google-gemma/gemma-skills

google-gemma-Profil

Letzte erfasste Quellaktivität: 18. Oktober 2026 um 03:18

SkillsMP-Katalog aktualisiert: 26. Oktober 2026 um 11:37

gesammelte Skills: 2

GitHub-Stars: 1.031
GitHub-Forks: 85

README des Repositorys

README-Quelldatei: README.md

README-Quelldatei lesen

Vollständige README anzeigen

# gemma-skills Skills for the Gemma and model/agent interactions ## Skills in this repo | Skill | Description | | :--- | :--- | | [`gemma-dev`](skills/gemma-dev) | Skill for building application with Gemma or for general knowledge inquiries related to Gemma models | | [`gemma-trainer`](skills/gemma-trainer) | Skill for training, fine-tuning, or adapt Gemma models (e.g. SFT, DPO. RLHF, Reward Modeling) on local hardware | ## Installation You can install these skills across your preferred AI coding assistants and package managers: ### Using [Vercel skills CLI](https://skills.sh) ```sh # Interactively browse and install skills. npx skills add google-gemma/gemma-skills --list # Install a specific skill (e.g., gemma-dev). npx skills add google-gemma/gemma-skills --skill gemma-dev ``` ### Antigravity Install through the AGY CLI: ```sh # Install it directly agy plugin install https://github.com/google-gemma/gemma-skills ``` ## Disclaimer This is not an officially supported Google product. This project is not eligible for the [Google Open Source Software Vulnerability Rewards Program](https://bughunters.google.com/open-source-security).

README des Repositorys wird geladen…

Skills in diesem Repository

Softwareentwickler

1 Berufskategorien · 50% klassifiziert

Skill

Beruf

Beschreibung

Aktualisiert

gemma-dev

nicht klassifiziert

Trigger this skill when building applications with Gemma or for general knowledge inquiries related to Gemma models (e.g. prompt structure, capabilities). Covers model selection, development workflows, and deployment best practices.

Quellsprache: Englisch

2026-10-18

gemma-trainer

Softwareentwickler

Trigger this skill when the user wants to train, fine-tune, or adapt Gemma models (e.g. SFT, DPO, RLHF, Reward Modeling) on local hardware. Covers TRL, Unsloth, dataset preparation, validation, and GGUF/LiteRT conversion.

Quellsprache: Englisch

2026-07-31

Es werden 2 von 2 gesammelten Skills angezeigt.

Mit einem KI-Assistenten installieren

Diesen Prompt kopieren und in den verwendeten KI-Assistenten einfügen.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/google-gemma/gemma-skills.