菜单
Validate a userscript end-to-end in a real Chrome tab via the Claude in Chrome MCP. Loads the target page, simulates the script's effect, reads console logs and DOM state, and reports whether the script's behavior matches its `@description`.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/danielrosehill/Claude-Userscript-Development-Plugin --skill test-userscript命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Look up Tampermonkey documentation — metadata keys (`@match`, `@grant`, `@run-at`, etc.), the GM_* / GM.* API, and configuration. Fetches the official docs page on demand to stay current.
Set up a brand-new development workspace for a single userscript. Asks public or private, creates the GitHub repo with the chosen visibility, installs this plugin at project scope inside it, and ends. The user opens that repo in a fresh Claude Code session and starts authoring the script with `new-userscript`.
Bump a userscript's `@version` (semver), update README, commit, tag, and push. Tampermonkey only auto-updates installed scripts when `@version` increases — forgetting this means users never receive fixes.
基于 SOC 职业分类
正在显示 SKILL.md
| name | test-userscript |
| description | Validate a userscript end-to-end in a real Chrome tab via the Claude in Chrome MCP. Loads the target page, simulates the script's effect, reads console logs and DOM state, and reports whether the script's behavior matches its `@description`. |
Validate userscript behavior live in Chrome. Tampermonkey itself can't be installed/configured by Claude in Chrome (it's a browser extension installed by the user), so this skill does simulated injection: it navigates to the target site and evaluates the userscript body via playwright_evaluate / javascript_tool to confirm logic works against real DOM.
bump-versionThe Claude in Chrome MCP must be available. Tools used:
mcp__claude-in-chrome__tabs_context_mcp — pick a tabmcp__claude-in-chrome__tabs_create_mcp — open the target URLmcp__claude-in-chrome__navigate — go to a @match URLmcp__claude-in-chrome__javascript_tool — inject and run the script bodymcp__claude-in-chrome__read_console_messages — collect console.log outputmcp__claude-in-chrome__read_page / get_page_text — inspect the resulting DOMLoad each tool via ToolSearch first.
.user.js file. Parse the metadata block — extract @match / @include URLs and @grant list.GM_* APIs the simulator can't provide (GM_xmlhttpRequest, GM_setValue, GM_getValue, etc.). Tell the user this script can only be validated by installing it in Tampermonkey and exercising it manually. Stop here.@grant none, proceed: open one of the matched URLs in a new tab, wait for document-idle, then playwright_evaluate the IIFE body.gif_creator.A short report (under 30 lines) the user can paste into a commit message or PR description.