Gemini Skill

What it does

When your agent uses it

• Tasks that involve MCP servers
• Tasks that involve Image generation

Example prompts

• “生图/画图/绘图/nano banana/nanobanana/生成图片”
• “/gemini-skill”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1🥇 首选：调用 MCP 工具 — 直接调用本 Skill 暴露的 MCP 工具完成操作，覆盖绝大多数场景
2. 2🥈 次选：运行 Skill 脚本 — 当 MCP 工具无法满足需求时，可运行本 Skill 项目中提供的脚本来完成
3. 3🥉 最次：连接 Skill 管理的浏览器 — 仅当前两种方式都无法解决时，可通过 gemini_browser_info 获取 CDP 连接信息，主动连接到本 Skill 管理的浏览器进行操作。此方式必须先征得用户同意

What it can do on your machine

Read from SKILL.md and the folder at commit 333e818. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • npm
  • node

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gemini Skill loads about 1.1k tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 47 tokens; SKILL.md has 297 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~47

When it runs · the whole SKILL.md, loaded when a task matches

~1.1k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from WJZ-P/gemini-skill at commit 333e818, republished under its MIT licence (© WJZ-P). 297 words, ~1,069 tokens.

name

gemini-skill

description

通过 Gemini 官网（gemini.google.com）执行生图、对话等操作。用户提到"生图/画图/绘图/nano banana/nanobanana/生成图片"等关键词时触发。操作方式分三级优先级：首选 MCP 工具 → 次选 Skill 脚本 → 最次连接 Skill 浏览器手动操作（需用户授权）。禁止自行启动外部浏览器访问 Gemini。

{
  "mcpServers": {
    "gemini": {
      "command": "node",
      "args": ["<项目绝对路径>/src/mcp-server.js"]
    }
  }
}

© WJZ-P, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 39 other files (references) in the repository root of WJZ-P/gemini-skill.

• SKILL.md
• .env
• .env.example
• .gitignore
• ATLAS_CLOUD_PROVIDER_REVIEW.md
• LICENSE
• README.en.md
• README.md
• markdown/Bloome.jpg
• markdown/atlas-cloud-provider.png
• markdown/bloome-home.png
• markdown/example.png
• markdown/example2.png
• markdown/gemini-color.svg
• markdown/home.png
• package-lock.json
• package.json
• references/gemini-flow.md
• references/intent-routing.md
• … and 21 more

Open the folder on GitHubat commit 333e818