New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Antigravity Gemini Image

by uluckyXH in uluckyXH/OpenMOSS

Generate or edit images using the Antigravity-hosted Gemini image model via the local gateway.

MITAuto-check: notesMedia & Creative

Install Antigravity Gemini Image

skills CLI
$ npx skills add uluckyXH/OpenMOSS --skill antigravity-gemini-image -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install uluckyXH/OpenMOSS antigravity-gemini-image --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/uluckyXH/OpenMOSS.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/antigravity-gemini-image .claude/skills/antigravity-gemini-image && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
antigravity-gemini-image
GitHub stars
1.3k
Token cost
~730 tokens
SKILL.md length
200 words
Files
4 (incl. scripts, references)
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Generate or edit images using the Antigravity-hosted Gemini image model via the local gateway.

  • Works in 3 steps: Confirm the prompt (and optional input… → Run the script in… → Return the generated image file to the…
  • The user asks to create an image
  • SKILL.md covers Overview, Quick start, Workflow (always follow) and Parameters, plus 2 more sections
  • Runs Python scripts from its folder; calls python3; needs LOCAL_160_API_KEY

What it does

Antigravity Gemini Image is an agent skill from uluckyXH/OpenMOSS. Generate or edit images using the Antigravity-hosted Gemini image model via the local gateway. Use when the user asks to create an image, generate an avatar, or edit/transform an existing image with text instructions. Supports text-to-image and image-to-image editing.

Its SKILL.md is about 730 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including scripts and reference files (for example `REFERENCES.md`, `references/API.md` and `scripts/generate_gemini_image.py`).

It sits in Media & Creative, covering Image editing and Image generation. It works with Google Gemini. The repository describes itself as: A self-organizing multi-agent collaboration platform for OpenClaw. Multiple AI agents work as an autonomous team — planning, executing, reviewing, and patrolling tasks with zero… The licence is MIT.

When your agent uses it

  • The user asks to create an image
  • Generate an avatar
  • Edit/transform an existing image with text instructions

Example prompts

  • “/antigravity-gemini-image”

Requirements

  • Python 3
  • A credential in LOCAL_160_API_KEY

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Confirm the prompt (and optional input image) with the user.
  2. Run the script in scripts/generate_gemini_image.py.
  3. Return the generated image file to the user.

What it can do on your machine

Read from SKILL.md and the folder at commit 98f76b8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • LOCAL_160_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Antigravity Gemini Image loads about 730 tokens when it runs, and up to ~877 if it reads all its reference files. Until then it costs about 73 tokens; SKILL.md has 200 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~730
With references · SKILL.md plus every file in references/, read only if the agent opens them
~877

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:30
    Optional (explicit .env path):
  • NoteMentions a .env fileSKILL.md:34
    --env-file ~/.openclaw/workspace/.env \
  • NoteMentions a .env fileSKILL.md:50
    --env-file` (optional): load a specific `.env` file.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from uluckyXH/OpenMOSS at commit 98f76b8, republished under its MIT licence (© uluckyXH). 200 words, ~730 tokens.

Download SKILL.mdSave it as .claude/skills/antigravity-gemini-image/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
antigravity-gemini-image
description
Generate or edit images using the Antigravity-hosted Gemini image model via the local gateway. Use when the user asks to create an image, generate an avatar, or edit/transform an existing image with text instructions. Supports text-to-image and image-to-image editing.

Antigravity Gemini Image

Overview

Use the Gemini REST endpoint (via the local gateway base URL) to create or edit images. This skill wraps the correct request format for the gemini-3.1-flash-image model, which does not work reliably with /v1/responses + image_generation.

Quick start

Text → Image
bash
mkdir -p ~/.openclaw/workspace/tmp
/usr/bin/python3 {baseDir}/scripts/generate_gemini_image.py \
  --prompt "A cute yellow chick mascot, vector style" \
  --out ~/.openclaw/workspace/tmp/chick.jpg
Image → Image (edit)
bash
mkdir -p ~/.openclaw/workspace/tmp
/usr/bin/python3 {baseDir}/scripts/generate_gemini_image.py \
  --prompt "Add a tiny red scarf, keep the style" \
  --image /path/to/input.jpg \
  --out ~/.openclaw/workspace/tmp/chick_edit.jpg

Optional (explicit .env path):

bash
/usr/bin/python3 {baseDir}/scripts/generate_gemini_image.py \
  --env-file ~/.openclaw/workspace/.env \
  --prompt "A cute yellow chick mascot, vector style" \
  --out ~/.openclaw/workspace/tmp/chick.jpg

macOS Keychain (optional): service openclaw-local-160, accounts base-url and api-key.

