optimize-gemini-prompts

optimize-gemini-prompts is a skill for Claude Code, Codex from IchenDEV/prompt-optimizer-plugins. It costs 126 tokens per session (1,602 once invoked), scanned A, original, MIT.

A prompt-editing skill for clarifying and rewriting prompts intended for Google’s Gemini models.

In plain words
What is it for?
Use it to improve, debug, migrate, or design Gemini prompts and agent instructions using Google’s prompt-design guidance.
Why use it?
It helps make an underspecified prompt easier for Gemini to follow while preserving the requested outcome and constraints.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the prompt-optimizer plugin — 9 skills shipped together

Good fit Use it to improve, debug, migrate, or design Gemini prompts and agent instructions using Google’s prompt-design guidance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ichendev/prompt-optimizer-plugins/optimize-gemini-prompts
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add IchenDEV/prompt-optimizer-plugins --skill optimize-gemini-prompts
Clone the repo
git clone --depth 1 https://github.com/IchenDEV/prompt-optimizer-plugins

Made for: Claude Code, Codex.

Or install prompt-optimizer, the plugin that ships this one along with the rest of its 9 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for optimize-gemini-prompts

README.md
[![agentmods](https://agentmods.dev/badge/skills/ichendev/prompt-optimizer-plugins/optimize-gemini-prompts.svg)](https://agentmods.dev/skills/ichendev/prompt-optimizer-plugins/optimize-gemini-prompts)
Your own site
<a href="https://agentmods.dev/skills/ichendev/prompt-optimizer-plugins/optimize-gemini-prompts"><img src="https://agentmods.dev/badge/skills/ichendev/prompt-optimizer-plugins/optimize-gemini-prompts.svg" alt="Measured on agentmods" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,602 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00126 $0.01602
Opus 5 $0.00063 $0.00801
Sonnet 5 $0.00025 $0.00320
Haiku 4.5 $0.00013 $0.00160

Measured 7d ago against content hash 1e2e196f773f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

optimize-gemini-prompts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/prompt-optimizer/skills/optimize-gemini-prompts/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Optimize Gemini Prompts

Turn rough ideas and existing prompt stacks into copy-ready prompts for Gemini. Preserve the user's intent and hard constraints, ask for genuinely blocking information, and add model-specific structure only when it changes behavior.

Use the official basis

Read references/official-guidance.md when model-specific rationale, runtime guidance, or the longer checklist is needed. Treat its prose as a dated summary and its URLs as canonical sources. Fetch the live Google AI pages before making claims about current model IDs, API fields, thinking controls, tool support, context limits, knowledge cutoffs, availability, or pricing.

Follow the workflow

1. Capture the prompt contract

Identify:

  • the intended outcome, audience, language, and desired level of detail;
  • the target Gemini model or model family when version-specific behavior matters;
  • the text, documents, images, audio, video, examples, or other inputs Gemini will receive;
  • facts, definitions, and hard constraints to preserve;
  • the required output content, structure, schema, and length;
  • allowed sources, grounding, tools, calculations, citations, and validation needed for success;
  • fallback behavior when supplied context or tools do not support an answer.

Treat these as diagnostic dimensions, not mandatory headings. Preserve system, developer, user, tool-description, and untrusted-data boundaries when the user supplies a layered prompt stack.

2. Apply the clarity gate

Ask a question only when two reasonable answers would materially change the outcome, source boundary, model-specific strategy, multimodal interpretation, schema, permissions, or success criteria.

Treat these gaps as blocking by default:

  • a vague topic and generic verb with no identifiable deliverable or audience;
  • an input or source set whose identity changes what Gemini may conclude;
  • a multimodal request that does not identify which media or regions the instructions refer to;
  • a strict output contract with undefined fields, allowed values, or missing-value behavior;
  • an external or irreversible action without clear authorization;
  • conflicting requirements or a request for version-specific advice without a target model when the answer differs materially by version.

Read the full file on GitHub · 96 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 96 lines · 126 tokens per session scan A 1e2e196f773f

Subscribe to this mod's changes

optimize-gemini-prompts is a skill published in the GitHub repository IchenDEV/prompt-optimizer-plugins (6 stars, last pushed yesterday), licensed MIT. It adds 126 tokens to every session and 1,602 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

instructor

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.

OpenLAIR/dr-claw · 41 tokens

build-dotnet-agent-service

Build a local-first F# or C# Semantic Kernel agent service with explicit tools, model capability checks, evaluation fixtures, and draft-before-write promotion.

gaelic-ghost/socket · 36 tokens

instructor

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.

Orchestra-Research/AI-Research-SKILLs · 41 tokens

analyze-prompt

Use when the user wants to review, score, or improve how they write prompts; when coaching prompt quality; or when tracking prompting mistakes over a session. Keywords: prompt analysis, prompt coaching, how should I ask, rate my prompt, am I prompting well, prompt statistics, prompt score.

rayapatiranjithai/prompt-analyzer · 64 tokens

prompt-mini

Forges weak Claude Code prompts into structured, credit-saving, framework-aware prompts. Use when prompts are vague, missing scope, or mention a stack without clear task definition.

nidhinjs/prompt-mini · 37 tokens

gpt-5-6-prompt-engine

Use when creating, auditing, rewriting, debugging, migrating, or evaluating GPT-5.6 Sol, Terra, or Luna prompt layers, tool descriptions, agent briefs, or prompt stacks; choosing runtime configuration; or comparing controlled prompt candidates.

wp-a/gpt-5.6-prompt-engine · 58 tokens