Agent Skills › langwatch/langwatch › browser-pair

browser-pair

GitHub

协助用户通过可视化反馈迭代UI。读取用户备注,使用headless浏览器验证修复效果,最小化修改组件样式并等待用户确认。

.claude/skills/browser-pair/SKILL.md langwatch/langwatch

Trigger Scenarios

browser pair paired browser let's look at this together open chromium

Install

npx skills add langwatch/langwatch --skill browser-pair -g -y
More Options

Non-standard path

npx skills add https://github.com/langwatch/langwatch/tree/main/.claude/skills/browser-pair -g -y

Use without installing

npx skills use langwatch/langwatch@browser-pair

指定 Agent (Claude Code)

npx skills add langwatch/langwatch --skill browser-pair -a claude-code -g -y

安装 repo 全部 skill

npx skills add langwatch/langwatch --all -g -y

预览 repo 内 skill

npx skills add langwatch/langwatch --list

SKILL.md

Frontmatter
{
    "name": "browser-pair",
    "description": "Iterate on UI with a person watching and giving live visual feedback. Pointer skill: the person uses their own tab on the stack and the haven orb; you read their notes and check fixes with `haven browser`. Use when the user says 'browser pair', 'paired browser', 'let's look at this together', 'open chromium', or wants live visual feedback on a UI change.",
    "argument-hint": "[page-or-feature]",
    "user-invocable": true
}

Browser pair: a person and you on one stack

There is no separate headed browser. Where haven is installed its gate refuses Playwright's MCP tools, and haven browser is headless. The person looks at their own tab; you work from their notes. haven-browser is the one authority for driving a browser.

  1. Stack. haven status gives the app URL. If none runs, haven up --agent -d only when asked (haven-lifecycle). Tell the person the URL, and the mode: the default stack serves the built UI (an edit shows after a rebuild), pnpm dev:hmr serves Vite (an edit shows on save).
  2. Their feedback. The haven orb on the page lets them point at an element or drag a region and leave a note. Read it with haven orb feedback list --open --agent, or block on haven orb feedback wait (haven-orb). Resolve a note once fixed.
  3. Your look. Check a fix with haven browser open <path> --lane pair --as admin (haven-auth for sign-in). Use snapshot --grep to find controls and a screenshot when the change is visual (width, padding, colour, clipping, dark mode); a snapshot cannot show paint.
  4. Edits. Read the component, make the smallest edit, say in one line what to look for, then tell them when the rebuild or save has landed. Components come from the design system (design-system skill); do not reach for raw Chakra.

Keep reports to a sentence or two: the person can see the page. Wait for their direction between changes.

For a walk through scenarios with a pass/fail report, use browser-test.

Version History

  • c0c14dc Current 2026-10-19 19:32
  • 12615f1 2026-08-20 10:00

Same Skill Collection

.claude/skills/analyticssim/SKILL.md
.claude/skills/browser-test/SKILL.md
.claude/skills/chakra-ui-builder/SKILL.md
.claude/skills/chakra-ui-refactor/SKILL.md
.claude/skills/code-review/SKILL.md
.claude/skills/code-search/SKILL.md
.claude/skills/feature-map/SKILL.md
.claude/skills/githubsim/SKILL.md
.claude/skills/haven-auth/SKILL.md
.claude/skills/haven-db/SKILL.md
.claude/skills/haven-orb/SKILL.md
.claude/skills/haven-play/SKILL.md
.claude/skills/haven-seed/SKILL.md
.claude/skills/haven-setup/SKILL.md
.claude/skills/idpsim/SKILL.md
.claude/skills/lambdasim/SKILL.md
.claude/skills/langwatch-kanban/SKILL.md
.claude/skills/llmsim/SKILL.md
.claude/skills/mailsim/SKILL.md
.claude/skills/module/SKILL.md
.claude/skills/outboundsim/SKILL.md
.claude/skills/ownership/SKILL.md
.claude/skills/repo-tree/SKILL.md
.claude/skills/storagesim/SKILL.md
.claude/skills/voicesim/SKILL.md
plugins/langwatch/skills/langwatch/SKILL.md
services/langy-agent/skills/github/SKILL.md
skills/_compiled/native/agent-best-practices/SKILL.md
skills/_compiled/native/agent-performance/SKILL.md
skills/_compiled/native/automations/SKILL.md
skills/_compiled/native/code-changes/SKILL.md
skills/_compiled/native/context-sweet-spot/SKILL.md
skills/_compiled/native/daily-insights/SKILL.md
skills/_compiled/native/dashboard-widgets/SKILL.md
skills/_compiled/native/datasets/SKILL.md
skills/_compiled/native/debug-instrumentation/SKILL.md
skills/_compiled/native/debug-with-langwatch/SKILL.md
skills/_compiled/native/drive-the-ui/SKILL.md
skills/_compiled/native/eval-triage/SKILL.md
skills/_compiled/native/evaluate-multimodal/SKILL.md
skills/_compiled/native/evaluations/SKILL.md
skills/_compiled/native/experiments/SKILL.md
skills/_compiled/native/find-traces/SKILL.md
skills/_compiled/native/generate-rag-dataset/SKILL.md
skills/_compiled/native/github/SKILL.md
skills/_compiled/native/guided-onboarding/SKILL.md
skills/_compiled/native/level-up/SKILL.md
skills/_compiled/native/lwql-charts/SKILL.md
skills/_compiled/native/online-evaluations/SKILL.md

Metadata

Files
0
Version
c0c14dc
Hash
1a90a8d0
Indexed
2026-08-20 10:00

홈 - 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-10-26 06:05
浙ICP备14020137号-1