Agent Skills › langwatch/langwatch › haven-orb

haven-orb

GitHub

用于读取 Haven Orb 工具收集的用户反馈、页面控制台日志及网络请求数据,辅助前端开发人员进行 UI 调试和问题排查。

.claude/skills/haven-orb/SKILL.md langwatch/langwatch

Trigger Scenarios

用户询问页面错误或反馈 需要查看控制台或网络请求记录 检查未解决的反馈笔记

Install

npx skills add langwatch/langwatch --skill haven-orb -g -y
More Options

Non-standard path

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

Use without installing

npx skills use langwatch/langwatch@haven-orb

指定 Agent (Claude Code)

npx skills add langwatch/langwatch --skill haven-orb -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": "haven-orb",
    "description": "Read what a person sent from the haven orb on the app page: `haven orb feedback` notes with selector, viewport, console and requests, and `haven orb console|network`. Use when someone says 'haven feedback', 'haven page console', 'haven orb feedback', 'the haven orb', 'read the notes I left', 'resolve the feedback', 'wait for feedback', 'page console errors', 'failed requests on the page', 'haven orb', or 'what did I point at'.",
    "argument-hint": "feedback list --open | show <id> | resolve <id> | wait | console|network",
    "user-invocable": true
}

The haven orb: feedback and page buffers

When haven runs a stack, dev or built UI, the app page carries the haven orb, bottom right (apps/ui/vite/haven-orb/, specs/setup/haven-dev-orb.feature). A reader picks an element or drags a region, types a note, and it lands in this stack's store. The orb also pushes the page's last 200 console messages and requests: method, URL without its query, status, duration. Never a body, a header or a cookie.

While building UI, read it before you call the work done:

haven orb feedback list --open --agent      # notes nobody resolved yet
haven orb feedback show <id> --agent        # one note: selector or region, viewport, console, requests
haven orb feedback resolve <id>             # once you fixed it
haven orb feedback wait --timeout 5m        # block until the reader sends the next note (default 30s)
haven orb console --level error --agent   # levels: error, warn, info, log, debug
haven orb network --failed --agent
  • --json and --stack <slug> work on all of them.
  • The page buffer is whichever tab pushed last, and is empty until someone opens the app with the orb showing. The files live in .haven/logs/<slug>/orb/.
  • On a built-UI stack (haven up or --watch) the dev runtime injects the orb into the built page (tools/dev-runtime/src/haven-orb.ts); the first page load waits a few seconds while it builds. Under --hmr the Vite lane injects the same orb itself (apps/ui/vite.config.ts). Without a person's tab, drive the page with haven-browser.

Version History

  • c0c14dc Current 2026-10-19 19:33

Same Skill Collection

.claude/skills/analyticssim/SKILL.md
.claude/skills/browser-pair/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-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
fd2f989b
Indexed
2026-10-19 19:33

Home - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-10-19 23:15
浙ICP备14020137号-1