gemini-cli

Included with Lifetime

$97 forever

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.

AI Agents

What this skill does


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.

```bash
# 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

```bash
# 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 @

```bash
# 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

```bash
# 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

```bash
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

```bash
# WRONG - deprecated
gemini -p "prompt" --sandbox

# CORRECT - positional prompt
gemini --sandbox "prompt"
```

### Variable Assignment

```bash
# WRONG
DIFF=$(git diff)
gemini --sandbox "$DIFF"

# CORRECT
git diff | gemini --sandbox -o text "Review"
```

### Missing Sandbox

```bash
# WRONG - no sandbox
gemini "Review this code"

# CORRECT
gemini --sandbox "Review this code"
```

## Integration with Agents

When invoking gemini from Claude Code agents:

1. Always use stdin piping or `@` syntax
2. Always include `--sandbox`
3. Always include `-o text` for parseable output
4. Select model based on task: pro for quality, flash for speed

```bash
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:

```bash
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"` |

Files: 1

Size: 4.0 KB

Complexity: 8/100

Category: AI Agents

Source: https://github.com/rbozydar/rbw-claude-code/tree/main/plugins/python-backend/skills/gemini-cli

Related in AI Agents

skill-development

Included

Comprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.

AI Agentsscripts

reprompter

Included

Transform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.

AI Agentsscripts

adaptive-compaction

Included

Adaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.

AI Agentsscripts

agent-skill-creator

Included

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.

AI Agentsscripts

llm-wiki

Included

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.

AI Agentsscripts

skill-master

Included

Agent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.

AI Agentsscripts