菜单
Use when working with the Agentuity CLI itself: installation, authentication, profiles, JSON output, command discovery, schema inspection, non-interactive automation, structured input, and deciding which Agentuity command family to use.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
| name | agentuity-cli |
| description | Use when working with the Agentuity CLI itself: installation, authentication, profiles, JSON output, command discovery, schema inspection, non-interactive automation, structured input, and deciding which Agentuity command family to use. |
| license | Apache-2.0 |
| metadata | {"author":"agentuity","version":"1.0.0"} |
The agentuity CLI manages project setup, local development, deploys, cloud
resources, auth, profiles, and agent-friendly command schemas. When unsure about
flags or response shapes, ask the CLI instead of guessing.
agentuity --version
agentuity auth whoami
agentuity --help
If the user is not authenticated:
agentuity auth login
Headless environments should use documented API-key environment variables or a configured profile. A first-class API-key login flow is tracked as an SDK issue; do not invent unsupported auth commands.
Use these before guessing flags:
agentuity <command> --help
agentuity --help json
agentuity ai schema show
agentuity ai capabilities show
agentuity ai intro
Per-command schema:
agentuity cloud deployment logs --describe
agentuity project import --describe
The CLI schema is useful for agentic tools because commands declare arguments, options, tags, and response shapes.
Use --json for machine-readable output:
agentuity --json project show
agentuity --json cloud deployment list
agentuity --json cloud session list --success=false --count=25
Use --fields to reduce output:
agentuity --json --fields id,name,region project list
Use --input when building commands programmatically:
agentuity --input '{"name":"my-app","framework":"nextjs","confirm":true}' project create
Use --validate with --input to check shape without executing when the command supports validation:
agentuity --validate --input '{"name":"my-app"}' project import
| Need | Command family | Skill |
|---|---|---|
| Create/import/run/build/deploy an app | project, dev, build, deploy | agentuity-project |
| Manage deployments, logs, env, resources, SSH | cloud | agentuity-cloud |
| Use service clients from app code | package installs | agentuity-services |
| Build model-backed features | AI Gateway and provider SDK commands | agentuity-ai |
| Add relational data | cloud db, project add database | agentuity-database |
| Add async work | cloud queue, cloud schedule, cloud webhook, cloud task | agentuity-background-work |
| Manage cloud coding sessions | coder | Agentuity Coder docs |
Useful auth commands:
agentuity auth login
agentuity auth logout
agentuity auth whoami
agentuity auth org select
agentuity auth ssh add --file ~/.ssh/id_rsa.pub
Profiles let users switch account, org, and region context:
agentuity profile list
agentuity profile use <name>
If profile commands do not appear in normal help, use the docs and
agentuity ai schema show to inspect current support. Profile discoverability is
tracked as an SDK issue under the agentic flow label.
For CI and autonomous agents:
agentuity --json project show
agentuity project import --name my-app --org-id <org-id> --confirm
agentuity deploy --json --message "Automated deploy"
Prefer explicit context:
| Context | Prefer |
|---|---|
| Project | run from the app directory or pass --dir / --project-id |
| Organization | pass --org-id or select it in auth/profile setup |
| Region | pass --region or select one before automation |
| Destructive commands | pass --force or --confirm when supported |
The CLI has strong JSON support, but a few command gaps remain. Use bounded polling and explicit timeouts when waiting for deployments or logs.
Use JSON error output in scripts:
agentuity --json --error-format json project show
If a command fails:
--help to verify flags.--describe to inspect schema.--json for structured output.--project-id, --org-id, and --region if context resolution failed.agentuity-cloud.| Mistake | Better approach |
|---|---|
| Guessing CLI flags from memory | Run agentuity <command> --help or --describe |
| Parsing human tables in automation | Use --json and --fields |
| Relying on implicit org/region in CI | Pass --org-id, --region, and project context explicitly |
| Assuming every prompt is safe in non-TTY | Use explicit confirm/force flags where available |
| Teaching unsupported commands | Verify with help or schema output first |
Use when building model-backed Agentuity features, AI routes, structured output, chat, streaming, tool calling, or app-owned state and memory. Covers plain server functions, AIGatewayClient, provider SDK choices, validation, KV-backed history, and safe tool execution.
Use when adding async jobs, queue workers, cron schedules, webhook ingestion, task tracking, long-running workflows, status polling, durable output, or idempotent background processing to an Agentuity app.
Use when managing Agentuity Cloud from the terminal. Covers deployments, deployment logs, environment variables and secrets, regions, project resource linking, cloud resource commands, SSH, SCP, monitoring snapshots, and agent-friendly CLI workarounds.
Use when adding relational data to an Agentuity app. Covers creating or linking managed Postgres, DATABASE_URL, pg, Drizzle ORM, pooling, transactions, migrations, safe parameter binding, and the narrow admin-script role for DBClient.
Use when adding Agentuity code to a framework app and choosing where routes, pages, server functions, config, or service clients belong. Covers Next.js, Nuxt, SvelteKit, Astro, Hono, React Router, Vite with React, and TanStack Start file placement.
Use when creating, importing, running, building, or deploying an Agentuity app. Covers framework-first project structure, agentuity.json, .env setup, agentuity dev, agentuity build, agentuity deploy, monorepo --dir usage, and deployment bundle inspection.