跳到正文
cccskills
免费在 GitHub 公开

showme

Drive a headed browser to a specific state in a web app (a feature, flow, screen, or bug repro) and leave the window open for the user to explore. Use when the user says "show me X", "take me to that screen", "set up the repro", or wants to try an app state firsthand.

中文简介正在准备中。当前显示原文说明。

集成工具Playwright

实测评分 未实测

查看安装方法

包含的文件(1)

  • SKILL.md3.1 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

showme

Drive a headed browser to the state the user described, then hand them the live window. You do the setup, they do the exploring.

This skill only adds the headed, leave-open, hand-over wrapper. For the actual driving (navigate, snapshot, click, fill, log in), load the playwright-cli skill and follow it.

Steps

  1. Preflight. Run ${CLAUDE_PLUGIN_ROOT}/skills/playwright-cli/check.sh. If it fails, relay its message to the user and stop. Do not fall back to another automation tool.

  2. Work out the target. From context, find the URL (production, staging, or localhost:PORT), the preconditions that define the state, and the point of interest. If the app is this repo's and its dev server is not running, start it first. Ask one short question only when the target is genuinely ambiguous.

  3. Open a headed, named session. Every later command carries the same -s=showme.

    playwright-cli -s=showme open --headed <url>
    

    If no window appears, a showme session is already running headless. Close it with playwright-cli -s=showme close and reopen. playwright-cli list shows every session and whether it is headed.

  4. Drive to the state with the snapshot-and-ref loop from playwright-cli, stopping just before the point of interest.

  5. Verify before handing over. When the state is a claim to confirm (a bug, a regression, "X happens when you do Y"), trigger the key action yourself and check the outcome, as long as it is non-destructive. Never hand over a window that "should" show something you have not seen it show.

    • It reproduced: reset to just before the action (reload or undo) so the user can trigger it themselves, then hand over and say you confirmed it.
    • It did not reproduce: stop and tell the user the claim did not hold, with what you did and what happened instead of the expected result. Catching this here saves the user a dead-end click-through.
    • The action is destructive, or the state is open-ended exploration: leave the action to the user and hand over.
  6. Hand over. Do not close. The session daemon keeps the window alive. Tell the user in a few lines:

    • It is open: session showme, on which page.
    • You are here: the current state, what you set up, and whether you confirmed the action works.
    • Try this: the exact action, for example "click the blue Save button".
    • You will see: what should happen, so they know what to look for.

    Mention playwright-cli -s=showme close for when they are done.

Notes

  • The open window is the deliverable. Never close it on your own.
  • To keep login state across runs, open with --persistent (profile managed by playwright-cli) or --profile=$HOME/.showme-profile for a directory you choose. The in-memory default forgets everything on close.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Structure AI work artifacts under .aiwork/{YYYY-MM-DD}_{slug}/ folders using the project's protocol (intent, triage, research, spec, prd, areas, plan, review, notes, docs/). Use when the user asks to plan, capture an intent, make a spec, triage, research a task, write a report, code review, summarize findings, save the work, document decisions, record this, write that down, persist findings, or references any path under .aiwork/. Also use when starting a non-trivial task that needs a plan or spec before implementation, or when finishing one and capturing notes.

中文简介正在准备中。当前显示原文说明。

lttr/claude-marketplace22026年10月22日 更新

Use this skill when the user asks to test, verify, interact with, or automate web pages and browsers. Trigger for requests involving Chrome automation, browser testing, web scraping, screenshot capture, element selection, or checking web applications. Also trigger when user mentions "browser tools" explicitly.

中文简介正在准备中。当前显示原文说明。

lttr/claude-marketplace22026年10月22日 更新

changelog

免费

Show recent Claude Code changes personalized to user's setup. Trigger when user asks about changelog, "what's new", "cc changelog", "claude code updates", "recent changes", or wants to know what changed in Claude Code.

中文简介正在准备中。当前显示原文说明。

lttr/claude-marketplace22026年10月22日 更新

Review code changes from current branch, an Azure DevOps PR, a git ref, or a diff/patch file. Trigger when user says "review this", "code review", "/df:code-review", or provides a PR id/URL, ticket URL, git ref, or diff path. Read-only — never posts comments.

中文简介正在准备中。当前显示原文说明。

lttr/claude-marketplace22026年10月22日 更新

Review code changes from the current branch, staged changes, a git ref, or a diff/patch file. Pure git-native — no platform/PR awareness. Trigger when user says "review this", "review diff", "/aiwork:code-review-diff", or provides a git ref or diff path. Read-only — never posts comments.

中文简介正在准备中。当前显示原文说明。

lttr/claude-marketplace22026年10月22日 更新

Czech typography rules for web development. Use when building web pages in Czech language, writing Czech content, or fixing typography issues in Czech text. Covers punctuation, dashes, quotes, numbers, units, non-breaking spaces, and HTML entities.

中文简介正在准备中。当前显示原文说明。

lttr/claude-marketplace22026年10月22日 更新

查看 lttr 的全部技能

报告此技能的问题