Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问许可证需确认审计提醒

gemini-infographicGemini infographic 搜索

Agent Skill

gemini-infographic 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

186

周安装

8

GitHub Stars

520

下载量

65
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:gemini-infographic(Gemini infographic 搜索)
来源仓库:https://github.com/charlie947/social-media-skills
仓库路径:skills/gemini-infographic
安装命令:
npx skills add https://github.com/charlie947/social-media-skills --skill gemini-infographic
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/charlie947/social-media-skills --skill gemini-infographic

简介

用于查找、检索和筛选相关信息。gemini-infographic 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

  • 适合根据关键词快速定位候选结果或来源线索。
  • 通过 GitHub 安装,建议确认搜索范围和结果过滤方式。
  • 可能触发联网请求,需评估数据源可靠性和更新频率。
  • 适用于 Codex、Claude、Cursor 和 Gemini CLI 研究场景。

SKILL.md

Gemini Infographic

CRITICAL: Auto-start on load

When this skill triggers, go straight to Step 1. Do not summarise the process.

Step 1. Get the source content

Ask:

Paste the content you want to turn into an infographic. A post, newsletter section, blog, research note, or raw bullet points all work.

Wait for the content.

Step 2. Build the brief

Analyse the content and produce an infographic brief in plain language. Include:

  • Title (6 words or fewer, punchy)
  • Subtitle (optional, one line of context)
  • Core structure: decide between steps, framework, comparison, stats, or list
  • Key points: 3 to 7 bullets max, each 10 words or fewer
  • Visual suggestions: arrows, boxes, highlighted numbers, icons, color accents. Be specific about placement and colour.
  • Footer CTA: handwritten text reading "Follow [Name] [Tagline] for more helpful content | Repost ♻️"

Tell the user:

Here is the brief. Tell me what to change, or say "generate" when you're happy.

Wait for approval.

Step 3. Output the Gemini prompt

Once approved, output the full prompt in a code block, with the brief inserted into the [INSERT YOUR INFOGRAPHIC CONTENT AND LAYOUT HERE] placeholder:

Generate a single image of a physical, hand-drawn infographic on a large whiteboard or notebook page.

Crucial Style Instructions (Read First):

Medium: The image must look like a photograph of a real whiteboard or large paper notepad.

Texture: All elements must look created by hand using colored marker pens (black, blue, red, green) and highlighters (yellow/orange). Lines should be slightly imperfect, wobbly, and have the texture of ink on a surface.

No Digital Fonts: All text, headings, and bullet points must appear handwritten or hand-printed in marker pen.

Layout: Structure the 1080x1350 image as follows:

[INSERT THE BRIEF HERE — title, subtitle, core structure, key points, visual suggestions]

Use multi-colored markers for emphasis. Keep text large and legible. Make everything look hand-drawn with slight imperfections. Make it look like a photograph of an actual notebook page.

Always include the handwritten text "Follow [Name] [Tagline] for more helpful content | Repost ♻️" at the bottom of the image, in the same hand-drawn marker style.

Tell the user:

Paste this into a new Gemini chat with Create Image enabled and Nano Banana selected. Generate at 1080x1350.

Step 4. Offer iteration

After the prompt, offer:

If the first generation misses, tell me what to adjust and I will rewrite the prompt. Common fixes: fewer colours, bigger title, different layout direction.

Rules

  • 1080x1350 pixel output is non-negotiable. Vertical format owns the LinkedIn feed.
  • Footer CTA always includes the recycle symbol and "Repost".
  • Never use em dashes in any output.
  • Keep bullets under 10 words. Longer text loses legibility at the whiteboard scale.
  • Always wait for user approval of the brief before outputting the final prompt.
  • British English unless voice.md says otherwise.
  • If the user has brand-kit.md or colours.md in the project, bake their brand colours into the visual suggestions.

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

34.9%
按下载量换算23

Claude

28.67%
按下载量换算19

Cursor

21.05%
按下载量换算14

Gemini CLI

10.21%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。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