Gemini API Dev Guide
Official Gemini API rules for Gemini 3 and Flash — models, text, vision, audio, web grounding
- What
- Official Gemini API rules for Gemini 3 and Flash — models, text, vision, audio, web grounding
- Cost
- Free
- Needs
- a Google AI Studio or AI Gateway API key (GEMINI_API_KEY as an environment variable) — paid service; Python with the google-genai package (v1)
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
💳 Curated by Skill Harbor — the official Gemini API skill from Google's own repo: hard rules for developing with Gemini — use the google-genai SDK (`from google import genai`, Python `google-genai >= 2.25.0`, JS/TS `@google/genai >= 2.3.0`), default to `gemini-3.8-flash` (fast) and `gemini-3.1-pro-preview` for complex reasoning, coding, and research, never use the legacy SDKs (`google-generativeai`, `@google/generative-ai`) or the deprecated `gemini-1.5-*`, `gemini-2.0-*`, and `gemini-2.5-*` models (if one is requested, substitute `gemini-3.8-flash` and say so), and fetch the matching hosted doc page before writing code — the docs, not the examples, are the source of truth. It covers stateful conversations, response helpers, streaming, Deep Research and managed agents (Antigravity, custom agents), image, video, and speech generation, the interaction data model, and the Gemini Live API skill. Honest transparency: its rules override your training data — treat model names and package versions as frozen at the skill's last update, and check Google's docs for the current list; interactions are stored by default (55 days paid tier, 1 day free tier). By @google-gemini, listed here with credit to its creator. Skill Harbor never reviews the code, review it yourself before use.
Version:
Quick answer
Gemini API Dev Guide is a free Gemini API skill from Google's repo with hard rules for developing with Gemini. API keys live in environment variables, from ~/.gemini/.env, never in files, no client wrapper, use google-genai v1, pin gemini-3-pro-preview for reasoning and gemini-2.5-flash for speed in a single AI_GATEWAY key, never mix SDK generations, and use pydantic schemas.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 832c8f9Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: a Google AI Studio or AI Gateway API key (GEMINI_API_KEY as an environment variable) — paid service; Python with the google-genai package (v1) Install "Gemini API Dev Guide" for me. Official Gemini API development rules — keys, text, vision, audio, web grounding Repository: https://raw.githubusercontent.com/google-gemini/gemini-skills/832c8f94114dc343d86ff27296fe9335b45affa0/skills/gemini-api-dev/SKILL.md Pinned version: install the code at commit 832c8f94114dc343d86ff27296fe9335b45affa0 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file for the google-gemini-gemini-skills-gemini-api-dev skill from the repository into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "google-gemini-gemini-skills-gemini-api-dev". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. any accounts, API keys, or CLI tools mentioned in the prerequisites above). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. Never ask me to paste secrets in chat — credentials go through the secure vault or environment variables. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
- It works with an API key or a token that you provide.
What the scan found — excerpts from the install prompt
- uses API keys or tokens — Prerequisites: a Google AI Studio or AI Gateway API key (GEMINI_API_KEY as an environment variable) — paid ser · Prérequis : une clé API Google AI Studio ou AI Gateway (GEMINI_API_KEY comme variable d'environnement) — servi
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 832c8f9 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : uses API keys or tokens
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.