Borrowing it
Nothing to install: this file belongs to Dynokostya/just-works. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Dynokostya/just-works/main/.claude/skills/gemini-3-prompting/SKILL.mdgit clone --depth 1 https://github.com/Dynokostya/just-worksWrote 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.
[](https://agentmods.dev/skills/dynokostya/just-works/gemini-3-prompting)<a href="https://agentmods.dev/skills/dynokostya/just-works/gemini-3-prompting"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/gemini-3-prompting/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dynokostya/just-works/gemini-3-prompting"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/gemini-3-prompting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high System Prompt Leakage · line 3 Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00099 | $0.06052 |
| Opus 5 | $0.00049 | $0.03026 |
| Sonnet 5 | $0.00020 | $0.01210 |
| Haiku 4.5 | $0.00010 | $0.00605 |
Grade A, and why
gemini-3-prompting 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 522 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini 3 Prompting
When to Use
- Creating or editing system prompts targeting Gemini 3
- Writing few-shot examples for classification or extraction tasks
- Structuring long-context prompts with multiple sources
- Writing agentic instructions for Gemini 3 tool-use workflows
- Decomposing complex prompts into chainable sub-prompts
- Migrating prompt text from Gemini 2.5
Overview
Gemini 3 responds best to direct, concise instructions. Verbose prompt engineering techniques from older models (Gemini 2.5 and earlier) cause over-analysis and degrade output quality. The model has native thinking capabilities controlled by a thinking_level parameter (snake_case in Python, thinkingLevel in JS/REST) -- do not write manual chain-of-thought instructions. (Source: ai.google.dev/gemini-api/docs/gemini-3)
- Conciseness Over Verbosity: "Be concise in your input prompts. Gemini 3 responds best to direct, clear instructions." Remove filler.
- Context Before Task: "When providing large amounts of context (e.g., documents, code), supply all the context first. Place your specific instructions or questions at the very end of the prompt."
- Constraints + Persona at the Beginning: "Place essential behavioral constraints, role definitions (persona), and output format requirements in the System Instruction or at the very beginning of the user prompt."
- Native Thinking:
thinking_level(values:minimal/low/medium/high; defaulthigh, dynamic) replaces manual CoT prompting -- do not write "Let's think step by step." Availability varies by model -- see the thinking-level table. - Temperature at 1.0: "We strongly recommend keeping the
temperatureat its default value of 1.0." Setting it below may cause "looping or degraded performance." - Persona + Constraint Alignment: Persona and other constraints belong together in the System Instruction. Ensure they do not contradict each other.
- Default Directness: "By default, Gemini 3 models provide direct and efficient answers." Request conversational tone explicitly if needed.
- Few-Shot Recommended: "Prompts without few-shot examples are likely to be less effective."
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.
- 6d ago First seen · 522 lines · 99 tokens per session scan A b7f3e0376da6
gemini-3-prompting is a skill published in the GitHub repository Dynokostya/just-works (14 stars, last pushed 2d ago), licensed Apache-2.0. It adds 99 tokens to every session and 6,052 once invoked, about $0.0005 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 2026-09-04.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…