rbozydar/gemini-cli
plugins/python-backend/skills/gemini-cli/SKILL.md
This skill should be used when invoking the Gemini CLI for code review, plan review, or any prompt-based task. It provides correct invocation patterns emphasizing stdin piping and @ syntax over shell variable gymnastics.
tools
Updated Apr 20, 2026
$ install --global
skillsauthnpx skillsauth add rbozydar/rbw-claude-code gemini-cliInstall 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: Apr 20, 2026, 5:01 AM22.6s1 file scanned
SKILL.md
- name:
- gemini-cli
- description:
- This skill should be used when invoking the Gemini CLI for code review, plan review, or any prompt-based task. It provides correct invocation patterns emphasizing stdin piping and @ syntax over shell variable gymnastics.
Ensure clean, readable Gemini CLI invocations without shell gymnastics.
Core Principle
Always pipe content via stdin or use @ syntax. Never use heredocs or shell variable assignment.
# CORRECT - Clean stdin pipe
cat file.md | gemini --sandbox -o text "Review this for issues"
# CORRECT - @ syntax for file references
gemini --sandbox -o text "Review this code" @src/module.py
# WRONG - Shell gymnastics
CONTENT=$(cat file.md)
gemini --sandbox "Review: $CONTENT"
Command Structure
# Pipe content via stdin
<content-source> | gemini [options] "prompt"
# Reference files/folders directly
gemini [options] "prompt" @file.py @folder/
Required Options
| Option | Purpose |
|--------|---------|
| --sandbox or -s | Required -- prevents code modifications |
| -o text | Plain text output (required for parsing) |
| -m MODEL | Model selection |
Available Models
| Model | Use Case |
|-------|----------|
| gemini-3-pro-preview | Default, best quality |
| gemini-3-flash-preview | Faster, cheaper |
Common Patterns
File and Folder References with @
# Single file
gemini --sandbox -o text "Review this code" @src/module.py
# Multiple files
gemini --sandbox -o text "Check consistency" @src/models.py @src/views.py
# Entire folder
gemini --sandbox -o text "Review this module" @src/auth/
# Mix files and folders
gemini --sandbox -o text "Review the API" @src/api/ @tests/test_api.py
Git Diff Review
# Unstaged changes
git diff | gemini --sandbox -o text "Review this diff for bugs and security issues"
# Staged changes
git diff --cached | gemini --sandbox -o text "Review these staged changes"
# Branch vs main
git diff main...HEAD | gemini --sandbox -o text "Review all changes on this branch"
Focused Review with Prompt Detail
git diff | gemini --sandbox -o text "Review this diff focusing on:
1. SQL injection vulnerabilities
2. Missing error handling
3. Performance issues"
Anti-Patterns
Deprecated -p Flag
# WRONG - deprecated
gemini -p "prompt" --sandbox
# CORRECT - positional prompt
gemini --sandbox "prompt"
Variable Assignment
# WRONG
DIFF=$(git diff)
gemini --sandbox "$DIFF"
# CORRECT
git diff | gemini --sandbox -o text "Review"
Missing Sandbox
# WRONG - no sandbox
gemini "Review this code"
# CORRECT
gemini --sandbox "Review this code"
Integration with Agents
When invoking gemini from Claude Code agents:
- Always use stdin piping or
@syntax - Always include
--sandbox - Always include
-o textfor parseable output - Select model based on task: pro for quality, flash for speed
git diff --cached | gemini --sandbox -o text -m gemini-3-pro-preview \
"Review this diff for bugs, security vulnerabilities, and performance issues.
Provide specific file:line references."
Error Handling
The error "No input provided via stdin" indicates missing piped content. When using stdin mode, always pipe content before the gemini command. When referencing files directly, use @ syntax instead.
For large files, review specific sections or use the flash model:
head -500 large-file.py | gemini --sandbox -o text "Review this code section"
Quick Reference
| Task | Command |
|------|---------|
| Review plan | gemini --sandbox -o text "Review for issues" @plan.md |
| Review file | gemini --sandbox -o text "Check security" @file.py |
| Review folder | gemini --sandbox -o text "Review module" @src/auth/ |
| Review unstaged diff | git diff \| gemini --sandbox -o text "Review for bugs" |
| Review staged diff | git diff --cached \| gemini --sandbox -o text "Review" |
| Review branch | git diff main...HEAD \| gemini --sandbox -o text "Review" |
Related Skills
rbozydar/python-coding
development
VerifiedTrustedCommunity
This skill should be loaded when writing, reviewing, or refactoring Python code to apply strict coding standards directly in the current context without spawning a subagent. It provides comprehensive Python development standards covering SOLID principles, asyncio patterns, type hints, testing, and production-quality code.
SKILL.mdUpdated Apr 20, 2026
rbozydar/quickshell
development
VerifiedTrustedCommunity
Use this skill when writing, reviewing, or debugging Quickshell configurations (QML files for desktop shell UI on Wayland/Hyprland). Triggers on: QML files with Quickshell imports, shell.qml entry points, PanelWindow or FloatingWindow usage, Quickshell service integration (PipeWire, MPRIS, notifications, Hyprland IPC), Wayland layer-shell or session-lock code, custom bar/panel/widget/dock/OSD/lockscreen/launcher development, or any question about building a desktop shell with Quickshell on Hyprland.
SKILL.mdUpdated Apr 20, 2026
rbozydar/deep-research
development
VerifiedTrustedCommunity
This skill should be used when thorough, multi-perspective research with citations is needed. It performs comprehensive research using a diffusion research loop with domain specialization, supporting general web research and specialized domains (geopolitical with GDELT). Auto-detects domain from query or accepts an explicit --domain flag.
SKILL.mdUpdated Apr 20, 2026
rbozydar/data-context-extractor
testing
VerifiedTrustedCommunity
Generate or improve a company-specific data analysis skill by extracting tribal knowledge from analysts. BOOTSTRAP MODE - Triggers: "Create a data context skill", "Set up data analysis for our warehouse", "Help me create a skill for our database", "Generate a data skill for [company]" → Discovers schemas, asks key questions, generates initial skill with reference files ITERATION MODE - Triggers: "Add context about [domain]", "The skill needs more info about [topic]", "Update the data skill with [metrics/tables/terminology]", "Improve the [domain] reference" → Loads existing skill, asks targeted questions, appends/updates reference files Use when data analysts want Claude to understand their company's specific data warehouse, terminology, metrics definitions, and common query patterns.
SKILL.mdUpdated Apr 20, 2026