Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add skillmds/skillmd --skill gemini-skillgit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skillmds/skillmd/gemini-skill)<a href="https://agentmods.dev/skills/skillmds/skillmd/gemini-skill"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/gemini-skill/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/skillmds/skillmd/gemini-skill"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/gemini-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00098 | $0.02058 |
| Opus 5.5 | $0.00039 | $0.00823 |
| Sonnet 5 | $0.00020 | $0.00412 |
| Haiku 4.5 | $0.00010 | $0.00206 |
Grade A, and why
gemini-skill 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 4d 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.
This is a copy
100% identical to gemini-skill — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Skill
⚠️ 操作优先级（必须遵守）
与 Gemini 的一切交互，按以下优先级选择方式：
- 🥇 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
- 🥈 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
- 🥉 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
绝对禁止：自行启动新的浏览器实例访问 Gemini 页面（如使用 OpenClaw 浏览器、另起 Puppeteer 等），这会导致会话冲突。
浏览器 Daemon 未运行时 MCP 工具会自动拉起，无需任何手动操作。
📡 进度同步 & 长耗时工具规则
MCP 工具调用（尤其是生图、等待回复等）可能耗时较长（60~180 秒）。必须遵守以下规则：
- 本 Skill 所有 MCP 工具均为同步阻塞调用，会等到最终结果才返回。不存在"中间状态"需要轮询。
- 调用长耗时工具时，
timeoutMs必须设为 ≥180000（3 分钟），避免传输层提前超时截断。 - 禁止在未收到工具最终返回前结束对话或向用户报告"还在运行"/"工具超时"。
- 每隔 15~30 秒向用户发送一条进度消息（如"正在等待 Gemini 生成图片…已等待 30 秒…"），保持反馈。
- 拿到最终结果后立即回传产物（文件路径）或报告错误，不得遗漏。
- 若
fullSize模式失败，可降级重试fullSize=false（预览图模式更稳定）。
触发关键词
- 生图任务：
生图、画、绘图、海报、nano banana、nanobanana、image generation、生成图片 - 若请求含糊，先确认用户是否需要生图
使用方式
本 Skill 通过 MCP Server 暴露工具，AI 直接调用即可。
浏览器启动、会话管理、图片提取、文件保存等流程已全部封装在工具内部。
⚠️ 强制规则
AI 必须始终通过 MCP 工具完成所有操作。
禁止绕过 MCP 自行编写临时脚本（如
node -e "..."或创建.js临时文件）来import/require本项目导出的函数（如createGeminiSession、createOps等）。如果 MCP 工具确实无法满足当前需求，AI 必须先向用户说明原因并获得明确同意， 才能编写临时脚本调用底层 API。未经用户同意，一律禁止。
可用工具
核心生图（封装完整流程）：
| 工具名 | 说明 | 入参 |
|---|---|---|
gemini_generate_image |
完整生图流程：新建会话→发prompt→等待→提取图片→保存本地（耗时约 60~120 秒） | prompt，newSession（默认false），referenceImages（参考图路径数组），fullSize（默认true，高清原图；false则预览图），timeout（默认120000ms） |
会话管理：
| 工具名 | 说明 | 入参 |
|---|---|---|
gemini_new_chat |
新建一个空白对话 | 无 |
gemini_temp_chat |
进入临时对话模式（不保留历史记录） | 无 |
模型切换：
| 工具名 | 说明 | 入参 |
|---|---|---|
gemini_switch_model |
切换 Gemini 模型 | model（pro / quick / think） |
文本对话：
| 工具名 | 说明 | 入参 |
|---|---|---|
gemini_send_message |
发送文本消息并等待回答完成，直接返回 Gemini 的回复文本 | message，timeout（默认120000ms） |
图片操作：
| 工具名 | 说明 | 入参 |
|---|---|---|
gemini_upload_images |
上传图片到输入框（仅上传不发送，可配合 send_message） | images（路径数组） |
gemini_get_images |
获取会话中所有已加载图片的元信息 | 无 |
gemini_extract_image |
提取指定图片的 base64 并保存到本地 | imageUrl（从 get_images 获取） |
gemini_download_full_size_image |
下载完整尺寸的高清图片，默认最新一张，可指定索引 | index（可选，从0开始，从旧到新） |
gemini_share_latest_image |
为图片创建公开分享链接并直接返回链接，默认最新一张 | index（可选），timeout，copyToClipboard，closeDialog |
What ships with it
7 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.
- 4d ago First seen · 165 lines · 98 tokens per session scan A 5ef8fef14a0a
gemini-skill is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 2,058 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to gemini-skill, differing in 1 line, and is treated as a copy.
Other skills, from other repositories
browser-use
Control the user's Chrome through the existing persistent Node REPL and the Qwen Browser SDK.
computer-use
Drives the GUI of a visible local app window through orca computer: accessibility tree, clicks, typing, menus, dialogs, and screenshots in native apps and external browser windows (Chrome, Edge, Safari) or webviews. Prefer a programmatic path (shell, filesystem, git, HTTP, existing CLIs) whenever it can complete the…
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
opencli-browser-sitemap
Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live…
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.