Gemini
Delegate heavy or specialized analysis to Google Gemini CLI from your primary coding agent with non-interactive prompts, sessions, and model choice.
Overview
Gemini is an agent skill most often used in Build (also Ship review and Operate triage) that documents Gemini CLI delegation patterns—non-interactive prompts, sessions, and model selection—for solo builders pairing multi
Install
npx skills add https://github.com/giuseppe-trisciuoglio/developer-kit --skill geminiWhat is this skill?
- Documents non-interactive `gemini -p` delegation as the recommended agent handoff pattern
- Covers session resume via `gemini -r latest` and continuing analysis with follow-up prompts
- Maps Gemini 3 Flash (speed, JSON, triage) vs Gemini 3 Pro (deeper reasoning) with example commands
- Includes `--approval-mode plan`, `--output-format json`, and security-scan style prompt templates
- Quick reference for interactive vs scripted Gemini CLI usage in automation pipelines
Adoption & trust: 875 installs on skills.sh; 271 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You want a second LLM to analyze or generate output from the terminal without ad-hoc flags, wrong models, or losing context between agent turns.
Who is it for?
Indie builders who shell out to Gemini CLI from Claude Code or Cursor for large-repo scans, JSON automation, or fast prototyping alongside their main agent.
Skip if: Teams that only use in-chat models with no Gemini CLI installed, or workflows that require a packaged MCP server instead of subprocess delegation.
When should I use this skill?
You need to call Gemini CLI from an agent workflow with documented flags for prompts, sessions, models, JSON output, or plan approval.
What do I get? / Deliverables
You run repeatable `gemini -p` and `-r` invocations with the right Flash or Pro model and output format, then fold results back into your primary agent’s next step.
- Correct Gemini CLI invocation patterns for the agent’s subprocess
- Session-resume commands for continued analysis
- Model-specific prompt examples (scan, JSON list, boilerplate)
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is build/agent-tooling because the skill documents how to wire Gemini CLI into agent workflows rather than ship or grow the product itself. Agent-tooling fits CLI delegation, `-p` prompts, session resume, and Flash vs Pro model flags used while building with AI assistants.
Where it fits
Script `gemini -p` with Flash and JSON output so your main agent ingests refactoring candidates automatically.
Run a focused auth-module continuation after `gemini -r latest` without re-uploading the whole repository context.
Kick a plan-mode security scan on the codebase before merge when you want speed over deepest reasoning.
How it compares
CLI delegation reference for Gemini subprocesses—not an in-IDE skill package or MCP bridge on its own.
Common Questions / FAQ
Who is gemini for?
Solo and indie builders who use Google’s Gemini CLI as a delegated worker from another coding agent and need a consistent prompt and session cheat sheet.
When should I use gemini?
During Build when wiring agent-tooling, during Ship when you want a fast security pass on a big tree, or during Operate when resuming a long analysis session with `-r latest` and a focused follow-up prompt.
Is gemini safe to install?
Treat it as documentation for commands that can read your repo and call Google’s APIs; review the Security Audits panel on this Prism page and restrict approval modes before running on production secrets.
SKILL.md
READMESKILL.md - Gemini
# Gemini CLI Command Reference Quick reference for the `gemini` skill delegation workflow. ## Core Usage ```bash # Interactive mode gemini # Non-interactive single prompt (recommended for delegation) gemini -p "<english-prompt>" ``` ## Prompting and Sessions ```bash # Non-interactive prompt gemini -p "Analyze this repository architecture" # Resume session by alias/id gemini -r latest gemini -r <session-id> # Resume and continue with a prompt gemini -r latest -p "Continue analysis and focus on auth module" ``` ## Model Selection Choose the right model based on task requirements. Gemini 3 Flash and Pro are designed for complementary use cases: ### Gemini 3 Flash — Speed-Focused Tasks ```bash # Fast security scan on a large codebase (speed + cost-effective) # Best for: quick triage, iterative analysis, budget-sensitive tasks gemini -p "Analyze this repository for security vulnerabilities. Report only high-confidence issues with file paths, severity, and patch recommendations." -m gemini-3-flash --approval-mode plan # Structured JSON output for automation pipelines (fast + predictable) # Best for: data extraction, automated tooling, script integration gemini -p "Return a JSON list of top 10 refactoring opportunities with fields: title, file, impact, effort." -m gemini-3-flash --output-format json # Quick boilerplate generation (fast iteration) # Best for: prototyping, scaffolding, rapid feedback gemini -p "Generate a minimal Express.js REST endpoint for POST /items with input validation and a unit test. Keep the implementation concise and ready to paste." -m gemini-3-flash # Cost-effective CSV/file analysis (low-cost summary) # Best for: data triage, initial exploration, lightweight analysis gemini -p "Summarize this CSV file's key statistics: row count, missing-value counts, and top 5 columns by variance. Provide a 6-line bullet summary suitable for quick triage." -m gemini-3-flash --output-format json --approval-mode plan # Fast microcopy prototyping (quick iterations) # Best for: UX copy, onboarding text, A/B test variants gemini -p "Provide 3 short alternative microcopy options (<=20 words each) for an onboarding tooltip that explains account recovery. Include a one-line A/B test metric proposal for each option." -m gemini-3-flash ``` ### Gemini 3 Pro — Power-Focused Tasks ```bash # Architectural design analysis (complex reasoning + quality) # Best for: system design, migration planning, high-stakes decisions gemini -p "Analyze the current system architecture and propose a detailed migration strategy to a microservices architecture. Include component boundaries, communication patterns, data ownership, and estimated risks for each migration step." -m gemini-3-pro --approval-mode plan # Comprehensive security audit (deep analysis + thoroughness) # Best for: critical systems, compliance reviews, detailed assessments gemini -p "Perform a thorough security audit of the authentication and authorization layer. Identify potential vulnerabilities, rate-limiting gaps, token handling weaknesses, and injection vectors. Provide severity ratings and specific remediation steps for each finding." -m gemini-3-pro --approval-mode plan # Production-quality code generation (quality + robustness) # Best for: production systems, critical modules, high-reliability code gemini -p "Generate a production-ready TypeScript module for paginated API responses. Include input validation, error handling, retry logic with exponential backoff, and comprehensive unit tests with mocks. Follow best practices for error types, logging, and type safety." -m gemini-3-pro --approval-mode auto_edit # Large-context refactor analysis (broad context + reasoning) # Best for: monorepos, cross-module refactors, legacy system analysis gemini -p "Propose a phased refactor plan for this monorepo. Include impacted modules, migration risks, and rollback procedures for each phase." -m gemini-3-pro --output-format json ``` ### Performance and Cost Tradeoffs |