做什么
当工作取决于用户的活浏览器会话或可看见的渲染状态而非静态获取时使用,特别是用于浏览器调试上下文或DevTools所选的元素或请求,登录到的仪表板或CMS流,localhost apps,形式,上传,下载,媒体检查,DOM或iframe检查,Shadow DOM,或浏览器故障,看起来像是软404s,认证墙,反机器人检查,或速率限制.
技能库 智客分类:Agent 工作流 use-my-browser
当工作取决于用户的活浏览器会话或可看见的渲染状态而非静态获取时使用,特别是用于浏览器调试上下文或DevTools所选的元素或请求,登录到的仪表板或CMS流,localhost apps,形式,上传,下载,媒体检查,DOM或iframe检查,Shadow DOM,或浏览器故障,看起来像是软404s,认证墙,反机器人检查,或速率限制.
官方网址:skills.sh
先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。
当工作取决于用户的活浏览器会话或可看见的渲染状态而非静态获取时使用,特别是用于浏览器调试上下文或DevTools所选的元素或请求,登录到的仪表板或CMS流,localhost apps,形式,上传,下载,媒体检查,DOM或iframe检查,Shadow DOM,或浏览器故障,看起来像是软404s,认证墙,反机器人检查,或速率限制.
工作取决于用户的活浏览器会话或可见的渲染状态而不是静态获取,特别是针对浏览器调试上下文或DevTools所选的元素或请求,登录的仪表板或CMS流,localhost应用,表单,上传,下载,媒体检查io
按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Prerequisite check、Experience loop、Decision guide、Hard rules、Reference index。
文件分析:除 SKILL.md 外,正文引用了 references/site-patterns/、references/task-routing.md、references/browser-playbook.md、references/browser-capability-matrix.md、references/debug-handoff.md、references/control-plane-workflows.md,属于带资源的技能包,这些文件按需再读。
Use when work depends on the user's live browser session or visible rendered state rather than static fetches, especially for browser debugging contexts or DevTools-selected elements or requests, logged-in dashboards or CMS flows, localhost apps, forms, uploads, downloads, media inspection, DOM or iframe inspection, Shadow DOM, or browser failures that look like soft 404s, auth walls, anti-bot checks, or rate limits.
Prerequisite checkExperience loopDecision guideHard rulesReference index
来源分类:skills.sh agent-skill
nameuse-my-browserdescriptionreferences/site-patterns/references/task-routing.mdreferences/browser-playbook.mdreferences/browser-capability-matrix.mdreferences/debug-handoff.mdreferences/control-plane-workflows.md以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。
具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗
先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。
该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。
复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。
把 Agent Skill「use-my-browser」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-e14503f7e0482ad2-%E4%BD%BF%E7%94%A8%E6%88%91%E7%9A%84%E6%B5%8F%E8%A7%88%E5%99%A8.html 请存为 .cursor/skills/use-my-browser/SKILL.md 或 .claude/skills/use-my-browser/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。 该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/xixu-me/skills 取完整目录,不要只建一个 SKILL.md。
需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。
npx skills add 'https://github.com/xixu-me/skills' --list
npx skills add 'https://github.com/xixu-me/skills' --skill 'use-my-browser'
CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。
Do not treat this skill as a generic browsing default. Route from the evidence you need, not from tool preference.
Every task must be classified before you choose a route:
static-capable: the evidence can be produced without live browser state, visible confirmation, or page interactionbrowser-required: the evidence depends on rendered state, interaction, live session behavior, or browser-only structuresOnly static-capable tasks may fall back to static retrieval, curl, or other non-browser paths. Once a task is browser-required, stay on the browser path and mark missing capability as blocked instead of silently downgrading.
This skill is for work inside the user's live browser session, not for launching a separate fresh automation browser.
Before doing browser automation, confirm that your environment already has access to a live browser stack that can provide the capabilities the task depends on, such as page inventory, task-owned page creation, page selection, snapshots or visible-state reads, DOM inspection, text or form input, uploads, dialogs, console inspection, and network inspection. The exact stack does not matter here: confirm capability, not brand.
If the live browser stack is unavailable, do not attempt browser automation through this skill. Only static-capable work may fall back to static retrieval.
Live browser automation can trigger anti-bot or anti-automation defenses on some sites. Use browser interaction only when the task truly needs it, and avoid unnecessary repetitive actions once the needed evidence has been obtained.
Treat site patterns as part of the browser protocol, not as optional background reading.
For browser-required work, run this loop:
references/site-patterns/.Do not create a domain note for one-off noise. Do not skip the end-of-run review just because the task itself succeeded.
Writeback is expected when a run verifies any of the following:
isolatedContext quirkStart with the outcome, not the tool. Make the user's goal explicit, define what counts as done, and choose the cheapest route that can still produce the right evidence.
Use this routing order:
static-capable or browser-required.static-capable, load references/task-routing.md and stay on the cheapest route that still satisfies the evidence target.browser-required, load references/browser-playbook.md.references/browser-capability-matrix.md.references/debug-handoff.md.references/control-plane-workflows.md.references/anti-automation-friction.md.references/deep-dom.md.references/media-inspection.md.references/parallel-browser-ownership.md.uid target, also load references/selector-bridge.md.uid may have gone stale, or console / network inspection is now needed to explain the next browser decision, also load references/browser-recovery.md.references/site-patterns/, read that note before operating on the site.Treat the following as browser-required by default:
localhost, 127.0.0.1, or benchmark-style local fixturesdetails / collapsed evidence, or lazy-loaded contentThe normal happy path for a common task is this entrypoint plus one or two references, not the entire reference set.
browser-required, do not silently downgrade.browser-required task without explicitly checking whether the run should create, update, downgrade, or remove a site-pattern claim.curl, Invoke-WebRequest, or shell HTTP fetches for browser-required tasks.references/task-routing.md: static retrieval vs live browser routingreferences/browser-playbook.md: core page-action protocol and base browser loopreferences/browser-capability-matrix.md: capability proof for uncertain host sessionsreferences/debug-handoff.md: active debugging-context handoffreferences/control-plane-workflows.md: logged-in dashboard / CMS save-publish disciplinereferences/anti-automation-friction.md: soft 404 / auth / anti-automation classificationreferences/deep-dom.md: iframe, Shadow DOM, collapsed, or lazy-loaded evidencereferences/media-inspection.md: image, audio, and video evidencereferences/parallel-browser-ownership.md: multi-owner browser coordinationreferences/selector-bridge.md: selector-to-uid bridgingreferences/browser-recovery.md: stale uid, navigation drift, and console / network escalationreferences/site-patterns/README.md: site-pattern note maintenance rulesAgent 工作流
创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.
Agent 工作流
使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.
Agent 工作流
管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.
Agent 工作流
Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…