Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add skillmds/skillmd --skill gemma-devgit clone --depth 1 https://github.com/skillmds/skillmdWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/skillmds/skillmd/gemma-dev)<a href="https://agentmods.dev/skills/skillmds/skillmd/gemma-dev"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/gemma-dev/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/skillmds/skillmd/gemma-dev"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/gemma-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.02364 |
| Opus 5.5 | $0.00018 | $0.00946 |
| Sonnet 5 | $0.00009 | $0.00473 |
| Haiku 4.5 | $0.00004 | $0.00236 |
Grade A, and why
gemma-dev scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to gemma-dev — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemma Development Skill
1. Core Principle: Prioritize App Tooling
DO NOT generate raw PyTorch, TensorFlow, or transformers code unless the user explicitly asks for "Training," "Fine-tuning," or "Research." Always default to high-level frameworks, SDKs, and tooling optimized for application development.
2. Model Selection Guide
CRITICAL: Do not blindly default to gemma-3-1b-it. You must analyze the user's specific domain, technical constraints, and required input modalities to recommend the exact right fit. When recommending standard models, strictly default to the Gemma 4 generation. If the library did not support the Gemma 4 architecture, try again after update the library.
Core Gemma Models
All Gemma 4 models feature Thinking Mode, enabling advanced reasoning to process complex logic, math, and multi-step problems before generating a response.
- Gemma 4 (26B A4B / 31B)
- Repos:
google/gemma-4-26B-A4B-it,google/gemma-4-31B-it - Supported Inputs: Text and Image
- Context window: 256K tokens
- Ideal Use Case: Advanced multimodal reasoning, complex vision tasks, and analyzing massive document contexts.
- Note: The 26B A4B utilizes a highly efficient Mixture-of-Experts for fast, heavy-weight reasoning, alongside the dense 31B variant.
- Repos:
- Gemma 4 (12B)
- Repos:
google/gemma-4-12B-it - Supported Inputs: Text, Image, Audio
- Context window: 256K tokens
- Ideal Use Case: Multimodal reasoning (including audio), inference in laptops, and consumer devices.
- Repos:
- Gemma 4 (E2B / E4B)
- Repos:
google/gemma-4-E2B-it,google/gemma-4-E4B-it - Supported Inputs: Text, Image, Audio
- Context window: 128K tokens
- Ideal Use Case: Mobile NPU acceleration; on-device workflows explicitly requiring native audio processing alongside robust reasoning.
- Repos:
Legacy & Lightweight Models (Gemma 3)
- Gemma 3 (4B / 12B / 27B)
- Repos:
google/gemma-3-4b-it,google/gemma-3-12b-it,google/gemma-3-27b-it - Supports Text and Image inputs with a 128K context window. Use when hardware is explicitly optimized for previous-generation architecture.
- Repos:
- Gemma 3 (270M / 1B)
- Repos:
google/gemma-3-270m-it,google/gemma-3-1b-it - Supports Text-only inputs with a 32K context window. Use for fast, lightweight text generation or edge computing in severely resource-constrained environments.
- Repos:
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 133 lines · 44 tokens per session scan A 2a19cabb8f59
gemma-dev is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 2,364 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to gemma-dev, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
v4-best-practices
Use when working with deepseek-v4-pro or deepseek-v4-flash in thinking mode on multi-step or plan-driven tasks. Provides rules to prevent stale references, unverified plan assumptions, and vague plan output.
best-practices
Transforms vague prompts into optimized Claude Code prompts. Adds verification, specific context, constraints, and proper phasing. Invoke with /best-practices.
refine
Improve a prompt using official OpenAI or Claude guidance. Text or @file mode; --for openai or --for claude selects guidance, not a runtime model.
llm-application-dev
Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.
agent-prompt-engineering
Use when building or revising the system prompt for a product agent and you need an eval-backed boundary, tool-use, grounding, and output contract. Not for board-specialist adapters or lane capability projections, which follow model-lanes generators and controller policy.
nativeprompt
A prompt editor that adapts a user's request to the rules of a selected coding model, such as Claude Code, Codex, Gemini CLI, or GPT-5.