Agent Skills › langwatch/langwatch › haven-seed

haven-seed

GitHub

用于为 haven 堆栈生成种子数据、查看登录凭据及状态,支持自动播种、多种数据规模预设和干运行检查。

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

Trigger Scenarios

填充测试或开发环境的初始数据 获取生成的虚假账号和密码以便登录 检查种子数据的生成进度或状态 在启动时跳过自动数据播种

Install

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

Non-standard path

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

Use without installing

npx skills use langwatch/langwatch@haven-seed

指定 Agent (Claude Code)

npx skills add langwatch/langwatch --skill haven-seed -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-seed",
    "description": "Fill a haven stack with seeded data and read its logins with `haven db seed`, including the auto-seed that `haven up` runs on an empty stack. Use when someone says 'haven seed', 'haven db seed', 'seed the stack', 'seed data', 'auto-seed', 'haven up --no-seed', 'who can I log in as', 'seeded logins', 'fake credentials', 'tiny small medium large seed', 'seed status', 'haven db status', 'haven db logins', 'live load', 'seed an org on a licence', or 'seedgen'.",
    "argument-hint": "[preset] [--size tiny|small|medium|large] [--persona all] [--json] [--reveal]",
    "user-invocable": true
}

haven db seed

haven db seed generates seeded data into this stack (seedgen, tools/seedgen), then prints the logins and credentials. Names are invented; same --seed gives the same content.

Auto-seed on haven up

On a stack that was never seeded, haven up runs the tiny tier with all four personas after the identity seed. It waits about a minute, then reports ready and lets the seed finish in the background; haven db status and haven status show progress. Skip it with haven up --no-seed or HAVEN_AUTO_SEED=0. A failure is one line and never stops the boot.

Commands

haven db seed                       # small tier, then the logins (masked)
haven db status                # the last run's state and latest log lines
haven db seed --size tiny --persona startup
haven db seed --dry-run             # counts, rows, bytes, duration; writes nothing
haven db seed --json --reveal       # logins and credentials as one object, unmasked
haven db seed --live                # a gentle live load into the last seed's orgs
haven db seed --resume              # continue the last run of the same flags, keeping its anchor and run id

Flags: --size tiny|small|medium|large, --spans <n> (1 to 2000000), --days <d>, --persona startup,enterprise,gateway,agent-eval|all, --private <n> (default 0 on every tier: nothing binds a private org yet, so ask for them), --seed <s>, --anchor <rfc3339>, --age <n>d (history ends n days ago, to test retention), --conversations <n>, --turns <n>, --shape saas|sh-licensed|sh-free, --org name=..,plan=free|licence,users=N[,persona=..][,owner=EMAIL][,admin=no] (repeatable), --into <org-id>/<project-id> (telemetry only, into an existing project), --live, --dry-run, --json, --reveal.

Exit codes: 0 done, 1 a check failed, 2 refused before writing, 4 stalled. A stall (exit 4) saves a checkpoint and prints seedgen's own line; rerun the same flags with --resume, in any hour. haven down --destroy forgets the stack's seed records and logins.

Logins and credentials

  • The end of a seed prints the admin login, org, team and project slugs, the project API key, the personal access token, the SCIM token and the instance admin key. They are masked; --reveal shows them, --json gives one object. Never paste revealed output.
  • Credentials are made up by haven per stack and live in haven's state; no real key and no 1Password. They rotate only on haven down --destroy. A browser signs in with haven browser login --as admin or --as <email> (haven-browser, haven-auth); nobody types the password.
  • haven db logins prints the seeded logins again, masked unless --reveal.
  • The stack home's Seed panel runs the same command for a running stack.

Presets and the neighbours

  • haven db seed <preset> and haven db reset <preset> take the presets (haven-db): demo runs haven db seed --size tiny --persona startup; bare, onboarding, post-onboarding are storage-seed switches.
  • GitHub pull-request fixture (no App): haven db seed demo maps PRs #101 (open) and #102 (merged) on langwatch-seed/checkout to the local dev org; haven sim telemetry send --preset claude-code-events gives a session on #101's branch.
  • The seed guard refuses (exit 2) when a database URL the seed would connect to points anywhere but local dev, so it cannot seed a real database named by .env.
  • Pointers only: the generator is tools/seedgen, the design is dev/docs/plans/seed-2026-10-09.md, and upgrade rehearsals that seed old releases are upgradelab (see the upgrade skill).

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-play/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
74b22a25
Indexed
2026-10-19 19:33

Home - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-10-20 07:49
浙ICP备14020137号-1