Workflow (always follow)

  1. Confirm the prompt (and optional input image) with the user.
  2. Run the script in scripts/generate_gemini_image.py.
  3. Return the generated image file to the user.

Parameters

  • --prompt (required): text instruction.
  • --image (optional): input image for edits.
  • --out (required): output path (jpg/png).
  • --env-file (optional): load a specific .env file.
  • --base-url (optional): defaults to LOCAL_160_BASE_URL.
  • --api-key (optional): defaults to LOCAL_160_API_KEY.
  • --model (optional): defaults to gemini-3.1-flash-image.
  • --temperature (optional): default 0.3.
  • --size (optional): default 4K (set via GEMINI_IMAGE_SIZE).
  • --ratio (optional): default 16:9 (set via GEMINI_IMAGE_RATIO).
  • --timeout (optional): HTTP 超时（秒），默认 1200（也可用 GEMINI_IMAGE_TIMEOUT 或 LOCAL_160_TIMEOUT）。

Notes

  • The gateway endpoint is: POST {BASE_URL}/v1beta/models/gemini-3.1-flash-image:generateContent
  • Auth header uses x-goog-api-key.
  • Image generation can be slow; 10–20 minutes is possible. Keep timeouts high (default 1200s or override via --timeout / env).
  • Output image is returned as base64 under: candidates[0].content.parts[*].inlineData.data.
  • 4K 输出必须写在 generationConfig.imageConfig（不要直接写 image_size）：
    json
    {"imageConfig": {"imageSize": "4K", "aspectRatio": "16:9"}}

References

  • See references/API.md for request/response shape.

© uluckyXH, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts, references) in skills/antigravity-gemini-image of uluckyXH/OpenMOSS.

  • SKILL.md
  • REFERENCES.md
  • references/API.md
  • scripts/generate_gemini_image.py

Open the folder on GitHubat commit 98f76b8

Compare with similar skills

Antigravity Gemini Image next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Antigravity Gemini Image compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Antigravity Gemini Image this skilluluckyXH/OpenMOSS1.3k—~730Automated safety check: NotesMIT
AI Image Generation and Editingzhayujie/CowAgent47k—~1.3kAutomated safety check: PassMIT
BlockRun Image GenerationBlockRunAI/ClawRouter6.6k—~2.1kAutomated safety check: PassMIT
FigureMuuuun/luxas1.2k—~1.2kAutomated safety check: PassMIT
Gemini Image Generatordair-ai/dair-academy-plugins6142 repos~3.5kAutomated safety check: NotesMIT
NanobananaReScienceLab/opc-skills1.8k—~1.3kAutomated safety check: PassApache-2.0

Similar skills

  • AI Image Generation and Editing

    zhayujie/CowAgent

    Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.

    47k GitHub stars~1.3k tokensUpdated yesterday
    Media & CreativeAuto-check passed

  • BlockRun Image Generation

    BlockRunAI/ClawRouter

    Generates or edits images through ClawRouter's local image API, with a choice of models and sizes and payment handled automatically through x402.

    6.6k GitHub stars~2.1k tokensUpdated 5 days ago
    Media & CreativeAuto-check passed

  • Figure

    Muuuun/luxas

    Hybrid figure pipeline (Nano Banana raster + rembg background removal + TikZ vector assembly).

    1.2k GitHub stars~1.2k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed

  • Gemini Image Generator

    dair-ai/dair-academy-plugins

    Generates and edits images with Google's Gemini Nano Banana Pro model through the Gemini API, including photo edits and multi-image composition.

    614 GitHub starsUsed in 2 repos~3.5k tokens
    Media & CreativeAuto-check: notes

  • Nanobanana

    ReScienceLab/opc-skills

    Generate and edit images using Google Gemini 3 Pro Image (Nano Banana Pro).

    1.8k GitHub stars~1.3k tokensUpdated yesterday
    Media & CreativeAuto-check passed

  • Nano Banana Image Generator

    LichAmnesia/lich-skills

    Generates or edits PNG images with Google's Nano Banana 2 model through a small script, with a choice of 512, 1K, 2K or 4K output.

