina Studio's Gemini API integration across text chat, image generation, video generation, function calling, search, thinking, and multi-turn context. Use when working in services/geminiService.ts, services/agentService.ts, components/ChatInterface.tsx, or App.tsx, or when debugging prompt/parameter flow and context bridging for Gemini/Veo in this project. Use when this capability is needed.

tomevault-io Updated Sep 17, 2026

File contents

Lumina Gemini Api

Overview

Use this skill to implement or debug Lumina Studio's Gemini API behavior with correct prompt flow, tool calling, and context handling for text, image, and video generation.

Workflow

Identify the request type: text chat, image gen, video gen, tool calling, search, or multi-turn editing.
Open the project implementation reference first to align changes with current behavior.
Check official API notes only for the relevant surface (text, image, video, tools).
Make changes in the smallest scope and keep chat vs studio isolation intact.
Verify model IDs and config fields against the model matrix.

Guardrails

Treat tool call args as possibly wrapped in parameters; unpack before use.
Do not fall back to Studio params when handling chat tool calls; keep chat and studio contexts isolated.
Keep search and function declarations in separate requests; do not mix them.
Preserve multi-turn image behavior by using the per-project image chat session or explicit reference images.

References

references/lumina-implementation.md: open when changing or debugging project code paths.
references/model-matrix.md: open when validating model IDs or defaults.
references/official-docs.md: open when verifying API surface details or best practices.

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: lumina-gemini-apidescription: Project-specific guidance for Lumina Studio's Gemini API integration across text chat, image generation, video generation, function calling, search, thinking, and multi-turn context. Use when working in services/geminiService.ts, services/agentService.ts, components/ChatInterface.tsx, or App.tsx, or when debugging prompt/parameter flow and context bridging for Gemini/Veo in this project. Use when this capability is needed.---# Lumina Gemini Api## OverviewUse this skill to implement or debug Lumina Studio's Gemini API behavior with correct prompt flow, tool calling, and context handling for text, image, and video generation.## Workflow1. Identify the request type: text chat, image gen, video gen, tool calling, search, or multi-turn editing.2. Open the project implementation reference first to align changes with current behavior.3. Check official API notes only for the relevant surface (text, image, video, tools).4. Make changes in the smallest scope and keep chat vs studio isolation intact.5. Verify model IDs and config fields against the model matrix.## Guardrails- Treat tool call args as possibly wrapped in `parameters`; unpack before use.- Do not fall back to Studio params when handling chat tool calls; keep chat and studio contexts isolated.- Keep search and function declarations in separate requests; do not mix them.- Preserve multi-turn image behavior by using the per-project image chat session or explicit reference images.## References- `references/lumina-implementation.md`: open when changing or debugging project code paths.- `references/model-matrix.md`: open when validating model IDs or defaults.- `references/official-docs.md`: open when verifying API surface details or best practices.---> Converted and distributed by [TomeVault](https://tomevault.io/claim/alan-512) — claim your Tome and manage your conversions.

Frequently asked questions