npx skills add https://github.com/openclaw/skills
sundial-org/awesome-openclaw-skills
nano-banana-antigravity
Generate or edit images via Nano Banana Pro using Antigravity OAuth (no API key needed!)
Installation
npx skills add sundial-org/awesome-openclaw-skills --skill nano-banana-antigravity
Similar popular skills
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
Use when asked to ship a SaaS MVP, audit application security, build an AI agent, run browser Q…
901 installsCore UI/UX engineering skill for building highly interactive, spatial, weightless, and glassmor…
11 installsDesign, implement, and debug autonomous AI agents and multi-agent systems using the Google Anti…
297 installsA meta-skill that understands task requirements, dynamically selects appropriate skills, tracks…
290 installsAntiGravity 懶人包 — 服務連接與工作流程設定。說「AntiGravity 懶人包」「安裝 Antigravity 設定」…
170 installs在 AntiGravity 連接 NotebookLM MCP。說「連接 NotebookLM」「設定 NotebookLM」時載入。
141 installsAlso in this package
Other skills from sundial-org/awesome-openclaw-skills · top by installs.
npx skills add sundial-org/awesome-openclaw-skills
More details
Agent compatibility
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Also listed on
Alternate registries and mirrors of this skill.
Repository health
main
Skill metadata
Parsed from SKILL.md frontmatter.
Package contents
Files included with this skill beyond the listing page.
-
skill md
SKILL.md2,238 B -
docs
SUMMARY.md119 B
History
- First seen on skills.sh
- First recorded snapshot · 3 installs
SKILL.md
Nano Banana Antigravity (Gemini 3 Pro Image via OAuth)
Generate images using Nano Banana Pro (Gemini 3 Pro Image) via your existing Google Antigravity OAuth credentials.
No separate API key needed! Uses the same OAuth tokens as your OpenClaw Antigravity provider.
Generate Image
uv run {baseDir}/scripts/generate_image.py --prompt "your image description" --filename "output.png"
Generate with Options
uv run {baseDir}/scripts/generate_image.py \
--prompt "a sunset over mountains" \
--filename "sunset.png" \
--aspect-ratio 16:9 \
--resolution 2K
Edit/Composite Images
uv run {baseDir}/scripts/generate_image.py \
--prompt "add sunglasses to this person" \
--filename "edited.png" \
-i original.png
Multi-image Composition
uv run {baseDir}/scripts/generate_image.py \
--prompt "combine these into one scene" \
--filename "composite.png" \
-i image1.png -i image2.png -i image3.png
Options
--prompt, -p(required): Image description or edit instructions--filename, -f(required): Output filename--input-image, -i: Input image(s) for editing (can be repeated)--aspect-ratio, -a: 1:1 (default), 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9--resolution, -r: 1K (default), 2K, 4K
Authentication
Uses existing OpenClaw Antigravity OAuth credentials. Make sure you're authenticated:
openclaw models auth login --provider google-antigravity
The script looks for credentials in:
~/.openclaw/credentials/google-antigravity.json~/.config/openclaw/credentials/google-antigravity.json~/.config/opencode/antigravity-accounts.json
Notes
- The script prints a
MEDIA:line for OpenClaw to auto-attach on supported chat providers. - Do not read the image back; report the saved path only.
- Uses timestamps in filenames for uniqueness:
yyyy-mm-dd-hh-mm-ss-name.png - Falls back to regular Nano Banana if Nano Banana Pro isn't available yet.