Gemini CLI

What it does

When your agent uses it

• Tasks that involve Security review
• Tasks that involve Code review
• Tasks that involve Codebase onboarding

Example prompts

• “/gemini-cli”

Requirements

• A Bash shell

Workflow steps

12 steps, taken from the step headings in SKILL.md.

1. 1Install Gemini CLI
2. 2Authenticate
3. 3Verify Installation
4. 4Security Audit
5. 5Architecture Decision
6. 6Debugging Root Cause
7. 7Always Use -p for Automation
8. 8Select Model Based on Criticality
9. 9Provide Context in Prompts
10. 10Pipe File Content for Reviews
11. 11Synthesize, Don't Just Forward
12. 12Handle Errors Gracefully

What it can do on your machine

Read from SKILL.md and the folder at commit 8837836. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 3 files in scripts/ (Shell), which the agent can run.

  Shell commands in SKILL.md call:

  • gemini
  • bun
  • claude

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gemini CLI loads about 2.8k tokens when it runs, and up to ~7.8k if it reads all its reference files. Until then it costs about 46 tokens; SKILL.md has 721 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~46

When it runs · the whole SKILL.md, loaded when a task matches

~2.8k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~7.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from secondsky/claude-skills at commit 8837836, republished under its MIT licence (© secondsky). 721 words, ~2,820 tokens.

name

gemini-cli

description

Google Gemini CLI for second opinions, architectural advice, code reviews, security audits. Leverage 1M+ context for comprehensive codebase analysis via command-line tool.

license

MIT

metadata.version

2.1.0

metadata.production_tested

true

metadata.gemini_cli_version

0.13.0+

metadata.last_verified

2025-11-13

metadata.token_savings

~60-70%

metadata.errors_prevented

6+

metadata.keywords

gemini-cli, google gemini, gemini command line, second opinion, model comparison, gemini-2.5-flash, gemini-2.5-pro, architectural decisions, debugging…

# Quick question (non-interactive with -p flag)
gemini -p "Should I use D1 or KV for session storage?"

# Code review with file context
cat src/auth.ts | gemini -p "Review this authentication code for security vulnerabilities"

# Architecture advice using Pro model
gemini -m gemini-2.5-pro -p "Best way to handle WebSockets in Cloudflare Workers?"

# With all files in directory
gemini --all-files -p "Review this auth implementation for security issues"

# Interactive mode for follow-up questions
gemini -i "Help me debug this authentication error"

bun add -g @google/gemini-cli

gemini

gemini --version  # Should show 0.13.0+
gemini -p "What is 2+2?"  # Test connection

gemini -m gemini-2.5-flash -p "Review this function for performance issues"

gemini -m gemini-2.5-pro -p "Security audit this authentication system"

Quick question? → Flash
Security/architecture? → Pro
Debugging? → Flash (try Pro if stuck)
Refactoring 5+ files? → Pro

# Audit authentication code
cat src/middleware/auth.ts | gemini -m gemini-2.5-pro -p "
Security audit this authentication middleware. Check for:
1. Token validation vulnerabilities
2. Timing attack risks
3. Error handling leaks
4. CSRF protection
5. Rate limiting
"

# Compare technologies with context
gemini -m gemini-2.5-pro -p "
Context: Building Cloudflare Worker with user authentication.

Question: Should I use D1 or KV for storing session data?

Considerations:
1. Session reads on every request
2. TTL-based expiration
3. Cost under 10M requests/month
4. Deployment complexity
"

# Analyze error logs with context
tail -100 error.log | gemini -p "
These errors started after deploying auth changes. What's the likely root cause?

Context:
- Added JWT validation middleware
- Using @cloudflare/workers-jwt
- Errors only on /api/* routes
"

User: "Should I use D1 or KV for storing user sessions?"

Claude (internal): This is an architectural decision. Consult Gemini for second opinion.

[Runs: gemini -m gemini-2.5-pro -p "Compare D1 vs KV for user session storage in Cloudflare Workers. Consider: read/write patterns, cost, performance, complexity."]

Claude (to user): "I've consulted Gemini for a second opinion. Here's what we both think:

My perspective: [Claude's analysis]
Gemini's perspective: [Gemini's analysis]

Key differences: [synthesis]
Recommendation: [combined recommendation]"

gemini  # Follow authentication prompts

gemini -m gemini-2.5-flash -p "Your question"
gemini -m gemini-2.5-pro -p "Your question"

# ✅ Correct
gemini -p "Question"

# ❌ Wrong (will hang waiting for input)
gemini "Question"

# ✅ Good for scripts
gemini -p "Question"

# ❌ Bad (interactive)
gemini

# Architecture/security → Pro
gemini -m gemini-2.5-pro -p "[critical question]"

# Debugging/review → Flash
gemini -m gemini-2.5-flash -p "[general question]"

# ✅ Good: Context + Question + Considerations
gemini -p "Context: Building Cloudflare Worker. Question: Best auth pattern? Considerations: 1) Stateless, 2) JWT, 3) <100ms overhead"

# ❌ Bad: Vague
gemini -p "Best auth?"

# ✅ Efficient
cat src/auth.ts | gemini -p "Review for security"

# ❌ Less efficient
gemini -p "Review src/auth.ts"

Claude: [runs gemini] "Gemini says: [paste]"

Claude: "I've consulted Gemini for a second opinion:

My analysis: [Claude's perspective]
Gemini's analysis: [Gemini's perspective]
Key differences: [synthesis]
Recommendation: [unified answer]"

if output=$(gemini -p "Question" 2>&1); then
  echo "Gemini says: $output"
else
  echo "Gemini consultation failed, proceeding with Claude's recommendation"
fi

© secondsky, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (scripts, references) in plugins/gemini-cli/skills/gemini-cli of secondsky/claude-skills.

• SKILL.md
• references/gemini-experiments.md
• references/helper-functions.md
• references/models-guide.md
• references/prompting-strategies.md
• scripts/install-gemini-coach.sh
• scripts/setup-slash-command.sh
• scripts/test-connection.sh

Open the folder on GitHubat commit 8837836

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in secondsky/claude-skills, which our catalogue first saw on October 7, 2026.

• majiayu000/claude-skill-registryskills/ai-llm/gemini-cli-secondsky-claude-skills