Token导航 LogoToken导航TokenDH.com
前端设计只读github未标认证来源可访问许可证需确认审计通过

nano-banana-prompting纳米香蕉提示

Agent Skill

用于辅助提示词、系统指令、Agent 行为约束和工作流模板的整理。它适合让 Agent 规范任务边界、统一输出格式、拆分操作步骤或优化提示词可复用性。使用时需要保留真实业务约束,不要把示例当硬规则;涉及自动执行、外部工具或高风险操作时,应在提示词中明确确认步骤、权限边界和失败处理方式。

总安装

1,647

周安装

66

GitHub Stars

323

下载量

533
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:nano-banana-prompting(纳米香蕉提示)
来源仓库:https://github.com/pedronauck/skills
仓库路径:skills/nano-banana-prompting
安装命令:
npx skills add https://github.com/pedronauck/skills --skill nano-banana-prompting
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/pedronauck/skills --skill nano-banana-prompting

简介

用于辅助提示词模板、系统指令和工作流设计。nano-banana-prompting 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

  • 适合规范 Agent 行为边界、统一输出格式或拆分操作步骤。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装并使用该技能。
  • 使用时需保留真实业务约束,避免将示例提示词当作硬性规则。
  • 涉及自动执行时应明确确认步骤和失败处理机制后再实施。

SKILL.md

Nano Banana Prompting

Interactive prompt crafting for Nano Banana Pro image generation. This skill guides users through a structured process to create effective prompts by clarifying intent and applying proven techniques.

Workflow

Step 1: Gather Reference Materials

Before asking questions, check if the user has provided:

  • Reference images - Photos to use for character consistency, style, or composition
  • Existing prompts - Previous attempts to improve upon
  • Visual references - Screenshots or examples of desired output

If reference materials are available, this affects which techniques apply (e.g., Reference Role Assignment, Character Consistency).

Step 2: Clarify Intent with Questions

Use the AskUserQuestion tool to understand the user's goal. Ask questions in batches of 2-4, focusing on the most important aspects first.

Core Questions (always ask)

  1. Output Type - What kind of image?

- Photo/realistic - Illustration/artistic - Infographic/educational - Product shot/commercial - UI mockup/design

  1. Subject - Who or what is the main focus?

- Person (with or without reference) - Object/product - Scene/environment - Concept/abstract

Technique-Specific Questions (based on answers)

If Photo/Realistic:

  • What era or camera style? (modern DSLR, 1990s film, 2000s digital)
  • Specific lighting? (golden hour, studio, flash)
  • Aspect ratio needed? (16:9, 9:16, 1:1)

If Reference Images Provided:

  • What role for each image? (pose, style, color palette, background)
  • Should character identity be preserved?
  • Combine images or use as style reference?

If Text Needed:

  • What text should appear?
  • What font style? (serif, sans-serif, handwritten)
  • Where should text be placed?

If Educational/Infographic:

  • What concept to explain?
  • Target audience level?
  • Should it include labels, arrows, flow?

Step 3: Determine Prompt Style

Based on user responses, select the appropriate prompt format from references/guide.md:

User NeedRecommended Style
Simple, quick generationNarrative Prompt (Technique 1)
Precise control over detailsStructured Prompt (Technique 2)
Era-specific aestheticVibe Library + Photography Terms (Techniques 3-4)
Magazine/poster with textPhysical Object Framing (Technique 5)
Conceptual/interpretivePerspective Framing (Technique 6)
Diagram/infographicEducational Imagery (Technique 7)
Editing existing imageImage Transformation (Technique 8)
Multiple views/panelsMulti-Panel Output (Technique 9)
Multiple reference imagesReference Role Assignment (Technique 12)

Step 4: Generate the Prompt

Construct the prompt by:

  1. Loading references/guide.md to access technique details
  2. Applying relevant techniques based on Step 3 selection
  3. Cross-checking against guide examples for proper formatting
  4. Including negative prompts if needed (Technique 10)
  5. Specifying aspect ratio/resolution if required (Technique 11)

Prompt Construction Checklist

  • Subject clearly defined
  • Action/pose specified (if applicable)
  • Location/background described
  • Style/aesthetic anchored
  • Technical specs included (aspect ratio, lighting, camera)
  • Text integration specified (if needed)
  • Negative prompts added (if needed)
  • Reference image roles assigned (if using references)

Step 5: Present and Iterate

Present the generated prompt to the user with:

  1. The prompt - Ready to use
  2. Technique explanation - Why this structure was chosen
  3. Variation suggestions - Alternative approaches to try

Offer to refine based on feedback.

Step 6: Generate the Image

After the user is satisfied with the prompt, recommend using the nano-banana skill to generate the actual image. Inform the user:

"Your prompt is ready! Would you like me to generate the image now? I can use the nano-banana skill to create it."

If the user agrees, invoke the nano-banana skill with the crafted prompt.

Quick Reference: Technique Selection

User wants...                    → Use Technique...
─────────────────────────────────────────────────────
Simple description               → 1 (Narrative)
Detailed control                 → 2 (Structured YAML/JSON)
Specific era look                → 3 (Vibe Library)
Professional photo style         → 4 (Photography Terms)
Magazine/poster                  → 5 (Physical Object Framing)
"How X sees Y"                   → 6 (Perspective Framing)
Educational diagram              → 7 (Educational Imagery)
Edit existing image              → 8 (Image Transformation)
Multiple panels in one           → 9 (Multi-Panel)
Exclude something                → 10 (Negative Prompts)
Specific dimensions              → 11 (Aspect Ratio)
Multiple reference images        → 12 (Reference Roles)
Same character across images     → 13 (Character Consistency)
Merge multiple images            → 14 (Image Blending)
Enhance/restore image            → 15 (Upscaling)
Translate text in image          → 16 (Translation)

Resources

references/

  • guide.md - Complete prompting guide with 16 techniques, examples, and patterns. Load this file when constructing prompts to access specific technique details and examples.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.34%
按下载量换算178

Claude

28.95%
按下载量换算154

Cursor

19.12%
按下载量换算102

Gemini CLI

9.02%
按下载量换算48

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills