According to AlphaMoat, as of 2026-09, Webpage Screenshot has 3,891 downloads and 0 stars — ranked #2,671 of 5,078 AI skills overall, and #525 of 969 in AI Agent.
| Platform | Installs | Downloads | Stars | Comments |
|---|---|---|---|---|
| ClawHub ↗ | 125 | 3.8K | - | - |
| SkillHub ↗ | 123 | 3.9K | - | — |
Platforms count differently and update at different times.
The local script can create a full-page PNG including scrollable content. Browser MCP is suited to quick inspection and interaction but does not directly create a screenshot file. Screenshots may capture login details, private account data, or internal content; review the page and authenticated session before saving or sharing, and use trusted browser dependencies.
Profile published 2026-10-29
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 | 3.9K | — | - |
| 2026-08 | 3.7K | +4.0% | - |
| 2026-07 | 3.5K | +8.8% | - |
| 2026-06 | 3.3K | +5.5% | - |
| 2026-05 | 3.1K | — | - |
| 2026-03 | 2.2K | — | - |
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: webpage-screenshot description: 打开指定网页并截图为图片文件。在用户要求对某 URL 截图、保存网页为图片、或需要网页快照时使用。 --- # 网页截图 ## 何时使用 - 用户给出一个 URL,要求「打开并截图」或「保存网页为图片」
- 需要网页快照、页面留档或可视化结果时 ## 方式一:运行项目脚本(推荐,得到文件) 使用项目内 TypeScript 脚本,可保存为本地图片文件: ```bash # 在项目根目录执行 npm run screenshot -- <URL> [输出路径] ``` 示例: ```bash npm run screenshot -- https://example.com # 默认保存为 ./screenshot.png npm run screenshot -- https://example.com ./output/page.png ``` **前置条件**:已执行 `npm install` 且已安装浏览器:`npx playwright install chromium`。 ## 方式二:使用 MCP 浏览器 若仅需在对话中「看到」页面内容而不必保存为文件,可使用 Cursor 的 browser MCP: 1. `browser_navigate` 打开目标 URL 2. `browser_snapshot` 获取页面结构(相当于当前状态的“快照”信息) 注意:MCP 浏览器不直接生成截图文件,适合快速查看与交互。 ## 输出 - 脚本方式:在指定路径生成 PNG 截图(默认 `screenshot.png`)。 - 截图为整页(含滚动区域),视口宽度默认 1280px。
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.