Agent Skills › langwatch/langwatch › haven-play

haven-play

GitHub

用于在本地沙箱或持久环境中尝试和运行 GitHub PR,支持自动安装、环境搭建及销毁,适用于代码审查和本地验证场景。

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

Trigger Scenarios

try a PR locally haven pr haven play run this PR in a sandbox review a PR by running it

Install

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

Non-standard path

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

Use without installing

npx skills use langwatch/langwatch@haven-play

指定 Agent (Claude Code)

npx skills add langwatch/langwatch --skill haven-play -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-play",
    "description": "Try a GitHub PR on this machine with `haven pr` (own worktree, install, stack on a hostname) or `haven pr <n> --throwaway` (a throwaway sandbox that destroys itself on quit; formerly `haven play`). Use when someone says 'try a PR locally', 'haven pr', 'haven play', 'haven pr --throwaway', 'run this PR in a sandbox', 'review a PR by running it', 'play a PR', 'throwaway stack', or 'worktree overview' (`haven git` is deleted).",
    "argument-hint": "pr <number> [--throwaway]",
    "user-invocable": true
}

haven pr and haven pr --throwaway

Command What it does Quitting
haven pr <n> worktree + install + stack up on a hostname keeps everything
haven pr <n> --throwaway own checkout, own databases, own hostname in a sandbox DESTROYS all of it
haven pr 4913 --dry-run                    # resolve and print the plan, create nothing
haven pr 4913                              # the real run
haven pr 4913 --throwaway --seed demo                # seeded sandbox; presets bare|demo|onboarding|post-onboarding
haven pr 4913 --throwaway --allow-untrusted          # the only way in agent mode when an author lacks write access

haven pr flags: --dry-run, --no-install, --allow-closed, --allow-scripts (install lifecycle scripts for a fork), --discard-local-changes (overwrite local edits instead of stashing). Worktrees land in HAVEN_WORKTREE_DIR.

  • haven pr --throwaway needs the GitHub CLI (gh auth login), discloses the destruction contract, passes a trust gate, starts a container tier, and tears down on quit (a hard kill leaves a record that haven machine clean finishes). An agent never runs it without being asked. Untrusted PR checkouts install without lifecycle scripts.
  • Prefer a repo worktree via make worktree <name> for your own work; pr and pr --throwaway are for other people's code.
  • haven git and haven play are retired spellings: they exit 64 and name the new one.

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-orb/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
4fdcaadf
Indexed
2026-10-19 19:33

Главная - Вики-сайт
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-10-21 06:07
浙ICP备14020137号-1