beam-ai-team/google-gemini-image
skills/integrations/google/google-gemini-image/SKILL.md
Generate, edit, and refine images with Google Gemini. Load when user says 'generate image', 'edit image', 'refine image', 'text to image', 'gemini image', 'modify image'.
development
Updated Jul 8, 2026
$ install --global
skillsauthnpx skillsauth add beam-ai-team/beam-next-skills google-gemini-imageInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jul 8, 2026, 3:50 AM139.7s3 files scanned
SKILL.md
- name:
- google-gemini-image
- type:
- skill
- version:
- 2.1
- description:
- Generate, edit, and refine images with Google Gemini. Load when user says
- category:
- integrations
- platform:
- Google Gemini
- updated:
- 2026-03-23
- visibility:
- public
- - approval:
- image_generation
Google Gemini Image
Unified skill for text-to-image generation, image editing, and iterative refinement.
Safety Contract
Before generating, editing, refining, or saving images, show the prompt or edit summary, source image path when used, model, aspect/size settings, output path, and whether user-provided/private imagery is included. Require explicit user approval in the current turn before sending images to Gemini or writing output files. Discussing prompt options does not require approval.
Replaces: gemini-generate-image, gemini-edit-image, gemini-refine-image.
Usage
# Generate from text prompt
uv run python scripts/gemini_image.py generate "a cat in space"
uv run python scripts/gemini_image.py generate "sunset over mountains" --aspect 16:9 --size 2K
uv run python scripts/gemini_image.py generate "abstract art" --output my_art.png
# Edit an existing image
uv run python scripts/gemini_image.py edit photo.png "make the sky blue"
uv run python scripts/gemini_image.py edit scene.jpg "add clouds" --aspect 4:3 --size 1K --output result.png
# Refine the last generated/edited image
uv run python scripts/gemini_image.py refine "add more stars"
uv run python scripts/gemini_image.py refine "make it brighter" --image specific.png
Model
All actions use gemini-3.1-flash-image-preview (Nano Banana 2). Inputs are text-only, or image + text for edit/refine.
Legacy gemini-2.0-flash-exp* models are deprecated; Google scheduled shutdown June 1, 2026 — this skill targets 3.1 only.
Aspect ratio and size
--aspect:1:1,1:4,1:8,2:3,3:2,3:4,4:1,4:3,4:5,5:4,8:1,9:16,16:9,21:9(default1:1).--size:512,1K,2K,4K(default1K). Passed to the API asimage_config.image_size.
Requirements
GEMINI_API_KEYin.env(get from https://aistudio.google.com/app/apikey)pip install google-genai Pillow
Output
Images save as PNG to 04-workspace/generated-images/ (or --output path).
Filenames auto-generated with timestamp: generated_20260323_143000.png, edited_..., refined_....
Shared path helpers live in scripts/gemini_client.py.
Related Skills
beam-ai-team/use-case-proposal
tools
VerifiedTrustedCommunity
Build a Palantir-shape, PDF-native use-case proposal document for a sophisticated enterprise account: research-grounded use cases (each with description, challenge, impact, value), an operating-graph ontology page, a recommended PoC with a week-by-week plan, and a closing page that asks for one decision. Load when a client asks us to 'propose high-impact use cases', requests a use-case presentation/catalog for a function (finance, HR, ops), or when a technical evaluation team will review candidates to pick a PoC. NOT for single-account cold outreach (use prospect-brief), full process diagnostics (use operating-diagnostic), or priced proposals (use proposal-creation).
SKILL.mdUpdated Jul 8, 2026
beam-ai-team/beam-figma-to-html-slides
development
VerifiedTrustedCommunity
Convert Beam Figma slide designs into high-fidelity, editable HTML presentation decks. Use when Codex is asked to audit Figma slides, extract slide templates, rebuild Beam slides as HTML decks, decide whether Figma imagery should be exported or rebuilt in HTML/CSS, create Beam/Prism-compatible deck templates, or improve fidelity of existing Beam HTML slide rebuilds.
SKILL.mdUpdated Jul 8, 2026
beam-ai-team/beam-ai-slide-library
development
VerifiedTrustedCommunity
Use the Beam AI reusable slide library: individual HTML slide templates extracted from Beam Figma rebuilds, kept separate from deck themes and full deck templates. Load when the user asks for a slide library, specific Beam slide patterns, reusable Figma-inspired slides, Prism slide-library items, or slide-level HTML templates.
SKILL.mdUpdated Jul 8, 2026
beam-ai-team/beam-ai-deck-templates
development
VerifiedTrustedCommunity
Use Beam AI deck and report design packs, HTML templates, and curated examples to create sales decks, customer intro decks, RPO decks, and DIN A4 use-case proposal reports. Load when the user asks for Beam-branded presentation templates, Prism-compatible deck templates, Beam report templates, customer intro decks, commercial proposals, or reusable HTML deck/report examples.
SKILL.mdUpdated Jul 8, 2026