# Qinglong

> Operate a QingLong panel through its official open API. Use for QingLong health checks, env variables, cron tasks, task logs, and controlled panel API calls from AgentDock Skill.

- **Type:** Skill
- **Install:** `agentstack add skill-uvwt-agentdock-qinglong`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [uvwt](https://agentstack.voostack.com/s/uvwt)
- **Installs:** 0
- **Category:** [Cloud & Infrastructure](https://agentstack.voostack.com/c/cloud-infrastructure)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [uvwt](https://github.com/uvwt)
- **Source:** https://github.com/uvwt/agentdock/tree/main/skill-sources/qinglong
- **Website:** https://uvwt.github.io/agentdock-docs/

## Install

```sh
agentstack add skill-uvwt-agentdock-qinglong
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# QingLong Skill

Use this skill to operate a QingLong panel through `/open/...` APIs.

Default local target:

- Base URL: `http://127.0.0.1:5700`
- Data directory: `/Volumes/KIOXIA/Docker/qinglong/data`
- App credentials: read from the QingLong sqlite `Apps` table, using the `system` app.

Override with environment variables when needed:

- `QINGLONG_BASE_URL`
- `QINGLONG_CLIENT_ID`
- `QINGLONG_CLIENT_SECRET`
- `QINGLONG_DATA_DIR`
- `QINGLONG_DB_PATH`

Never print tokens, client secrets, or environment variable values unless the user explicitly asks and the action supports `include_values=true`.

Preferred operations:

- `status`: check Docker compose state, HTTP health, sqlite app credential availability, and token exchange.
- `envs`, `env_create`, `env_update`, `env_delete`, `env_enable`, `env_disable`: manage environment variables.
- `crons`, `cron_detail`, `cron_create`, `cron_update`, `cron_delete`, `cron_run`, `cron_stop`, `cron_enable`, `cron_disable`, `cron_logs`, `cron_log`: manage scheduled tasks and logs.
- `api`: call a QingLong open API path directly for advanced cases.

## 辅助脚本执行

Skill 本体是本说明文档。确需调用包内辅助脚本时，在 Skill 包根目录使用相对路径执行；运行宿主负责切换到包根目录并把所需变量注入当前子进程。

```bash
printf '%s' '{"skill_action":""}' | python3 run.py
```

输入必须是 JSON 对象。写操作仍按本文档中的确认规则执行。

| 动作 | 用途 |
|---|---|
| `status` | Check QingLong local compose state, HTTP health, sqlite app credentials, and token exchange. |
| `envs` | List QingLong environment variables. Values are redacted by default. |
| `env_create` | Create one or more QingLong environment variables. |
| `env_update` | Update a QingLong environment variable. |
| `env_delete` | Delete QingLong environment variables by ids. Requires confirmed=true. |
| `env_enable` | Enable QingLong environment variables by ids. |
| `env_disable` | Disable QingLong environment variables by ids. |
| `crons` | List QingLong cron tasks. |
| `cron_detail` | Get a QingLong cron task by id. |
| `cron_create` | Create a QingLong cron task. |
| `cron_update` | Update a QingLong cron task. |
| `cron_delete` | Delete QingLong cron tasks by ids. Requires confirmed=true. |
| `cron_run` | Run QingLong cron tasks by ids. |
| `cron_stop` | Stop QingLong cron tasks by ids. |
| `cron_enable` | Enable QingLong cron tasks by ids. |
| `cron_disable` | Disable QingLong cron tasks by ids. |
| `cron_logs` | List log files for a QingLong cron task. |
| `cron_log` | Read latest/current log content for a QingLong cron task. |
| `api` | Call a QingLong open API path directly. Paths are relative to /open unless api_prefix is supplied. |

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [uvwt](https://github.com/uvwt)
- **Source:** [uvwt/agentdock](https://github.com/uvwt/agentdock)
- **License:** Apache-2.0
- **Homepage:** https://uvwt.github.io/agentdock-docs/

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-uvwt-agentdock-qinglong
- Seller: https://agentstack.voostack.com/s/uvwt
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.