By WJZ-PUpdated 2026-05-11gemini-skill@clawhub_wjz-p/gemini-skill
Task AutomationTool Use#图片生成
According to AlphaMoat, as of 2026-09, Gemini Skill has 2,477 downloads and 2 stars — ranked #4,118 of 5,078 AI skills overall, and #839 of 969 in AI Agent.
| Platform | Installs | Downloads | Stars | Comments |
|---|---|---|---|---|
| ClawHub ↗ | 55 | 1.9K | 1 | - |
| SkillHub ↗ | 463 | 2.5K | 2 | — |
Platforms count differently and update at different times.
It checks sign-in, routes the task to text or image generation, chooses an available model and returns the answer or image. Ambiguous requests require clarification of the output type. Model fallback is disclosed, with documented handling for generation timeouts or download failures. Actual features depend on the account and website availability. Prompts and any submitted images are sent through the Gemini website to Google. Do not submit sensitive content unless that external processing is approved; features depend on the signed-in account and the page.
Profile published 2026-10-27
Generated from the skill’s documentation as examples; not results of actual runs.
The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.
| Month | Downloads | MoM | Stars |
|---|---|---|---|
| 2026-09 | 2.5K | — | 2 |
| 2026-08 | 2.0K | +10.0% | 2 |
| 2026-07 | 1.8K | +14.0% | 2 |
| 2026-06 | 1.6K | +11.4% | 2 |
| 2026-05 | 1.4K | — | 2 |
| 2026-03 | 736 | — | 1 |
The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.
--- name: gemini-skill description: 通过 Gemini 官网（gemini.google.com）执行问答与生图操作。用户提到“问问Gemini/让Gemini回答/去Gemini问”，或出现“生图/画图/绘图/nano banana/nanobanana/生成图片”等关键词时触发。默认使用可用模型中最强档（优先 Gemini 3.1 Pro），按任务切换文本问答或图片生成流程，并把结果回传给用户。 --- # Gemini Web Ops ## 核心规则 1. 使用 OpenClaw 内置浏览器，`profile="openclaw"`。
2. 涉及生图关键词（如：生图、绘图、画一张、nano banana）时，优先用无头浏览器流程执行。 3. 文本问答任务（如“问问Gemini xxx”）走 Gemini 文本提问链路。 4. 默认模型：可用列表中最强模型，优先 `Gemini 3.1 Pro`。 5. 执行生图后先向用户回报“正在绘图中”，完成后回传图片。 ## 任务分流 - **文本问答**触发词：`问问Gemini`、`让Gemini回答`、`去Gemini问`。 - **生图任务**触发词：`生图`、`画`、`绘图`、`海报`、`nano banana`、`nanobanana`、`image generation`。 - 若请求含糊，先确认：是文本回答还是要出图。 ## 标准执行流程 ### A. 文本问答 1. 打开 `https://gemini.google.com`。 2. 校验登录态（头像/输入框可见）。 3. 选择最强可用模型（优先 Gemini 3.1 Pro）。 4. 将用户问题原样输入并发送。 5. 等待完整输出，提炼后回传（必要时附原文要点）。 ### B. 生图流程 1. 打开 Gemini 页面并确认登录。 2. 选择最强可用模型（优先 Gemini 3.1 Pro）。 3. 将用户提示词原样输入。 4. 开启/勾选图片生成能力（若 UI 有“生成图片/图片”开关）。 5. 发送后立即通知用户：正在绘图中。 6. 结果出现后： - 优先用“下载原图”按钮获取原图。 - 若无下载按钮或失败，可对图片右键另存（通常是标清图）。 7. 把图片返回用户；若有多张，按顺序全部回传。 ## 失败回退 1. 元素定位失败：刷新页面后重试一次。 2. 模型不可用：降级到次优 Gemini 模型并告知。 3. 生成超时：回报“仍在生成中”，继续等待一次；再次超时则请用户换短提示词。 ## 低 token 优先策略 - 优先使用 `scripts/gemini_ui_shortcuts.js` 的快捷选择器。 - 先 evaluate 批量动作，再 snapshot 精准兜底。 - 避免高频全量快照。 ## 参考 - 详细执行与回退：`references/gemini-flow.md` - 关键词与路由：`references/intent-routing.md`
Records learnings, errors and corrections as Markdown files for later reuse and promotion into workspace memory.
Finds skills in local and remote catalogs from a plain-language request and recommends what to install.
A browser-automation command line skill for AI agents.
Turns corrections and self-review into tiered memory and promotes or archives it by use.
Reviews a third-party skill's source, permissions, and danger patterns against a checklist before it is installed.
Stores agent memory and cross-skill state as a typed, constraint-checked knowledge graph.
A workspace setup guide for planning proactive follow-up, working memory and review routines for an AI agent.
A guide to creating and updating effective Claude skills.
Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.