    234 GitHub stars~1.1k tokensUpdated 4 mo ago
    Media & CreativeAuto-check: notes

More from uluckyXH/OpenMOSS

  • Local Web Search

    uluckyXH/OpenMOSS

    A skill your agent uses when the user asks for web search that should run via the local-160 Responses API with websearch tool (base URL like https://proxy.example.com, model gpt-5.2-codex(xhigh)).

    1.3k GitHub stars~392 tokensUpdated 3 mo ago
    Auto-check: notes

  • Wordpress Skill

    uluckyXH/OpenMOSS

    WordPress 站点管理 Skill — 通过 CLI 工具管理文章、页面、媒体、分类、标签和搜索. An agent skill from uluckyXH/OpenMOSS.

    1.3k GitHub stars~1.4k tokensUpdated 3 mo ago
    Auto-check passed

  • Task Executor Skill

    uluckyXH/OpenMOSS

    任务执行者 Skill — 通过 CLI 工具领取子任务、提交成果、处理返工

    1.3k GitHub stars~615 tokensUpdated 3 mo ago
    Auto-check passed

  • Task Patrol Skill

    uluckyXH/OpenMOSS

    巡查 Skill — 通过 CLI 工具巡查任务状态、标记异常、发送告警

    1.3k GitHub stars~514 tokensUpdated 3 mo ago
    Auto-check passed

  • Task Planner Skill

    uluckyXH/OpenMOSS

    任务规划师 Skill — 通过 CLI 工具创建任务、拆分模块、分配子任务

    1.3k GitHub stars~683 tokensUpdated 3 mo ago
    Auto-check passed

  • Task Reviewer Skill

    uluckyXH/OpenMOSS

    审查者 Skill — 通过 CLI 工具审查子任务、评分、驳回返工

    1.3k GitHub stars~558 tokensUpdated 3 mo ago
    Auto-check passed

Works with

Categories

Questions about Antigravity Gemini Image

What does Antigravity Gemini Image do?

Generate or edit images using the Antigravity-hosted Gemini image model via the local gateway. Antigravity Gemini Image is an agent skill from uluckyXH/OpenMOSS. Generate or edit images using the Antigravity-hosted Gemini image model via the local gateway.

When should I use Antigravity Gemini Image?

Antigravity Gemini Image fits situations like: the user asks to create an image; generate an avatar; edit/transform an existing image with text instructions.

How do I install Antigravity Gemini Image in Claude Code?

Run `npx skills add uluckyXH/OpenMOSS --skill antigravity-gemini-image -a claude-code`. Or copy the skill folder (skills/antigravity-gemini-image in uluckyXH/OpenMOSS) into .claude/skills/antigravity-gemini-image in your project. Claude Code loads it when a task matches its description.

How do I install Antigravity Gemini Image in Codex?

Run `npx skills add uluckyXH/OpenMOSS --skill antigravity-gemini-image -a codex`. Or copy the skill folder (skills/antigravity-gemini-image in uluckyXH/OpenMOSS) into .agents/skills/antigravity-gemini-image in your project. Codex loads it when a task matches its description.

Can I use Antigravity Gemini Image in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add uluckyXH/OpenMOSS --skill antigravity-gemini-image -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/antigravity-gemini-image, .gemini/skills/antigravity-gemini-image, .github/skills/antigravity-gemini-image and .opencode/skills/antigravity-gemini-image in your project.

What does Antigravity Gemini Image need to run?

Going by SKILL.md and its folder, Antigravity Gemini Image needs Python for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named LOCAL_160_API_KEY. Our summary lists: Python 3; A credential in LOCAL_160_API_KEY.

Does Antigravity Gemini Image access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Antigravity Gemini Image safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Antigravity Gemini Image use?

Antigravity Gemini Image is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Antigravity Gemini Image use?

About 730 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 147 tokens, read only when the agent opens those files.

What are the alternatives to Antigravity Gemini Image?

Skills that share tags, products or a category with Antigravity Gemini Image: AI Image Generation and Editing (zhayujie/CowAgent, 47k stars), BlockRun Image Generation (BlockRunAI/ClawRouter, 6.6k stars), Figure (Muuuun/luxas, 1.2k stars) and Gemini Image Generator (dair-ai/dair-academy-plugins, 614 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Antigravity Gemini Image?

uluckyXH (a GitHub user) maintains it in uluckyXH/OpenMOSS, which has 1,335 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on June 22, 2026.

Source: uluckyXH/OpenMOSS on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.