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 | $0.00089 | $0.02735 |
| Opus 5.5 | $0.00036 | $0.01094 |
| Sonnet 5.5 | $0.00018 | $0.00547 |
| Haiku 4.5 | $0.00009 | $0.00274 |
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 9d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini 3.x Prompting
When to Use
- Creating or editing system prompts targeting Gemini 3.x
- Writing few-shot examples for classification or extraction
- Structuring long-context prompts with multiple sources
- Writing agentic or tool-use instructions for Gemini 3.x
- Migrating prompt text from Gemini 2.5 or an earlier 3.x release
Gemini 4 (gemini-4-argon) has its own guidance; check https://ai.google.dev/gemini-api/docs/models before applying this skill to it.
Overview
Gemini 3.x is a reasoning model family. It responds best to short, direct instructions and may over-analyze verbose prompt-engineering techniques written for older models (https://ai.google.dev/gemini-api/docs/gemini-3, "Prompting best practices"). Reasoning depth is set by the thinking_level parameter (thinkingLevel in JS and REST), so do not write manual chain-of-thought instructions.
- Concise input. "Be concise in your input prompts. Gemini 3 responds best to direct, clear instructions." (gemini-3 page)
- Direct output by default. Ask explicitly for a conversational or detailed tone. (prompting-strategies page)
- Context first, question last. Supply all context first and put the specific question at the very end. (prompting-strategies page)
- Constraints first. Put behavioral constraints, persona, and output format in the system instruction or at the very start of the user prompt. (prompting-strategies page)
- Temperature stays at 1.0. Google strongly recommends the default for all Gemini 3 models; lower values "may lead to unexpected behavior, such as looping or degraded performance". (gemini-3 page)
- Few-shot examples. "We recommend to always include few-shot examples in your prompts." (prompting-strategies page)
Sources: https://ai.google.dev/gemini-api/docs/gemini-3 and https://ai.google.dev/gemini-api/docs/prompting-strategies.
Prompt Structure
Put stable rules first, long context next, and the task last. Pick one delimiter style per prompt, XML tags or Markdown headings, and do not mix them.
What ships with it
3 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.
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.
- 9d ago Changed · -13 tokens per session 6076c80085e5
- 17d ago Changed · -215 lines · +13 tokens per session e37501ab7350
- 1mo ago Changed · -126 lines · -10 tokens per session 37cfae74c05d
- 2mo 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 10d ago), licensed Apache-2.0. It adds 89 tokens to every session and 2,735 once invoked, about $0.0004 per session on Opus 5.5. 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.
gemini-3-prompting compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gemini-3-promptingDynokostya/just-works | Skill | 14 | 10d ago | Apache-2.0 | A | 89 | Claude Code |
| llm-app-patternsdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 54 | Claude Code, Codex |
| prompt-engineerJeffallan/claude-skills | Skill | 12k | 7d ago | MIT | A | 93 | Claude Code |
| prompt-optimizationlangwatch/langwatch | Skill | 5.0k | yesterday | Apache-2.0 | A | 105 | Claude Code, Codex |
| omh-model-optimizationrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 84 | Claude Code, Codex |
| ideogram4digitalsamba/claude-code-video-toolkit | Skill | 2.5k | yesterday | MIT | A | 99 | Claude Code |
| prompt-library-for-startupsaws/agent-toolkit-for-aws | Skill | 3.4k | yesterday | Apache-2.0 | A | 228 | Claude Code |