A Claude Code slash command that invokes Gemini 3.1 Pro as a specialized agent for visual analysis, UI/UX tasks, and research.
SaferSkills independently audited claude-gemini-skill (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A Claude Code slash command that invokes Gemini 3.1 Pro as a specialized agent for visual analysis, UI/UX tasks, and research.
npm install -g @google/gemini-cliGEMINI_API_KEY environment variable setjq for JSON parsing: brew install jqpngpaste for clipboard image capture: brew install pngpastegit clone <repo-url>
cd claude-gemini-skill
./install.shRestart Claude Code after installing.
Inside Claude Code:
/gemini analyze the screenshot of my dashboard
/gemini convert this mockup to HTML/CSS
/gemini review the architecture of this project
/gemini suggest UI improvements for the login pageIf you mention a screenshot or clipboard image, it will be captured automatically and sent to Gemini.
./install.sh --uninstall| Source | Destination |
|---|---|
commands/gemini.md | ~/.claude/commands/gemini.md |
bin/gemini-clean | ~/.claude/bin/gemini-clean |
gemini-prompt.md | ~/.claude/gemini-prompt.md |
MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.